Keep converted object keys alive while writing UBJSON and BJData

Since #5746, write_ubjson and write_ubjson_iterative pass each object key
to sanitize_utf8_for_write and keep the returned reference. When
object_t::key_type is not string_t but converts to it, the argument is a
temporary that is destroyed at the end of the statement, and the
function returns a reference to it in every case but a sanitized copy,
so the key bytes are read from a dead object (AddressSanitizer:
stack-use-after-scope). Default json and ordered_json are unaffected.

Bind the key to a named object_key_string_t first: a reference when
key_type is string_t, so no copy is added there, and a converted copy
otherwise. A deleted overload of sanitize_utf8_for_write for anything
other than string_t turns a recurrence into a compile error.

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

.github/CONTRIBUTING.md

@@ -111,8 +111,6 @@ context which existing file needs to be extended, and only very few cases requir
 When fixing a bug, edit `unit-regression3.cpp` and add a section referencing the fixed issue.
 `unit-regression2.cpp` holds the older tests; the two files exist because a single one grew large enough for the
 MinGW linker to fail relocating it, so please keep adding to the smaller file rather than growing the larger one.
-Regression tests that call `sax_parse` go into `unit-sax_parse.cpp` instead: every call instantiates the parser and
-the binary reader that recover from errors, which grows a test file considerably.
 
 #### Exceptions
 

.github/workflows/ubuntu.yml

@@ -31,6 +31,51 @@ jobs:
       - name: Build
         run: cmake --build build --target ci_test_gcc
 
+  ci_meson_install:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+      - name: Get latest CMake and ninja
+        uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
+      - name: Check that Meson and pkg-config offer the CMake options
+        run: make check_build_options
+      - name: Install Meson
+        run: pip install meson
+      - name: Install with Meson
+        run: |
+          meson setup build-meson --prefix=${{ github.workspace }}/install
+          meson install -C build-meson
+      - name: Use the installed package with find_package
+        run: |
+          cmake -S tests/cmake_import/project -B build-import -DCMAKE_PREFIX_PATH=${{ github.workspace }}/install
+          cmake --build build-import
+      - name: Install with Meson and non-default options
+        run: |
+          meson setup build-meson-options --prefix=${{ github.workspace }}/install-options -DMultipleHeaders=true -DDiagnostics=true -DGlobalUDLs=false -DDisableTupleReferenceConversion=true -DStrictBinaryUTF8=true -DDeleteDeprecatedFunctions=true
+          meson install -C build-meson-options
+      - name: Check that the options reach the installed files
+        run: |
+          test -d install-options/include/nlohmann/detail
+          cflags=$(PKG_CONFIG_PATH=${{ github.workspace }}/install-options/share/pkgconfig pkg-config --cflags nlohmann_json)
+          echo "$cflags"
+          echo "$cflags" | grep -q -- '-DJSON_DIAGNOSTICS=1'
+          echo "$cflags" | grep -q -- '-DJSON_USE_GLOBAL_UDLS=0'
+          echo "$cflags" | grep -q -- '-DJSON_DISABLE_TUPLE_REFERENCE_CONVERSION=1'
+          echo "$cflags" | grep -q -- '-DJSON_STRICT_BINARY_UTF8=1'
+          echo "$cflags" | grep -q -- '-DJSON_DELETE_DEPRECATED_FUNCTIONS=1'
+          grep -q 'JSON_USE_GLOBAL_UDLS=0;JSON_DISABLE_TUPLE_REFERENCE_CONVERSION=1;JSON_DIAGNOSTICS=1' install-options/share/cmake/nlohmann_json/nlohmann_jsonTargets.cmake
+          grep -q 'JSON_STRICT_BINARY_UTF8=1;JSON_DELETE_DEPRECATED_FUNCTIONS=1' install-options/share/cmake/nlohmann_json/nlohmann_jsonTargets.cmake
+          cmake -S tests/cmake_import/project -B build-import-options -DCMAKE_PREFIX_PATH=${{ github.workspace }}/install-options
+          cmake --build build-import-options
+      - name: Install with Meson and the include directory outside the prefix
+        run: |
+          meson setup build-meson-split --prefix=${{ github.workspace }}/install-split --includedir=${{ github.workspace }}/install-split-dev/include
+          meson install -C build-meson-split
+          cmake -S tests/cmake_import/project -B build-import-split -DCMAKE_PREFIX_PATH=${{ github.workspace }}/install-split
+          cmake --build build-import-split
+
   ci_infer:
     runs-on: ubuntu-latest
     steps:

CMakeLists.txt

@@ -189,7 +189,39 @@ if (MSVC)
     )
 endif()
 
-# Install a pkg-config file, so other tools can find this.
+# Install a pkg-config file, so other tools can find this. It carries the same
+# compile definitions as the target above.
+set(NLOHMANN_JSON_PKGCONFIG_CFLAGS "")
+if (NOT JSON_GlobalUDLs)
+    string(APPEND NLOHMANN_JSON_PKGCONFIG_CFLAGS " -DJSON_USE_GLOBAL_UDLS=0")
+endif()
+if (NOT JSON_ImplicitConversions)
+    string(APPEND NLOHMANN_JSON_PKGCONFIG_CFLAGS " -DJSON_USE_IMPLICIT_CONVERSIONS=0")
+endif()
+if (JSON_DisableEnumSerialization)
+    string(APPEND NLOHMANN_JSON_PKGCONFIG_CFLAGS " -DJSON_DISABLE_ENUM_SERIALIZATION=1")
+endif()
+if (JSON_DisableTupleReferenceConversion)
+    string(APPEND NLOHMANN_JSON_PKGCONFIG_CFLAGS " -DJSON_DISABLE_TUPLE_REFERENCE_CONVERSION=1")
+endif()
+if (JSON_Diagnostics)
+    string(APPEND NLOHMANN_JSON_PKGCONFIG_CFLAGS " -DJSON_DIAGNOSTICS=1")
+endif()
+if (JSON_Diagnostic_Positions)
+    string(APPEND NLOHMANN_JSON_PKGCONFIG_CFLAGS " -DJSON_DIAGNOSTIC_POSITIONS=1")
+endif()
+if (JSON_LegacyDiscardedValueComparison)
+    string(APPEND NLOHMANN_JSON_PKGCONFIG_CFLAGS " -DJSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON=1")
+endif()
+if (JSON_StrictNulHandling)
+    string(APPEND NLOHMANN_JSON_PKGCONFIG_CFLAGS " -DJSON_STRICT_NUL_HANDLING=1")
+endif()
+if (JSON_StrictBinaryUTF8)
+    string(APPEND NLOHMANN_JSON_PKGCONFIG_CFLAGS " -DJSON_STRICT_BINARY_UTF8=1")
+endif()
+if (JSON_DeleteDeprecatedFunctions)
+    string(APPEND NLOHMANN_JSON_PKGCONFIG_CFLAGS " -DJSON_DELETE_DEPRECATED_FUNCTIONS=1")
+endif()
 configure_file(
     "${CMAKE_CURRENT_SOURCE_DIR}/cmake/pkg-config.pc.in"
     "${CMAKE_CURRENT_BINARY_DIR}/${PROJECT_NAME}.pc"

FILES.md

@@ -249,9 +249,31 @@ make BUILD.bazel
 
 The "Check amalgamation" workflow fails if the file is out of date.
 
-### `meson.build`
+### `meson.build` and `meson_options.txt`
 
-The build definition for the [Meson](https://mesonbuild.com) build system.
+Meson build definitions suitable for use as a subproject ("wrap" in Meson terminology).
+
+Projects wishing to use the wrap can execute:
+```sh
+meson wrap install nlohmann_json
+```
+
+Which allows Meson to build from source when a system provided dependency isn't available.
+
+To build directly:
+```sh
+meson setup builddir
+ninja -C builddir
+```
+
+`meson_options.txt` defines the options, which mirror the CMake options that change the library's target (for example,
+`-DDiagnostics=true`). Meson requires this file next to `meson.build`, so it is also part of `include.zip`. `make check_build_options`
+([`tools/check_build_options`](tools/check_build_options/README.md)) checks in CI that both files and the pkg-config files
+stay in sync with the CMake options.
+
+When installing, `meson.build` installs the headers, a pkg-config file, and the CMake package config files, so that
+`find_package(nlohmann_json)` works. As Meson cannot generate `nlohmann_jsonTargets.cmake` itself, it is created from
+the template `cmake/nlohmann_jsonTargets.cmake.in`, which is only used by Meson.
 
 ### `Package.swift`
 

Makefile

@@ -1,4 +1,4 @@
-.PHONY: pretty clean ChangeLog.md release update_hedley update_hedley_undef BUILD.bazel natvis macro_builder_check
+.PHONY: pretty clean ChangeLog.md release update_hedley update_hedley_undef BUILD.bazel natvis macro_builder_check check_build_options
 
 ##########################################################################
 # configuration
@@ -127,6 +127,10 @@ macro_builder_check:
 	diff "$$TMPDIR/paste.hpp" "$$TMPDIR/paste_actual.hpp" || (echo "===================================================================\n  $(MACRO_SCOPE_HPP) (NLOHMANN_JSON_EXPAND..NLOHMANN_JSON_DOUBLE_PASTE63) is out of date!\n  Regenerate it, see tools/macro_builder/README.md.\n===================================================================" ; exit 1); \
 	diff "$$TMPDIR/type_body.hpp" "$$TMPDIR/type_body_actual.hpp" || (echo "===================================================================\n  $(MACRO_SCOPE_HPP) (NLOHMANN_JSON_TYPE_BODY) is out of date!\n  Regenerate it, see tools/macro_builder/README.md.\n===================================================================" ; exit 1)
 
+# check that the Meson build and the pkg-config files offer the options of the CMake target
+check_build_options:
+	python3 tools/check_build_options/check_build_options.py .
+
 # check if file single_include/nlohmann/json.hpp has been amalgamated from the nlohmann sources
 check-amalgamation:
 	@mv $(AMALGAMATED_FILE) $(AMALGAMATED_FILE)~
@@ -184,7 +188,7 @@ json.tar.xz:
 # We use `-X` to make the resulting ZIP file reproducible, see
 # <https://content.pivotal.io/blog/barriers-to-deterministic-reproducible-zip-files>.
 include.zip: BUILD.bazel
-	zip -9 --recurse-paths -X include.zip $(SRCS) $(AMALGAMATED_FILE) $(AMALGAMATED_FWD_FILE) $(AMALGAMATED_LITERALS_FILE) BUILD.bazel MODULE.bazel meson.build LICENSE.MIT
+	zip -9 --recurse-paths -X include.zip $(SRCS) $(AMALGAMATED_FILE) $(AMALGAMATED_FWD_FILE) $(AMALGAMATED_LITERALS_FILE) BUILD.bazel MODULE.bazel meson.build meson_options.txt LICENSE.MIT
 
 # Create the files for a release and add signatures and hashes.
 release: include.zip json.tar.xz

README.md

@@ -494,7 +494,7 @@ bool key(string_t& val);
 bool parse_error(std::size_t position, const std::string& last_token, const detail::exception& ex);
 ```
 
-The return value of each function determines whether parsing should proceed. For `parse_error`, returning `true` [recovers from the error](https://json.nlohmann.me/features/parsing/error_recovery/): the parser repairs the input and continues.
+The return value of each function determines whether parsing should proceed.
 
 To implement your own SAX handler, proceed as follows:
 
@@ -502,7 +502,7 @@ To implement your own SAX handler, proceed as follows:
 2. Create an object of your SAX interface class, e.g. `my_sax`.
 3. Call `bool json::sax_parse(input, &my_sax)`; where the first parameter can be any input like a string or an input stream and the second parameter is a pointer to your SAX interface.
 
-Note the `sax_parse` function only returns a `bool` indicating whether the input was parsed without errors and no SAX event returned `false`. It does not return a  `json` value - it is up to you to decide what to do with the SAX events. Furthermore, no exceptions are thrown in case of a parse error -- it is up to you what to do with the exception object passed to your `parse_error` implementation. Internally, the SAX interface is used for the DOM parser (class `json_sax_dom_parser`) as well as the acceptor (`json_sax_acceptor`), see file [`json_sax.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/json_sax.hpp).
+Note the `sax_parse` function only returns a `bool` indicating the result of the last executed SAX event. It does not return a  `json` value - it is up to you to decide what to do with the SAX events. Furthermore, no exceptions are thrown in case of a parse error -- it is up to you what to do with the exception object passed to your `parse_error` implementation. Internally, the SAX interface is used for the DOM parser (class `json_sax_dom_parser`) as well as the acceptor (`json_sax_acceptor`), see file [`json_sax.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/json_sax.hpp).
 
 ### STL-like access
 

cmake/nlohmann_jsonTargets.cmake.in

@@ -0,0 +1,42 @@
+# Imported target for installations made with Meson (see meson.build).
+#
+# CMake installations generate this file with install(EXPORT ...). Meson cannot
+# do that, but as the library is header-only, the target only needs an include
+# directory, the C++ standard, and the compile definitions of the options that
+# differ from their defaults. Paths are computed relative to this file so that
+# the installation can be relocated (e.g., into a sysroot), unless includedir or
+# datadir is outside the prefix.
+
+if(TARGET @PROJECT_NAME@::@NLOHMANN_JSON_TARGET_NAME@)
+    return()
+endif()
+
+get_filename_component(_IMPORT_PREFIX "${CMAKE_CURRENT_LIST_DIR}/@NLOHMANN_JSON_CONFIG_TO_PREFIX@" ABSOLUTE)
+# As in CMake's generated file: avoid "//include" for an installation to "/".
+if(_IMPORT_PREFIX STREQUAL "/")
+    set(_IMPORT_PREFIX "")
+endif()
+
+add_library(@PROJECT_NAME@::@NLOHMANN_JSON_TARGET_NAME@ INTERFACE IMPORTED)
+set_target_properties(@PROJECT_NAME@::@NLOHMANN_JSON_TARGET_NAME@ PROPERTIES
+    INTERFACE_INCLUDE_DIRECTORIES "@NLOHMANN_JSON_INCLUDE_DIR@"
+)
+if(CMAKE_VERSION VERSION_LESS 3.8)
+    set_target_properties(@PROJECT_NAME@::@NLOHMANN_JSON_TARGET_NAME@ PROPERTIES
+        INTERFACE_COMPILE_FEATURES cxx_range_for
+    )
+else()
+    set_target_properties(@PROJECT_NAME@::@NLOHMANN_JSON_TARGET_NAME@ PROPERTIES
+        INTERFACE_COMPILE_FEATURES cxx_std_11
+    )
+endif()
+
+set(_NLOHMANN_JSON_COMPILE_DEFINITIONS "@NLOHMANN_JSON_COMPILE_DEFINITIONS@")
+if(_NLOHMANN_JSON_COMPILE_DEFINITIONS)
+    set_target_properties(@PROJECT_NAME@::@NLOHMANN_JSON_TARGET_NAME@ PROPERTIES
+        INTERFACE_COMPILE_DEFINITIONS "${_NLOHMANN_JSON_COMPILE_DEFINITIONS}"
+    )
+endif()
+
+unset(_NLOHMANN_JSON_COMPILE_DEFINITIONS)
+unset(_IMPORT_PREFIX)

cmake/pkg-config.pc.in

@@ -4,4 +4,4 @@ includedir=${prefix}/@CMAKE_INSTALL_INCLUDEDIR@
 Name: @PROJECT_NAME@
 Description: JSON for Modern C++
 Version: @PROJECT_VERSION@
-Cflags: -I${includedir}
+Cflags: -I${includedir}@NLOHMANN_JSON_PKGCONFIG_CFLAGS@

docs/mkdocs/docs/api/basic_json/sax_parse.md

@@ -96,9 +96,7 @@ The SAX event lister must follow the interface of [`json_sax`](../json_sax/index
 
 ## Return value
 
-`#!cpp true` if the input was parsed without errors and no SAX event returned `#!cpp false`; `#!cpp false` otherwise.
-In particular, the result is `#!cpp false` for input with errors, even if the SAX parser recovered from all of them
-(see [error recovery](../../features/parsing/error_recovery.md)).
+return value of the last processed SAX event
 
 ## Exception safety
 
@@ -147,7 +145,6 @@ A UTF-8 byte order mark is silently ignored.
 - Added `ignore_trailing_commas` in version 3.13.0.
 - Added `tag_handler` in version 3.13.0.
 - Extended container support (1) to include types with lvalue-only ADL `begin`/`end` (matching `std::begin`/`std::end` semantics) in version 3.13.0.
-- Recovering from parse errors (see [`parse_error`](../json_sax/parse_error.md)) added in version 3.13.0.
 - Extended overload (2) to accept heterogeneous iterator+sentinel pairs (C++20 ranges support) in version 3.13.0.
 - `JSON_PRECISE_STREAM_POSITION` added in version 3.13.0 to optionally leave a `#!cpp std::istream` positioned right
   after the parsed value when `strict` is `#!cpp false`.

docs/mkdocs/docs/api/json_sax/index.md

@@ -7,8 +7,7 @@ struct json_sax;
 
 This class describes the SAX interface used by [sax_parse](../basic_json/sax_parse.md). Each function is called in
 different situations while the input is parsed. The boolean return value informs the parser whether to continue
-processing the input; for [`parse_error`](parse_error.md), it decides whether to
-[recover from the error](../../features/parsing/error_recovery.md).
+processing the input.
 
 For instance, parsing the JSON text `{"a": [1, true]}` triggers the following callbacks, in order:
 

docs/mkdocs/docs/api/json_sax/parse_error.md

@@ -21,18 +21,11 @@ A parse error occurred.
 
 ## Return value
 
-Whether to recover from the error:
-
-- `#!cpp false` stops parsing.
-- `#!cpp true` recovers from the error: the error is repaired and parsing continues. If that is not possible, which
-  happens in the binary formats when the end of the item with the error is unknown, the value read so far is completed
-  and parsing stops. See [error recovery](../../features/parsing/error_recovery.md) for how errors are repaired.
-
-Either way, [`sax_parse`](../basic_json/sax_parse.md) returns `#!cpp false`.
+Whether parsing should proceed (**must return `#!cpp false`**).
 
 ## Examples
 
-??? example "Example: (1) the SAX interface"
+??? example
 
     The example below shows how the SAX interface is used.
 
@@ -46,29 +39,12 @@ Either way, [`sax_parse`](../basic_json/sax_parse.md) returns `#!cpp false`.
     --8<-- "examples/sax_parse.output"
     ```
 
-??? example "Example: (2) recovering from errors"
-
-    The example below shows how a SAX parser recovers from errors.
-
-    ```cpp
-    --8<-- "examples/sax_parse__error_recovery.cpp"
-    ```
-    
-    Output:
-    
-    ```
-    --8<-- "examples/sax_parse__error_recovery.output"
-    ```
-
 ## See also
 
 - [sax_parse](../basic_json/sax_parse.md) - SAX parser
 - [Parsing and Exceptions](../../features/parsing/parse_exceptions.md) - the article on handling parse errors without
   exceptions
-- [Error Recovery](../../features/parsing/error_recovery.md) - the article on recovering from parse errors
 
 ## Version history
 
 - Added in version 3.2.0.
-- Returning `#!cpp true` recovers from the error since version 3.13.0; before, parsing stopped, but the result of
-  [`sax_parse`](../basic_json/sax_parse.md) could be wrong.

docs/mkdocs/docs/api/macros/json_use_implicit_conversions.md

@@ -67,7 +67,7 @@ By default, implicit conversions are enabled.
     `JSON_USE_IMPLICIT_CONVERSIONS` is defined to `0`:
 
     ```cpp
-    using wjson = nlohmann::basic_json<std::map, std::vector, std::wstring>;
+    using wjson = nlohmann::json::with_string_t<std::wstring>;
 
     void load(const nlohmann::json& j);
 

docs/mkdocs/docs/community/roadmap.md

@@ -36,13 +36,26 @@ work items are tracked in the [GitHub milestones](https://github.com/nlohmann/js
 ## API stability
 
 Releases follow [semantic versioning](https://semver.org): a minor or patch release of version 3.x does not break code
-that uses the public API. In particular, a 3.x release does not:
+that uses the public API, unless that code opts in to a change with a macro as described [below](#version-40). In
+particular, a 3.x release does not:
 
-- change the signature of a function (its parameter types, return type, number of parameters, or the const-ness of a
-  member function);
-- remove or rename a function or class;
+- make breaking changes to the signature of a function: the types or order of its existing parameters, its return type,
+  its `noexcept` or `constexpr` specifier, or the const-ness of a member function. New parameters may be added if they
+  have a default value;
+- remove or rename a function or class, or change the template parameters of a public class template;
 - change which exceptions a function throws, or the [exception ids](../home/exceptions.md);
-- change access specifiers or default arguments.
+- change access specifiers, or change or remove existing default arguments. New default arguments may be added;
+- change the JSON type that a valid input parses to, or the text that `dump()` produces for a valid value;
+- accept input that was rejected before, or reject input that was accepted before;
+- change the order in which the keys of an object are iterated. The default type sorts keys, and
+  [`ordered_json`](../api/ordered_json.md) keeps insertion order;
+- change when iterators, pointers, or references are invalidated, or the state of a moved-from `basic_json`;
+- add or remove implicit conversions from `basic_json`;
+- change how `to_json` and `from_json` functions are found, or the behavior of
+  [`adl_serializer`](../api/adl_serializer/index.md);
+- add pure virtual functions to the [`json_sax`](../api/json_sax/index.md) interface;
+- remove, rename, renumber, or add enumerators of `value_t`;
+- remove or rename a documented macro, CMake option, CMake target, or header, or change what a documented macro does.
 
 Exceptions to these rules, for instance when fixing a bug requires changing the exception a function throws, are
 documented in the [release notes](../home/releases.md).
@@ -51,13 +64,14 @@ The following are **not** part of the public API and may change in any release,
 
 - The text of exception messages returned by `what()`. Use the [exception id](../home/exceptions.md) to tell errors
   apart.
-- The ABI, including `sizeof(basic_json)` and the memory layout of its values. Recompile your code when you upgrade the
-  library. The [versioned inline namespace](../features/namespace.md) turns mixing versions into a link error.
+- The ABI, including `sizeof(basic_json)` and the memory layout of its values. The
+  [versioned inline namespace](../features/namespace.md) turns mixing versions into a link error.
+- The hash values returned by `std::hash` for `basic_json`. Numbers that compare equal still hash equally.
 - Everything in namespace `nlohmann::detail`, and macros and type traits that are not documented in the
   [API reference](../api/basic_json/index.md).
 
-Changes that would break the public API are only added behind a macro whose default keeps the 3.x behavior, see
-[Version 4.0](#version-40).
+Breaking changes are only added behind a macro whose default keeps the 3.x behavior. See [Version 4.0](#version-40) and
+the [macro overview](../features/macros.md).
 
 ## Version 4.0
 

docs/mkdocs/docs/examples/contains__json_pointer.cpp

@@ -19,25 +19,9 @@ int main()
               << j.contains("/array/1"_json_pointer) << '\n'
               << j.contains("/array/-"_json_pointer) << '\n'
               << j.contains("/array/4"_json_pointer) << '\n'
-              << j.contains("/baz"_json_pointer) << std::endl;
-
-    try
-    {
-        // try to use an array index with leading '0'
-        j.contains("/array/01"_json_pointer);
-    }
-    catch (const json::parse_error& e)
-    {
-        std::cout << e.what() << '\n';
-    }
-
-    try
-    {
-        // try to use an array index that is not a number
-        j.contains("/array/one"_json_pointer);
-    }
-    catch (const json::parse_error& e)
-    {
-        std::cout << e.what() << '\n';
-    }
+              << j.contains("/baz"_json_pointer) << '\n'
+              // an array index with a leading '0' is not found
+              << j.contains("/array/01"_json_pointer) << '\n'
+              // an array index that is not a number is not found
+              << j.contains("/array/one"_json_pointer) << std::endl;
 }

docs/mkdocs/docs/examples/contains__json_pointer.output

@@ -5,3 +5,5 @@ true
 false
 false
 false
+false
+false

docs/mkdocs/docs/examples/custom_array_type.cpp

@@ -1,11 +1,10 @@
 #include <iostream>
-#include <map>
 
 #include <nlohmann/json.hpp>
 
 #include "custom_array_type.hpp"
 
-using custom_json = nlohmann::basic_json<std::map, custom_array_type>;
+using custom_json = nlohmann::json::with_array_t<custom_array_type>;
 
 int main()
 {

docs/mkdocs/docs/examples/custom_binary_type.cpp

@@ -1,16 +1,10 @@
-#include <cstdint>
 #include <iostream>
-#include <map>
-#include <string>
-#include <vector>
 
 #include <nlohmann/json.hpp>
 
 #include "custom_binary_type.hpp"
 
-using custom_json = nlohmann::basic_json<std::map, std::vector, std::string, bool,
-      std::int64_t, std::uint64_t, double, std::allocator,
-      nlohmann::adl_serializer, custom_binary_type>;
+using custom_json = nlohmann::json::with_binary_t<custom_binary_type>;
 
 int main()
 {

docs/mkdocs/docs/examples/custom_object_type.cpp

@@ -1,12 +1,11 @@
 #include <iostream>
 #include <type_traits>
-#include <vector>
 
 #include <nlohmann/json.hpp>
 
 #include "custom_object_type.hpp"
 
-using custom_json = nlohmann::basic_json<custom_object_type, std::vector>;
+using custom_json = nlohmann::json::with_object_t<custom_object_type>;
 
 int main()
 {

docs/mkdocs/docs/examples/custom_string_type.cpp

@@ -1,12 +1,10 @@
 #include <iostream>
-#include <map>
-#include <vector>
 
 #include <nlohmann/json.hpp>
 
 #include "custom_string_type.hpp"
 
-using custom_json = nlohmann::basic_json<std::map, std::vector, custom_string_type>;
+using custom_json = nlohmann::json::with_string_t<custom_string_type>;
 
 int main()
 {

docs/mkdocs/docs/examples/parse_error.cpp

@@ -8,7 +8,7 @@ int main()
     try
     {
         // parsing input with a syntax error
-        json::parse("[1,2,3,]");
+        json j = json::parse("[1,2,3,]");
     }
     catch (const json::parse_error& e)
     {

docs/mkdocs/docs/examples/sax_parse__error_recovery.cpp

@@ -1,43 +0,0 @@
-#include <iostream>
-#include <iomanip>
-#include <nlohmann/json.hpp>
-
-using json = nlohmann::json;
-
-// a SAX parser that creates a JSON value like json::parse does, but that
-// recovers from parse errors instead of stopping at the first one
-class recovering_parser : public nlohmann::detail::json_sax_dom_parser<json>
-{
-  public:
-    explicit recovering_parser(json& result)
-        : nlohmann::detail::json_sax_dom_parser<json>(result, false)
-    {}
-
-    bool parse_error(std::size_t position,
-                     const std::string& /*last_token*/,
-                     const json::exception& ex)
-    {
-        std::cout << "byte " << position << ": " << ex.what() << '\n';
-
-        // repair the input and continue
-        return true;
-    }
-};
-
-int main()
-{
-    // JSON text with several mistakes that ends too early
-    const std::string text = R"({
-    "name": "Hello World",
-    "tags": ["a" "b",],
-    "valid": tru,
-    "size": 1.,
-    "nested": {"x": 1)";
-
-    json result;
-    recovering_parser sax(result);
-    const bool valid = json::sax_parse(text, &sax);
-
-    std::cout << "\nvalid JSON: " << std::boolalpha << valid << '\n'
-              << std::setw(4) << result << std::endl;
-}

docs/mkdocs/docs/examples/sax_parse__error_recovery.output

@@ -1,19 +0,0 @@
-byte 49: [json.exception.parse_error.101] parse error at line 3, column 20: syntax error while parsing array - unexpected string literal; expected ']'
-byte 51: [json.exception.parse_error.101] parse error at line 3, column 22: syntax error while parsing value - unexpected ']'; expected '[', '{', or a literal
-byte 70: [json.exception.parse_error.101] parse error at line 4, column 17: syntax error while parsing value - invalid literal; last read: '"valid": tru,'
-byte 86: [json.exception.parse_error.101] parse error at line 5, column 15: syntax error while parsing value - invalid number; expected digit after '.'; last read: '1.,'
-byte 109: [json.exception.parse_error.101] parse error at line 6, column 22: syntax error while parsing object - unexpected end of input; expected '}'
-
-valid JSON: false
-{
-    "name": "Hello World",
-    "nested": {
-        "x": 1
-    },
-    "size": 1,
-    "tags": [
-        "a",
-        "b"
-    ],
-    "valid": null
-}

docs/mkdocs/docs/features/parsing/error_recovery.md

@@ -1,122 +0,0 @@
-# Error Recovery
-
-By default, parsing stops at the first error. With the [SAX interface](sax_interface.md), you can instead ask the
-parser to *recover*: to repair the error and continue, so that you get as much as possible out of malformed input, for
-instance a file that was cut off, JSON edited by hand, or the output of a language model.
-
-## Recovering from errors
-
-The SAX parser's [`parse_error`](../../api/json_sax/parse_error.md) function is called for every error. Its return value
-decides what happens next:
-
-- `#!cpp false` stops parsing. This is what the SAX parsers of the library do, so [`parse`](../../api/basic_json/parse.md)
-  and [`accept`](../../api/basic_json/accept.md) never recover.
-- `#!cpp true` repairs the error and continues parsing.
-
-When recovering, the SAX parser still receives well-formed events: every `start_object` or `start_array` is followed by
-the matching `end_object` or `end_array`, and every `key` is followed by exactly one value. A SAX parser that creates a
-JSON value, such as the one in the example below, therefore gets a complete value. Parsing always ends, and
-[`sax_parse`](../../api/basic_json/sax_parse.md) returns `#!cpp false` for input that is not valid JSON, even if every
-error was repaired. Each token is reported at most once, and the SAX parser can stop at any error by returning
-`#!cpp false`.
-
-!!! example
-
-    The example below derives a SAX parser from the library's parser for `json` values (`json_sax_dom_parser`),
-    and recovers from all errors.
-
-    ```cpp
-    --8<-- "examples/sax_parse__error_recovery.cpp"
-    ```
-    
-    Output:
-    
-    ```
-    --8<-- "examples/sax_parse__error_recovery.output"
-    ```
-
-## How errors are repaired
-
-Each error is repaired with the smallest local edit: a missing separator is inserted, a stray token is removed, what can
-be read of a broken string or number is kept, and a value that cannot be read at all becomes `#!json null`.
-
-| Mistake                   | Repair                                                                         | Example                                  | Result                     |
-|---------------------------|--------------------------------------------------------------------------------|------------------------------------------|----------------------------|
-| missing `,` or `:`        | inserted                                                                       | `#!json [1 2]`, `#!json {"a" 1}`         | `[1,2]`, `{"a":1}`         |
-| missing value             | `#!json null` for an object key or between commas in an array                  | `#!json {"a":}`, `#!json [1,,2]`         | `{"a":null}`, `[1,null,2]` |
-| trailing comma            | removed                                                                        | `#!json [1,2,]`                          | `[1,2]`                    |
-| broken string             | invalid escapes and bytes are replaced (see below); a line break ends the string | `#!json ["a\qb"]`                        | `["aqb"]`                  |
-| broken number             | the longest valid beginning is kept                                            | `#!json [1., 2e+]`                       | `[1,2]`                    |
-| unreadable value          | `#!json null`                                                                  | `#!json [1, NaN, tru]`                   | `[1,null,null]`            |
-| number too large          | passed as infinity, together with its text                                     | `#!json [1e999]`                         | infinity (see below)       |
-| stray `:`                 | removed                                                                        | `#!json ["a":1]`                         | `["a",1]`                  |
-| member without a key      | skipped up to the next `,` or `}`                                              | `#!json {1:2, "b":3}`                    | `{"b":3}`                  |
-| wrong closing bracket     | closes the innermost array or object                                           | `#!json {"a":[1,2}, "b":3}`              | `{"a":[1,2],"b":3}`        |
-| input ends too early      | all open arrays and objects are closed                                         | `#!json {"a":[1,2`                       | `{"a":[1,2]}`              |
-| text before the value     | skipped                                                                        | `#!json )]}'{"a":1}`                     | `{"a":1}`                  |
-
-In a string, an unknown escape like `\q` stands for the escaped character (`q`), as in JavaScript. An invalid `\u`
-escape, a lone surrogate, and ill-formed UTF-8 are each replaced by U+FFFD (REPLACEMENT CHARACTER), and control
-characters are kept. A string without its closing quote ends at the next line break or at the end of the input.
-
-The input after the top-level value is not repaired: as without recovery, it is reported as an error, and parsing stops.
-
-## Binary formats
-
-The binary formats ([BJData](../binary_formats/bjdata.md), [BON8](../binary_formats/bon8.md),
-[BSON](../binary_formats/bson.md), [CBOR](../binary_formats/cbor.md), [MessagePack](../binary_formats/messagepack.md),
-and [UBJSON](../binary_formats/ubjson.md)) have no delimiters to find the next value by. So what can be repaired depends
-on whether the end of the item with the error is known, a distinction that
-[RFC 8949, Section 5.3](https://www.rfc-editor.org/rfc/rfc8949.html#section-5.3) makes for CBOR, too.
-
-If the item is complete, but cannot be passed on as it is, it is replaced, and parsing continues after it:
-
-| Mistake                                                             | Formats                 | Repair                                                                  |
-|---------------------------------------------------------------------|-------------------------|-------------------------------------------------------------------------|
-| tag, if `tag_handler` is `cbor_tag_handler_t::error` (the default)  | CBOR                    | ignored                                                                 |
-| simple value other than `false`, `true`, and `null`, like undefined | CBOR                    | `#!json null`                                                           |
-| number too large for a custom `number_float_t`, like `float`        | all                     | infinity                                                                |
-| character (`C`) that is not ASCII                                   | BJData, UBJSON          | U+FFFD                                                                  |
-| invalid high-precision number (`H`)                                 | BJData, UBJSON          | the longest valid beginning is kept, as for JSON text, or `#!json null` |
-| high-precision number too large                                     | BJData, UBJSON          | passed as infinity, together with its text                              |
-| object key that is not a string                                     | BON8, CBOR, MessagePack | the member is skipped                                                   |
-| element of a type the library does not read, like ObjectId or date  | BSON                    | `#!json null`                                                           |
-| string without its terminator                                       | BSON                    | kept                                                                    |
-| document whose size does not match its content                      | BSON                    | kept                                                                    |
-
-CBOR tags and simple values are repaired as [RFC 8949, Section 6.1](https://www.rfc-editor.org/rfc/rfc8949.html#section-6.1)
-suggests for converting CBOR to JSON. By default, [`sax_parse`](../../api/basic_json/sax_parse.md) reports every tag as
-an error; when recovering, tags are then ignored like with
-[`cbor_tag_handler_t::ignore`](../../api/basic_json/cbor_tag_handler_t.md). Strings that are not valid UTF-8 are no
-error: like [`from_cbor`](../../api/basic_json/from_cbor.md) and the other functions by default, `sax_parse` passes
-them on as they are.
-
-After any other error, the end of the item is unknown: the input ended, a byte is not a valid type marker, or a size
-cannot be right. Parsing then stops, and the value read so far is completed: a key that waits for its value gets
-`#!json null`, and all open arrays and objects are closed. This keeps everything before the error of an input that was
-cut off. The exception is BSON, which stores the size of every document: an element whose end is unknown gets
-`#!json null`, the rest of its document is skipped, and parsing continues after the document.
-
-## Limitations
-
-- A repair is a guess. For example, `#!json {"a" "b": 1}` could be meant as `#!json {"a": "b"}` or as
-  `#!json {"a": null, "b": 1}`; it is repaired to the former. Treat recovered values as a best effort, and check the
-  reported errors.
-- A closing bracket always closes the innermost array or object. If a bracket is missing rather than wrong, the
-  repair differs from the intention: `#!json {"a": {"b": [1, 2}, "c": 3}` is repaired to
-  `#!json {"a": {"b": [1, 2], "c": 3}}`, although `#!json {"a": {"b": [1, 2]}, "c": 3}` may have been meant.
-- Keys without quotes, and strings in single quotes, are not supported; such members are skipped.
-- In the binary formats, a member that is skipped because its key is not a string is lost, and so are the elements of a
-  BSON document after one whose end is unknown.
-- A number that is too large for `number_float_t` is passed as positive or negative infinity. The SAX parser's
-  `number_float` also gets the number's text, but a JSON value cannot store it, and
-  [`dump`](../../api/basic_json/dump.md) serializes infinity as `#!json null`.
-- When parsing is not strict (see [`sax_parse`](../../api/basic_json/sax_parse.md)), a repair may read parts of the
-  input after the value, for instance of the next value in a stream of concatenated values.
-
-## See also
-
-- [SAX interface](sax_interface.md) - implement a custom SAX handler
-- [`parse_error`](../../api/json_sax/parse_error.md) - the SAX event for parse errors
-- [`sax_parse`](../../api/basic_json/sax_parse.md) - generate SAX events
-- [parsing and exceptions](parse_exceptions.md) - control error handling

docs/mkdocs/docs/features/parsing/index.md

@@ -75,7 +75,7 @@ You can influence a DOM parse without switching to the SAX interface by passing
 When the input is not valid JSON, the `parse` function throws an exception by default. If exceptions are undesired or
 unavailable, the parser can instead return a discarded value, or [`accept`](../../api/basic_json/accept.md) can be used
 to only check whether an input is valid JSON. See [parsing and exceptions](parse_exceptions.md) for the available
-options. To get as much as possible out of malformed input, a SAX parser can [recover from errors](error_recovery.md).
+options.
 
 ## See also
 
@@ -86,5 +86,4 @@ options. To get as much as possible out of malformed input, a SAX parser can [re
 - [parser callbacks](parser_callbacks.md) - influence the parsing by a callback function
 - [SAX interface](sax_interface.md) - implement a custom SAX handler
 - [parsing and exceptions](parse_exceptions.md) - control error handling
-- [error recovery](error_recovery.md) - get as much as possible out of malformed input
 - [parsing untrusted input](untrusted_input.md) - what to consider when parsing input from untrusted sources

docs/mkdocs/docs/features/parsing/parse_exceptions.md

@@ -64,8 +64,7 @@ bool parse_error(std::size_t position,
                  const json::exception& ex);
 ```
 
-The return value decides whether to stop parsing (`#!cpp false`) or to repair the error and continue
-(`#!cpp true`); see [error recovery](error_recovery.md) for the latter.
+The return value indicates whether the parsing should continue, so the function should usually return `#!cpp false`.
 
 ??? example "Example: report parse errors without exceptions"
 

docs/mkdocs/docs/features/parsing/sax_interface.md

@@ -60,8 +60,7 @@ bool key(string_t& val);
 bool parse_error(std::size_t position, const std::string& last_token, const json::exception& ex);
 ```
 
-The return value of each function determines whether parsing should proceed. For `parse_error`, returning
-`#!cpp true` [recovers from the error](error_recovery.md).
+The return value of each function determines whether parsing should proceed.
 
 To implement your own SAX handler, proceed as follows:
 
@@ -69,7 +68,7 @@ To implement your own SAX handler, proceed as follows:
 2. Create an object of your SAX interface class, e.g. `my_sax`.
 3. Call `#!cpp bool json::sax_parse(input, &my_sax);` where the first parameter can be any input like a string or an input stream and the second parameter is a pointer to your SAX interface.
 
-Note the `sax_parse` function only returns a `#!cpp bool` indicating whether the input was parsed without errors and no SAX event returned `#!cpp false`. It does not return `json` value - it is up to you to decide what to do with the SAX events. Furthermore, no exceptions are thrown in case of a parse error - it is up to you what to do with the exception object passed to your `parse_error` implementation. Internally, the SAX interface is used for the DOM parser (class `json_sax_dom_parser`) as well as the acceptor (`json_sax_acceptor`), see file `json_sax.hpp`.
+Note the `sax_parse` function only returns a `#!cpp bool` indicating the result of the last executed SAX event. It does not return `json` value - it is up to you to decide what to do with the SAX events. Furthermore, no exceptions are thrown in case of a parse error - it is up to you what to do with the exception object passed to your `parse_error` implementation. Internally, the SAX interface is used for the DOM parser (class `json_sax_dom_parser`) as well as the acceptor (`json_sax_acceptor`), see file `json_sax.hpp`.
 
 ## See also
 

docs/mkdocs/docs/features/types/number_handling.md

@@ -351,9 +351,8 @@ The number types can be changed with template parameters.
 
     A `basic_json` type that uses `#!c long double` as floating-point type.
 
-    ```cpp hl_lines="2"
-    using json_ld = nlohmann::basic_json<std::map, std::vector, std::string, bool,
-                                         std::int64_t, std::uint64_t, long double>;
+    ```cpp hl_lines="1"
+    using json_ld = nlohmann::json::with_float_t<long double>;
     ```
 
     Note values should then be parsed with `json_ld::parse` rather than `json::parse` as the latter would parse

docs/mkdocs/docs/features/types/template_parameters.md

@@ -8,6 +8,10 @@ these requirements so they do not have to be discovered by trial and error. Each
 that are known to work for that parameter and the ones that do not, checked against Boost 1.83, Abseil 20250127.0,
 Folly, EASTL 3.21, `ankerl::unordered_dense`, `phmap`, `gtl`, `robin_hood`, `tsl::ordered_map`, and Qt 6.
 
+To change a single template parameter and keep the others, use the member alias templates
+[`with_*_t`](../../api/basic_json/with_t.md); for instance, `nlohmann::json::with_float_t<long double>` is `json` with
+`#!cpp long double` as [`number_float_t`](../../api/basic_json/number_float_t.md).
+
 ## How to read this page
 
 Requirements are split into two groups:
@@ -143,7 +147,7 @@ struct unordered_map_object
     using base_t::base_t;
 };
 
-using unordered_json = nlohmann::basic_json<unordered_map_object>;
+using unordered_json = nlohmann::json::with_object_t<unordered_map_object>;
 ```
 
 Whether `#!cpp std::unordered_map` can be instantiated at all depends on the standard library: `object_t` is formed
@@ -176,7 +180,7 @@ struct flat_hash_object
     using base_t::base_t;
 };
 
-using flat_hash_json = nlohmann::basic_json<flat_hash_object>;
+using flat_hash_json = nlohmann::json::with_object_t<flat_hash_object>;
 ```
 
 `absl::node_hash_map` keeps references to the mapped values valid across insertions; `absl::flat_hash_map` does not,

docs/mkdocs/docs/integration/migration_guide.md

@@ -116,7 +116,7 @@ function to use instead.
     === "Deprecated"
   
           ```cpp
-          using my_json = nlohmann::basic_json<std::map, std::vector, my_string_type>;
+          using my_json = nlohmann::json::with_string_t<my_string_type>;
           nlohmann::json_pointer<my_json> ptr("/foo/bar/1");
           ```
   

docs/mkdocs/docs/integration/package_managers.md

@@ -125,10 +125,24 @@ meson wrap install nlohmann_json
 Please see the Meson project for any issues regarding the packaging.
 
 The provided `meson.build` can also be used as an alternative to CMake for installing `nlohmann_json` system-wide in
-which case a [pkg-config](pkg-config.md) file is installed. To use it, have your build system require the
-`nlohmann_json` pkg-config dependency. In Meson, it is preferred to use the
-[`dependency()`](https://mesonbuild.com/Reference-manual.html#dependency) object with a subproject fallback, rather than
-using the subproject directly.
+which case a [pkg-config](pkg-config.md) file and the CMake package config files are installed. To use it, have your build system require
+the `nlohmann_json` pkg-config dependency, or use [`find_package(nlohmann_json)`](cmake.md#external) in CMake. In Meson,
+it is preferred to use the [`dependency()`](https://mesonbuild.com/Reference-manual.html#dependency) object with a
+subproject fallback, rather than using the subproject directly.
+
+The options that change the library's configuration are available in Meson as well, named like the
+[CMake options](cmake.md#cmake-options) without the `JSON_` prefix: `MultipleHeaders`, `GlobalUDLs`,
+`ImplicitConversions`, `DisableEnumSerialization`, `DisableTupleReferenceConversion`, `Diagnostics`,
+`Diagnostic_Positions`, `LegacyDiscardedValueComparison`, `StrictNulHandling`, `StrictBinaryUTF8`, and
+`DeleteDeprecatedFunctions`. They have the same defaults as in CMake, except that
+`MultipleHeaders` is `false`. Set them with `-D` when setting up the build, or with the subproject name as prefix when
+the library is used as a subproject:
+
+```shell
+meson setup build -Dnlohmann_json:Diagnostics=true
+```
+
+The resulting compile definitions are part of the Meson dependency, the pkg-config file, and the CMake target.
 
 ??? example "Example: Wrap"
 

docs/mkdocs/mkdocs.yml

@@ -88,7 +88,6 @@ nav:
       - features/performance.md
       - Parsing:
           - features/parsing/index.md
-          - features/parsing/error_recovery.md
           - features/parsing/json_lines.md
           - features/parsing/parse_exceptions.md
           - features/parsing/parser_callbacks.md

include/nlohmann/detail/bit_ops.hpp

@@ -9,12 +9,15 @@
 #pragma once
 
 #include <cstdint> // uint64_t
+#if !defined(__SIZEOF_INT128__) && defined(_MSC_VER) && (defined(_M_X64) || defined(_M_ARM64))
+    #include <intrin0.h> // __umulh, _umul128
+#endif
 
 #include <nlohmann/detail/abi_macros.hpp>
 
 // Portable bit-level helpers for the number and string scanners. They use
-// compiler builtins where available and plain C++ otherwise, so they need no
-// platform headers and work regardless of byte order.
+// compiler builtins or platform-specific intrinsics where available and plain
+// C++ otherwise, so they work regardless of byte order.
 
 NLOHMANN_JSON_NAMESPACE_BEGIN
 namespace detail
@@ -52,6 +55,12 @@ inline uint128_parts full_multiplication(std::uint64_t a, std::uint64_t b) noexc
     __extension__ using uint128 = unsigned __int128;
     const uint128 r = static_cast<uint128>(a) * b;
     return {static_cast<std::uint64_t>(r), static_cast<std::uint64_t>(r >> 64u)};
+#elif defined(_MSC_VER) && defined(_M_X64)
+    std::uint64_t high = 0;
+    const std::uint64_t low = _umul128(a, b, &high);
+    return {low, high};
+#elif defined(_MSC_VER) && defined(_M_ARM64)
+    return {a * b, __umulh(a, b)};
 #else
     const std::uint64_t a_lo = a & 0xFFFFFFFFu;
     const std::uint64_t a_hi = a >> 32u;

include/nlohmann/detail/input/json_sax.hpp

@@ -132,9 +132,7 @@ struct json_sax
     @param[in] position    the position in the input where the error occurs
     @param[in] last_token  the last read token
     @param[in] ex          an exception object describing the error
-    @return whether to recover from the error: false stops parsing; true
-            repairs the error and continues, or, if that is not possible,
-            stops after completing the value read so far
+    @return whether parsing should proceed (must return false)
     */
     virtual bool parse_error(std::size_t position,
                              const std::string& last_token,
@@ -271,12 +269,9 @@ a pointer to the respective array or object for each recursion depth.
 After successful parsing, the value that is passed by reference to the
 constructor contains the parsed value.
 
-@tparam BasicJsonType     the JSON type
-@tparam InputAdapterType  the input adapter of the lexer that can be passed to
-                          the constructor to record diagnostic positions; it
-                          does not matter if no lexer is passed
+@tparam BasicJsonType  the JSON type
 */
-template<typename BasicJsonType, typename InputAdapterType = string_input_adapter_type>
+template<typename BasicJsonType, typename InputAdapterType>
 class json_sax_dom_parser
 {
   public:
@@ -523,7 +518,7 @@ class json_sax_dom_parser
     lexer_t* m_lexer_ref = nullptr;
 };
 
-template<typename BasicJsonType, typename InputAdapterType = string_input_adapter_type>
+template<typename BasicJsonType, typename InputAdapterType>
 class json_sax_dom_callback_parser
 {
   public:

include/nlohmann/detail/input/lexer.hpp

@@ -10,7 +10,7 @@
 
 #include <array> // array
 #include <cstddef> // size_t
-#include <cstdint> // uint8_t, uint32_t
+#include <cstdint> // uint32_t
 #include <cstdio> // snprintf
 #include <initializer_list> // initializer_list
 #include <string> // char_traits, string
@@ -439,16 +439,8 @@ class lexer : public lexer_base<BasicJsonType>
                             if (0xD800 <= codepoint1 && codepoint1 <= 0xDBFF)
                             {
                                 // expect next \uxxxx entry
-                                if (JSON_HEDLEY_LIKELY(get() == '\\'))
+                                if (JSON_HEDLEY_LIKELY(get() == '\\' && get() == 'u'))
                                 {
-                                    if (JSON_HEDLEY_UNLIKELY(get() != 'u'))
-                                    {
-                                        // current is the character escaped by the backslash
-                                        error_message = "invalid string: surrogate U+D800..U+DBFF must be followed by U+DC00..U+DFFF";
-                                        string_error_resume = resume_kind::escaped_character;
-                                        return token_type::parse_error;
-                                    }
-
                                     const int codepoint2 = get_codepoint();
 
                                     if (JSON_HEDLEY_UNLIKELY(codepoint2 == -1))
@@ -473,11 +465,7 @@ class lexer : public lexer_base<BasicJsonType>
                                     }
                                     else
                                     {
-                                        // the second escape was read completely and is a
-                                        // code point of its own
                                         error_message = "invalid string: surrogate U+D800..U+DBFF must be followed by U+DC00..U+DFFF";
-                                        string_error_resume = resume_kind::after_escape;
-                                        string_error_codepoint = codepoint2;
                                         return token_type::parse_error;
                                     }
                                 }
@@ -491,9 +479,7 @@ class lexer : public lexer_base<BasicJsonType>
                             {
                                 if (JSON_HEDLEY_UNLIKELY(0xDC00 <= codepoint1 && codepoint1 <= 0xDFFF))
                                 {
-                                    // the escape was read completely
                                     error_message = "invalid string: surrogate U+DC00..U+DFFF must follow U+D800..U+DBFF";
-                                    string_error_resume = resume_kind::after_escape;
                                     return token_type::parse_error;
                                 }
                             }
@@ -2147,574 +2133,6 @@ scan_number_done:
         }
     }
 
-  public:
-    /////////////////////
-    // error recovery
-    /////////////////////
-
-    /*!
-    @brief make the best of the token that scan() rejected
-
-    Called by the parser after scan() returned token_type::parse_error and the
-    SAX parser asked to recover from the error (see #3989). Keeps what can be
-    read of the token and skips the rest:
-
-    - A string keeps its characters. An unknown escape stands for the escaped
-      character itself (as in JavaScript), an invalid Unicode escape and ill-formed
-      UTF-8 become U+FFFD, and a control character is kept. A line break or the
-      end of the input ends a string that lacks its closing quote.
-    - A number keeps its longest valid prefix, e.g. `1` for `1.` or `1e+`.
-    - A block comment that is not closed runs to the end of the input.
-    - Anything else is skipped.
-
-    The rest of an invalid token is skipped up to the next delimiter
-    (whitespace, a structural character, or a quote). A delimiter that the
-    invalid token consumed is returned to the input, so that the next scan()
-    reads it.
-
-    @return token_type::value_string or a number token type if a string or a
-            number could be read, token_type::end_of_input for a block comment
-            that is not closed, token_type::uninitialized otherwise
-    */
-    token_type recover_token()
-    {
-        const resume_kind resume = string_error_resume;
-        const int codepoint = string_error_codepoint;
-        string_error_resume = resume_kind::character;
-        string_error_codepoint = -1;
-
-        if (error_message_starts_with("invalid string"))
-        {
-            return recover_string(resume, codepoint);
-        }
-
-        if (error_message_starts_with("invalid number"))
-        {
-            return recover_number();
-        }
-
-        if (error_message_starts_with("invalid comment; missing"))
-        {
-            // the comment runs to the end of the input
-            return token_type::end_of_input;
-        }
-
-        skip_to_delimiter();
-        return token_type::uninitialized;
-    }
-
-    /*!
-    @brief return the token that scan() read last to the input, so that the
-           next scan() reads it again
-
-    Called by the parser when recovering from an error. The token must be a
-    single character (',', ':', '[', ']', '{', or '}') or the end of the
-    input, and scan() must have read it last.
-    */
-    void unget_token()
-    {
-        JSON_ASSERT(!next_unget);
-        unget();
-    }
-
-    /*!
-    @brief let the token string for the next error begin at the current character
-
-    The token string of an error reaches back to the beginning of the last
-    string or number. After an error, the parser calls this function so that
-    the next error does not report (and, with many errors, copy) everything
-    read since then.
-    */
-    void restart_token_string()
-    {
-        restart_token_string_impl(std::integral_constant<bool, lazy_token_string> {});
-    }
-
-  private:
-    /// how recover_string() continues after the error scan_string() reported
-    enum class resume_kind : std::uint8_t
-    {
-        /// current is the next character of the string (or the end of input)
-        character,
-        /// current is the character escaped by the preceding backslash
-        escaped_character,
-        /// current is the last character of a complete escape
-        after_escape
-    };
-
-    /// whether error_message begins with @a prefix
-    bool error_message_starts_with(const char* prefix) const noexcept
-    {
-        const char* message = error_message;
-        while (*prefix != '\0')
-        {
-            if (*message++ != *prefix++)
-            {
-                return false;
-            }
-        }
-        return true;
-    }
-
-    /// whether current ends an invalid token (see recover_token())
-    bool current_is_delimiter() const noexcept
-    {
-        switch (current)
-        {
-            case ' ':
-            case '\t':
-            case '\n':
-            case '\r':
-            case '[':
-            case ']':
-            case '{':
-            case '}':
-            case ',':
-            case ':':
-            case '\"':
-#if !JSON_STRICT_NUL_HANDLING
-            case '\0':
-#endif
-            case char_traits<char_type>::eof():
-                return true;
-
-            case '/':
-                return ignore_comments;
-
-            default:
-                return false;
-        }
-    }
-
-    /// skip the rest of an invalid token and return its delimiter to the input
-    void skip_to_delimiter()
-    {
-        while (!current_is_delimiter())
-        {
-            get();
-        }
-
-        if (current != char_traits<char_type>::eof())
-        {
-            unget();
-        }
-    }
-
-    /// append U+FFFD REPLACEMENT CHARACTER to token_buffer
-    void add_replacement_character()
-    {
-        add(0xEF);
-        add(0xBF);
-        add(0xBD);
-    }
-
-    /// append the UTF-8 encoding of @a codepoint (not a surrogate) to token_buffer
-    void add_codepoint(const int codepoint)
-    {
-        JSON_ASSERT(0x00 <= codepoint && codepoint <= 0x10FFFF);
-        const auto cp = static_cast<unsigned int>(codepoint);
-        if (cp < 0x80)
-        {
-            add(static_cast<char_int_type>(cp));
-        }
-        else if (cp <= 0x7FF)
-        {
-            add(static_cast<char_int_type>(0xC0u | (cp >> 6u)));
-            add(static_cast<char_int_type>(0x80u | (cp & 0x3Fu)));
-        }
-        else if (cp <= 0xFFFF)
-        {
-            add(static_cast<char_int_type>(0xE0u | (cp >> 12u)));
-            add(static_cast<char_int_type>(0x80u | ((cp >> 6u) & 0x3Fu)));
-            add(static_cast<char_int_type>(0x80u | (cp & 0x3Fu)));
-        }
-        else
-        {
-            add(static_cast<char_int_type>(0xF0u | (cp >> 18u)));
-            add(static_cast<char_int_type>(0x80u | ((cp >> 12u) & 0x3Fu)));
-            add(static_cast<char_int_type>(0x80u | ((cp >> 6u) & 0x3Fu)));
-            add(static_cast<char_int_type>(0x80u | (cp & 0x3Fu)));
-        }
-    }
-
-    /// append a code point read from a Unicode escape; a surrogate becomes U+FFFD
-    void add_escaped_codepoint(const int codepoint)
-    {
-        if (0xD800 <= codepoint && codepoint <= 0xDFFF)
-        {
-            add_replacement_character();
-        }
-        else
-        {
-            add_codepoint(codepoint);
-        }
-    }
-
-    /*!
-    @brief remove an incomplete UTF-8 sequence from the end of token_buffer
-
-    next_byte_in_range() adds the bytes of a sequence as it checks them, so
-    when it rejects a byte, the beginning of the sequence is already in
-    token_buffer, which otherwise holds only complete sequences.
-
-    @return whether an incomplete sequence was removed
-    */
-    bool remove_incomplete_utf8_sequence()
-    {
-        std::size_t lead = token_buffer.size();
-        std::size_t continuation_bytes = 0;
-        while (lead > 0 && continuation_bytes < 3
-                && (static_cast<unsigned char>(token_buffer[lead - 1]) & 0xC0u) == 0x80u)
-        {
-            --lead;
-            ++continuation_bytes;
-        }
-        if (lead == 0)
-        {
-            return false;
-        }
-
-        const auto lead_byte = static_cast<unsigned char>(token_buffer[lead - 1]);
-        std::size_t expected = 0;
-        if (lead_byte >= 0xF0)
-        {
-            expected = 3;
-        }
-        else if (lead_byte >= 0xE0)
-        {
-            expected = 2;
-        }
-        else if (lead_byte >= 0xC0)
-        {
-            expected = 1;
-        }
-        if (continuation_bytes >= expected)
-        {
-            return false;
-        }
-
-        token_buffer.resize(lead - 1);
-        return true;
-    }
-
-    /*!
-    @brief read the UTF-8 sequence that begins with current, which is not ASCII
-    @return whether the next character must be read; false if current still
-            needs to be handled, because it does not belong to the sequence
-    */
-    bool recover_utf8_sequence()
-    {
-        // the number of continuation bytes and the range of the first one;
-        // see the ranges in scan_string()
-        std::size_t count = 0;
-        char_int_type low = 0x80;
-        char_int_type high = 0xBF;
-        if (current >= 0xC2 && current <= 0xDF)
-        {
-            count = 1;
-        }
-        else if (current >= 0xE0 && current <= 0xEF)
-        {
-            count = 2;
-            low = (current == 0xE0) ? 0xA0 : 0x80;
-            high = (current == 0xED) ? 0x9F : 0xBF;
-        }
-        else if (current >= 0xF0 && current <= 0xF4)
-        {
-            count = 3;
-            low = (current == 0xF0) ? 0x90 : 0x80;
-            high = (current == 0xF4) ? 0x8F : 0xBF;
-        }
-        else
-        {
-            // an ill-formed byte
-            add_replacement_character();
-            return true;
-        }
-
-        const std::size_t start = token_buffer.size();
-        add(current);
-        for (std::size_t i = 0; i < count; ++i)
-        {
-            get();
-            if (current < low || current > high)
-            {
-                token_buffer.resize(start);
-                add_replacement_character();
-                return false;
-            }
-            add(current);
-            low = 0x80;
-            high = 0xBF;
-        }
-        return true;
-    }
-
-    /*!
-    @brief read the low surrogate that must follow the high surrogate @a high
-    @return whether the next character must be read; false if current still
-            needs to be handled
-    */
-    bool recover_low_surrogate(int high)
-    {
-        while (true)
-        {
-            if (get() != '\\')
-            {
-                add_replacement_character();
-                return false;
-            }
-            if (get() != 'u')
-            {
-                add_replacement_character();
-                // not 'u', so this does not come back here
-                return recover_escape();
-            }
-
-            const int low = get_codepoint();
-            if (low == -1)
-            {
-                add_replacement_character();
-                return false;
-            }
-            if (0xDC00 <= low && low <= 0xDFFF)
-            {
-                add_codepoint(static_cast<int>((static_cast<unsigned int>(high) << 10u)
-                                               + static_cast<unsigned int>(low) - 0x35FDC00u));
-                return true;
-            }
-
-            // high has no low surrogate
-            add_replacement_character();
-            if (low < 0xD800 || low > 0xDBFF)
-            {
-                add_codepoint(low);
-                return true;
-            }
-            // another high surrogate
-            high = low;
-        }
-    }
-
-    /*!
-    @brief read the escape whose backslash was read; current is the escaped character
-    @return whether the next character must be read; false if current still
-            needs to be handled
-    */
-    bool recover_escape()
-    {
-        switch (current)
-        {
-            case '\"':
-                add('\"');
-                return true;
-            case '\\':
-                add('\\');
-                return true;
-            case '/':
-                add('/');
-                return true;
-            case 'b':
-                add('\b');
-                return true;
-            case 'f':
-                add('\f');
-                return true;
-            case 'n':
-                add('\n');
-                return true;
-            case 'r':
-                add('\r');
-                return true;
-            case 't':
-                add('\t');
-                return true;
-
-            case 'u':
-            {
-                const int codepoint = get_codepoint();
-                if (codepoint == -1)
-                {
-                    add_replacement_character();
-                    return false;
-                }
-                if (0xD800 <= codepoint && codepoint <= 0xDBFF)
-                {
-                    return recover_low_surrogate(codepoint);
-                }
-                add_escaped_codepoint(codepoint);
-                return true;
-            }
-
-            // an unknown escape stands for the escaped character
-            default:
-                return false;
-        }
-    }
-
-    /*!
-    @brief read the rest of a string after scan_string() rejected it
-
-    token_buffer holds what scan_string() read before the error. See
-    recover_token() for how errors are repaired.
-
-    @param[in] resume     how to continue, see resume_kind
-    @param[in] codepoint  for a high surrogate followed by an escape of another
-                          code point: that code point; -1 otherwise
-    */
-    token_type recover_string(const resume_kind resume, const int codepoint)
-    {
-        // whether the next character must be read before it can be handled
-        bool fetch = false;
-
-        if (error_message_starts_with("invalid string: surrogate")
-                || error_message_starts_with("invalid string: '\\u'")
-                || (error_message_starts_with("invalid string: ill-formed UTF-8")
-                    && remove_incomplete_utf8_sequence()))
-        {
-            add_replacement_character();
-        }
-
-        switch (resume)
-        {
-            case resume_kind::escaped_character:
-                fetch = recover_escape();
-                break;
-            case resume_kind::after_escape:
-                if (0xD800 <= codepoint && codepoint <= 0xDBFF)
-                {
-                    fetch = recover_low_surrogate(codepoint);
-                }
-                else
-                {
-                    if (codepoint != -1)
-                    {
-                        add_escaped_codepoint(codepoint);
-                    }
-                    fetch = true;
-                }
-                break;
-            case resume_kind::character:
-            default:
-                break;
-        }
-
-        while (true)
-        {
-            if (fetch)
-            {
-                get();
-            }
-            fetch = true;
-
-            switch (current)
-            {
-                case '\"':
-                // a line break or the end of the input ends a string that
-                // lacks its closing quote
-                case '\n':
-                case '\r':
-                case char_traits<char_type>::eof():
-                    return token_type::value_string;
-
-#if !JSON_STRICT_NUL_HANDLING
-                case '\0':
-                    // the end of the input, see scan()
-                    unget();
-                    return token_type::value_string;
-#endif
-
-                case '\\':
-                    get();
-                    fetch = recover_escape();
-                    break;
-
-                default:
-                    if (current < 0x80)
-                    {
-                        // including control characters
-                        add(current);
-                    }
-                    else
-                    {
-                        fetch = recover_utf8_sequence();
-                    }
-                    break;
-            }
-        }
-    }
-
-    /*!
-    @brief keep the longest valid prefix of a number that scan_number() rejected
-
-    token_buffer holds the characters scan_number() accepted before the error,
-    so the prefix ends at its last digit.
-    */
-    token_type recover_number()
-    {
-        // only size(), operator[], and resize() are used, which every string
-        // type the library supports provides
-        std::size_t length = token_buffer.size();
-        while (length != 0 && (token_buffer[length - 1] < '0' || token_buffer[length - 1] > '9'))
-        {
-            --length;
-        }
-        token_buffer.resize(length);
-
-        if (length == 0)
-        {
-            skip_to_delimiter();
-            return token_type::uninitialized;
-        }
-
-        if (decimal_point_position >= length)
-        {
-            decimal_point_position = std::string::npos;
-        }
-
-        std::size_t exponent = std::string::npos;
-        for (std::size_t i = 0; i < length; ++i)
-        {
-            if (token_buffer[i] == 'e' || token_buffer[i] == 'E')
-            {
-                exponent = i;
-                break;
-            }
-        }
-        const std::size_t mantissa_end = (exponent == std::string::npos) ? length : exponent;
-        token_type number_type = token_type::value_unsigned;
-        if (decimal_point_position != std::string::npos || exponent != std::string::npos)
-        {
-            number_type = token_type::value_float;
-        }
-        else if (token_buffer[0] == '-')
-        {
-            number_type = token_type::value_integer;
-        }
-
-        const token_type result = convert_number(number_type, mantissa_end);
-        skip_to_delimiter();
-        return result;
-    }
-
-    /// seekable adapter: the token string begins at current, which was consumed
-    void restart_token_string_impl(std::true_type /*lazy*/) noexcept
-    {
-        const std::size_t consumed = ia.get_consumed_count();
-        token_string_start = (consumed > 0 && current != char_traits<char_type>::eof()) ? consumed - 1 : consumed;
-    }
-
-    /// streaming adapter: the token string begins at current; a character
-    /// that was put back is copied again when it is read again
-    void restart_token_string_impl(std::false_type /*lazy*/)
-    {
-        token_string.clear();
-        if (!next_unget && current != char_traits<char_type>::eof())
-        {
-            token_string.push_back(char_traits<char_type>::to_char_type(current));
-        }
-    }
-
     /// input adapter
     InputAdapterType ia;
 
@@ -2754,13 +2172,6 @@ scan_number_done:
     /// a description of occurred lexer errors
     const char* error_message = "";
 
-    /// how recover_token() continues a string that scan_string() rejected;
-    /// set only on the error paths that need more than error_message
-    resume_kind string_error_resume = resume_kind::character;
-    /// the code point of the second escape when a high surrogate is followed
-    /// by an escape that is not a low surrogate; -1 otherwise
-    int string_error_codepoint = -1;
-
     // number values
     number_integer_t value_integer = 0;
     number_unsigned_t value_unsigned = 0;

include/nlohmann/detail/input/parser.hpp

@@ -139,59 +139,26 @@ class parser
     bool accept(const bool strict = true)
     {
         json_sax_acceptor<BasicJsonType> sax_acceptor;
-        return sax_parse_impl<false>(&sax_acceptor, strict);
+        return sax_parse(&sax_acceptor, strict);
     }
 
-    /*!
-    @brief public SAX interface
-
-    If the SAX parser's parse_error() returns true, the parser recovers from
-    the error: it repairs the input and continues (see #3989).
-
-    @param[in] sax     the SAX parser
-    @param[in] strict  whether to expect the last token to be EOF
-    @return whether the input was parsed without errors and no SAX event
-            returned false
-    */
     template<typename SAX>
     JSON_HEDLEY_NON_NULL(2)
     bool sax_parse(SAX* sax, const bool strict = true)
-    {
-        return sax_parse_impl<true>(sax, strict);
-    }
-
-  private:
-    /// what sax_parse_internal() does after an object key was expected
-    enum class next_step : std::uint8_t
-    {
-        /// stop parsing
-        stop,
-        /// parse a value that begins with last_token
-        parse_value,
-        /// evaluate the state of the innermost container, which reads
-        /// last_token again
-        evaluate_state
-    };
-
-    template<bool AllowRecovery, typename SAX>
-    JSON_HEDLEY_NON_NULL(2)
-    bool sax_parse_impl(SAX* sax, const bool strict)
     {
         (void)detail::is_sax_static_asserts<SAX, BasicJsonType> {};
-        const bool result = sax_parse_internal<AllowRecovery>(sax);
+        const bool result = sax_parse_internal(sax);
 
         if (result)
         {
             if (strict)
             {
-                // strict mode: next byte must be EOF; after recovering from an
-                // error, the end of the input may already have been read
-                if (last_token != token_type::end_of_input && get_token() != token_type::end_of_input)
+                // strict mode: next byte must be EOF
+                if (get_token() != token_type::end_of_input)
                 {
-                    // the value is complete, so there is nothing to recover
-                    static_cast<void>(report_error(sax, parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_of_input, "value"), nullptr),
-                                                   std::integral_constant<bool, AllowRecovery> {}));
-                    return false;
+                    return sax->parse_error(m_lexer.get_position(),
+                                            m_lexer.get_token_string(),
+                                            parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_of_input, "value"), nullptr));
                 }
             }
             else
@@ -202,9 +169,10 @@ class parser
             }
         }
 
-        return result && !error_reported;
+        return result;
     }
 
+  private:
     /*!
     @brief run a DOM SAX parser to completion and position the lexer
 
@@ -222,7 +190,7 @@ class parser
     template<typename DomSax>
     bool parse_dom(DomSax& sdp, const bool strict)
     {
-        sax_parse_internal<false>(&sdp);
+        sax_parse_internal(&sdp);
 
         if (strict)
         {
@@ -245,20 +213,10 @@ class parser
         return !sdp.is_errored();
     }
 
-    /*!
-    @brief parse a JSON value and pass it to a SAX parser
-
-    @tparam AllowRecovery  whether to recover from an error if the SAX parser's
-                           parse_error() returns true; false for the SAX parsers
-                           of parse() and accept(), which never do, so that no
-                           code for recovering is generated for them
-    */
-    template<bool AllowRecovery, typename SAX>
+    template<typename SAX>
     JSON_HEDLEY_NON_NULL(2)
     bool sax_parse_internal(SAX* sax)
     {
-        const std::integral_constant<bool, AllowRecovery> allow_recovery{};
-
         // stack to remember the hierarchy of structured values we are parsing
         // true = array; false = object
         std::vector<bool> states;
@@ -289,18 +247,12 @@ class parser
                             break;
                         }
 
-                        // remember we are now inside an object
-                        states.push_back(false);
-
-                        // parse key (the steps of parse_key(), which are
-                        // repeated here and below for speed)
+                        // parse key
                         if (JSON_HEDLEY_UNLIKELY(last_token != token_type::value_string))
                         {
-                            if (!continue_after(key_error(sax, allow_recovery, false), skip_to_state_evaluation))
-                            {
-                                return false;
-                            }
-                            continue;
+                            return sax->parse_error(m_lexer.get_position(),
+                                                    m_lexer.get_token_string(),
+                                                    parse_error::create(101, m_lexer.get_position(), exception_message(token_type::value_string, "object key"), nullptr));
                         }
                         if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string())))
                         {
@@ -310,13 +262,14 @@ class parser
                         // parse separator (:)
                         if (JSON_HEDLEY_UNLIKELY(!get_token_expecting(token_type::name_separator)))
                         {
-                            if (!continue_after(key_error(sax, allow_recovery, true), skip_to_state_evaluation))
-                            {
-                                return false;
-                            }
-                            continue;
+                            return sax->parse_error(m_lexer.get_position(),
+                                                    m_lexer.get_token_string(),
+                                                    parse_error::create(101, m_lexer.get_position(), exception_message(token_type::name_separator, "object separator"), nullptr));
                         }
 
+                        // remember we are now inside an object
+                        states.push_back(false);
+
                         // parse values
                         get_token();
                         continue;
@@ -352,11 +305,9 @@ class parser
 
                         if (JSON_HEDLEY_UNLIKELY(!std::isfinite(res)))
                         {
-                            if (!overflow_error(sax, res, allow_recovery))
-                            {
-                                return false;
-                            }
-                            break;
+                            return sax->parse_error(m_lexer.get_position(),
+                                                    m_lexer.get_token_string(),
+                                                    out_of_range::create(406, concat("number overflow parsing '", m_lexer.get_token_string(), '\''), nullptr));
                         }
 
                         if (JSON_HEDLEY_UNLIKELY(!sax->number_float(res, m_lexer.get_string())))
@@ -424,63 +375,23 @@ class parser
                     case token_type::parse_error:
                     {
                         // using "uninitialized" to avoid an "expected" message
-                        if (!report_error(sax, parse_error::create(101, m_lexer.get_position(), exception_message(token_type::uninitialized, "value"), nullptr), allow_recovery))
-                        {
-                            return false;
-                        }
-
-                        // recover: keep what can be read of the token
-                        recover_token(allow_recovery);
-                        if (last_token != token_type::uninitialized)
-                        {
-                            // a string or a number
-                            continue;
-                        }
-                        if (states.empty())
-                        {
-                            // look for the value after the garbage
-                            if (!skip_to_value(allow_recovery))
-                            {
-                                return false;
-                            }
-                            continue;
-                        }
-                        // nothing could be read
-                        if (JSON_HEDLEY_UNLIKELY(!sax->null()))
-                        {
-                            return false;
-                        }
-                        break;
+                        return sax->parse_error(m_lexer.get_position(),
+                                                m_lexer.get_token_string(),
+                                                parse_error::create(101, m_lexer.get_position(), exception_message(token_type::uninitialized, "value"), nullptr));
                     }
                     case token_type::end_of_input:
                     {
                         if (JSON_HEDLEY_UNLIKELY(m_lexer.get_position().chars_read_total == 1))
                         {
-                            // there is nothing to recover
-                            static_cast<void>(report_error(sax, parse_error::create(101, m_lexer.get_position(),
-                                                           "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr), allow_recovery));
-                            return false;
+                            return sax->parse_error(m_lexer.get_position(),
+                                                    m_lexer.get_token_string(),
+                                                    parse_error::create(101, m_lexer.get_position(),
+                                                            "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
                         }
 
-                        if (!report_error(sax, parse_error::create(101, m_lexer.get_position(), exception_message(token_type::literal_or_value, "value"), nullptr), allow_recovery))
-                        {
-                            return false;
-                        }
-
-                        // recover: the input ends where a value is missing
-                        if (states.empty())
-                        {
-                            // there is no value
-                            return false;
-                        }
-                        if (!recover_missing_value(sax, states, allow_recovery))
-                        {
-                            return false;
-                        }
-                        // the state evaluation reads the token again
-                        unget_token(allow_recovery);
-                        skip_to_state_evaluation = true;
-                        continue;
+                        return sax->parse_error(m_lexer.get_position(),
+                                                m_lexer.get_token_string(),
+                                                parse_error::create(101, m_lexer.get_position(), exception_message(token_type::literal_or_value, "value"), nullptr));
                     }
                     case token_type::uninitialized:
                     case token_type::end_array:
@@ -490,35 +401,9 @@ class parser
                     case token_type::literal_or_value:
                     default: // the last token was unexpected
                     {
-                        if (!report_error(sax, parse_error::create(101, m_lexer.get_position(), exception_message(token_type::literal_or_value, "value"), nullptr), allow_recovery))
-                        {
-                            return false;
-                        }
-
-                        // recover
-                        if (states.empty())
-                        {
-                            // look for the value after the garbage
-                            if (!skip_to_value(allow_recovery))
-                            {
-                                return false;
-                            }
-                            continue;
-                        }
-                        if (last_token == token_type::name_separator)
-                        {
-                            // a stray ':'; the value may follow
-                            get_token();
-                            continue;
-                        }
-                        if (!recover_missing_value(sax, states, allow_recovery))
-                        {
-                            return false;
-                        }
-                        // the state evaluation reads the token again
-                        unget_token(allow_recovery);
-                        skip_to_state_evaluation = true;
-                        continue;
+                        return sax->parse_error(m_lexer.get_position(),
+                                                m_lexer.get_token_string(),
+                                                parse_error::create(101, m_lexer.get_position(), exception_message(token_type::literal_or_value, "value"), nullptr));
                     }
                 }
             }
@@ -569,30 +454,9 @@ class parser
                     continue;
                 }
 
-                if (!report_error(sax, parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_array, "array"), nullptr), allow_recovery))
-                {
-                    return false;
-                }
-
-                // recover
-                if (last_token == token_type::end_of_input)
-                {
-                    // the input ends inside the array
-                    return close_containers(sax, states, allow_recovery);
-                }
-                if (last_token == token_type::end_object)
-                {
-                    // a wrong closing bracket closes the innermost container
-                    if (JSON_HEDLEY_UNLIKELY(!sax->end_array()))
-                    {
-                        return false;
-                    }
-                    states.pop_back();
-                    skip_to_state_evaluation = true;
-                }
-                // otherwise, a missing ',' (or a stray ':', which value
-                // parsing drops): the next value begins here
-                continue;
+                return sax->parse_error(m_lexer.get_position(),
+                                        m_lexer.get_token_string(),
+                                        parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_array, "array"), nullptr));
             }
 
             // states.back() is false -> object
@@ -609,12 +473,11 @@ class parser
                     // parse key
                     if (JSON_HEDLEY_UNLIKELY(last_token != token_type::value_string))
                     {
-                        if (!continue_after(key_error(sax, allow_recovery, false), skip_to_state_evaluation))
-                        {
-                            return false;
-                        }
-                        continue;
+                        return sax->parse_error(m_lexer.get_position(),
+                                                m_lexer.get_token_string(),
+                                                parse_error::create(101, m_lexer.get_position(), exception_message(token_type::value_string, "object key"), nullptr));
                     }
+
                     if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string())))
                     {
                         return false;
@@ -623,11 +486,9 @@ class parser
                     // parse separator (:)
                     if (JSON_HEDLEY_UNLIKELY(!get_token_expecting(token_type::name_separator)))
                     {
-                        if (!continue_after(key_error(sax, allow_recovery, true), skip_to_state_evaluation))
-                        {
-                            return false;
-                        }
-                        continue;
+                        return sax->parse_error(m_lexer.get_position(),
+                                                m_lexer.get_token_string(),
+                                                parse_error::create(101, m_lexer.get_position(), exception_message(token_type::name_separator, "object separator"), nullptr));
                     }
 
                     // parse values
@@ -655,544 +516,12 @@ class parser
                 continue;
             }
 
-            if (!report_error(sax, parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_object, "object"), nullptr), allow_recovery))
-            {
-                return false;
-            }
-
-            // recover
-            if (last_token == token_type::end_of_input)
-            {
-                // the input ends inside the object
-                return close_containers(sax, states, allow_recovery);
-            }
-            if (last_token == token_type::end_array)
-            {
-                // a wrong closing bracket closes the innermost container
-                if (JSON_HEDLEY_UNLIKELY(!sax->end_object()))
-                {
-                    return false;
-                }
-                states.pop_back();
-                skip_to_state_evaluation = true;
-                continue;
-            }
-            if (!continue_after(recover_member(sax, allow_recovery), skip_to_state_evaluation))
-            {
-                return false;
-            }
+            return sax->parse_error(m_lexer.get_position(),
+                                    m_lexer.get_token_string(),
+                                    parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_object, "object"), nullptr));
         }
     }
 
-    /*!
-    @brief continue sax_parse_internal() after a recovery
-    @return whether to continue parsing
-    */
-    bool continue_after(const next_step step, bool& skip_to_state_evaluation)
-    {
-        if (step == next_step::evaluate_state)
-        {
-            // the state evaluation reads the token again
-            m_lexer.unget_token();
-            skip_to_state_evaluation = true;
-        }
-        return step != next_step::stop;
-    }
-
-    /// the parser for parse() and accept() never recovers: stop parsing
-    JSON_INTERNAL_ALWAYS_INLINE
-    static std::false_type continue_after(std::false_type /*step*/, bool& /*skip_to_state_evaluation*/) noexcept
-    {
-        return {};
-    }
-
-    /*!
-    @brief parse an object key and the name separator (:) after it
-
-    last_token is the token where the key is expected. sax_parse_internal()
-    repeats these steps rather than calling this function, which is used
-    when recovering from an error.
-
-    @return next_step::parse_value if the value follows, with last_token its
-            first token; next_step::evaluate_state if the object's state is
-            to be evaluated after recovering from an error; next_step::stop
-            to stop parsing
-    */
-    template<typename SAX>
-    next_step parse_key(SAX* sax)
-    {
-        const std::true_type allow_recovery{};
-
-        if (JSON_HEDLEY_UNLIKELY(last_token != token_type::value_string))
-        {
-            return key_error(sax, allow_recovery, false);
-        }
-
-        if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string())))
-        {
-            return next_step::stop;
-        }
-
-        // parse separator (:)
-        if (JSON_HEDLEY_UNLIKELY(get_token() != token_type::name_separator))
-        {
-            return key_error(sax, allow_recovery, true);
-        }
-
-        // the value begins with the next token
-        get_token();
-        return next_step::parse_value;
-    }
-
-    /*!
-    @brief report a number that is too large for number_float_t, and recover
-           from the error by passing the value on; the SAX parser gets the
-           number's text as well
-
-    This is a separate function, as reading other numbers is measurably
-    slower if the error is handled where they are read.
-
-    @param[in] sax    the SAX parser
-    @param[in] value  the value that is not finite
-    @return whether to continue parsing
-    */
-    template<typename SAX>
-    bool overflow_error(SAX* sax, const number_float_t value, std::true_type allow_recovery)
-    {
-        if (!report_error(sax, out_of_range::create(406, concat("number overflow parsing '", m_lexer.get_token_string(), '\''), nullptr), allow_recovery))
-        {
-            return false;
-        }
-        return sax->number_float(value, m_lexer.get_string());
-    }
-
-    /// @copydoc overflow_error
-    template<typename SAX>
-    JSON_INTERNAL_ALWAYS_INLINE
-    std::false_type overflow_error(SAX* sax, const number_float_t /*value*/, std::false_type allow_recovery)
-    {
-        return report_error(sax, out_of_range::create(406, concat("number overflow parsing '", m_lexer.get_token_string(), '\''), nullptr), allow_recovery);
-    }
-
-    /*!
-    @brief report a missing key, or a missing name separator (:) after the
-           key; the parser for parse() and accept() never recovers
-
-    @param[in] key_read  whether the key was read, so that the name separator
-                         is missing
-    @return std::false_type, see report_error()
-    */
-    template<typename SAX>
-    JSON_INTERNAL_ALWAYS_INLINE
-    std::false_type key_error(SAX* sax, std::false_type allow_recovery, const bool key_read)
-    {
-        return report_error(sax, parse_error::create(101, m_lexer.get_position(), key_read
-                            ? exception_message(token_type::name_separator, "object separator")
-                            : exception_message(token_type::value_string, "object key"), nullptr), allow_recovery);
-    }
-
-    /*!
-    @brief report a missing key, or a missing name separator (:) after the
-           key, and recover from it
-
-    @param[in] key_read  whether the key was read, so that the name separator
-                         is missing
-    */
-    template<typename SAX>
-    next_step key_error(SAX* sax, std::true_type allow_recovery, const bool key_read)
-    {
-        if (!key_read)
-        {
-            if (!report_error(sax, parse_error::create(101, m_lexer.get_position(), exception_message(token_type::value_string, "object key"), nullptr), allow_recovery))
-            {
-                return next_step::stop;
-            }
-            return recover_key(sax);
-        }
-
-        if (!report_error(sax, parse_error::create(101, m_lexer.get_position(), exception_message(token_type::name_separator, "object separator"), nullptr), allow_recovery))
-        {
-            return next_step::stop;
-        }
-        return recover_name_separator(sax);
-    }
-
-    /////////////////////
-    // error recovery
-    /////////////////////
-
-    /*
-    The functions below repair an error after the SAX parser's parse_error()
-    returned true (see #3989). Each mistake is repaired by the smallest local
-    edit: a missing ',' or ':' is inserted, a stray token is removed, what can
-    be read of an invalid string or number is kept (see
-    lexer::recover_token()), a missing value becomes null, a wrong closing
-    bracket closes the innermost container, and the end of the input closes
-    all of them. The events stay balanced, and every key() is followed by
-    exactly one value.
-
-    A repair hands a token to the state evaluation, by returning it to the
-    lexer (lexer::unget_token()) so that the state evaluation reads it again,
-    only if it is ',', ']', '}', or the end of the input. The state evaluation
-    hands a token to value or key parsing only if it is none of them, so a
-    token is never handed back and forth. Every other step reads a token or
-    closes a container, so parsing always ends.
-    */
-
-    /*!
-    @brief report an error to the SAX parser; the parser for parse() and
-           accept() never recovers
-
-    @return std::false_type rather than false: its value is known where the
-            function is called even if the call is not inlined, so the code
-            for recovering is not generated
-    */
-    template<typename SAX, typename Exception>
-    JSON_INTERNAL_ALWAYS_INLINE
-    std::false_type report_error(SAX* sax, const Exception& ex, std::false_type /*allow_recovery*/)
-    {
-        error_reported = true;
-        static_cast<void>(sax->parse_error(m_lexer.get_position(), m_lexer.get_token_string(), ex));
-        return {};
-    }
-
-    /*!
-    @brief report an error to the SAX parser
-    @return whether to recover from the error
-    */
-    template<typename SAX, typename Exception>
-    bool report_error(SAX* sax, const Exception& ex, std::true_type /*allow_recovery*/)
-    {
-        const std::size_t position = m_lexer.get_position().chars_read_total;
-        if (error_reported && position == last_error_position && last_token == last_error_token)
-        {
-            // a repair handed on the token of the error it repaired; the
-            // token was reported already, and the SAX parser asked to recover
-            return true;
-        }
-
-        error_reported = true;
-        last_error_position = position;
-        last_error_token = last_token;
-
-        if (!sax->parse_error(m_lexer.get_position(), m_lexer.get_token_string(), ex))
-        {
-            return false;
-        }
-
-        // the token string of the next error begins here
-        m_lexer.restart_token_string();
-        return true;
-    }
-
-    /*!
-    @brief keep what can be read of the token that the lexer rejected
-
-    The error was reported for the rejected token, so it is not reported again
-    for the token it is repaired to (see lexer::recover_token()).
-    */
-    token_type recover_token()
-    {
-        last_token = m_lexer.recover_token();
-        last_error_position = m_lexer.get_position().chars_read_total;
-        last_error_token = last_token;
-        return last_token;
-    }
-
-    // The functions below are called from sax_parse_internal() after an error
-    // was reported. The parser for parse() and accept() stopped there, so for
-    // it they are stubs: the code for recovering is then not even referenced,
-    // and unoptimized builds do not emit it either.
-
-    /// @copydoc recover_token()
-    JSON_INTERNAL_ALWAYS_INLINE
-    token_type recover_token(std::true_type /*allow_recovery*/)
-    {
-        return recover_token();
-    }
-
-    /// @copydoc recover_token()
-    JSON_INTERNAL_ALWAYS_INLINE
-    static std::false_type recover_token(std::false_type /*allow_recovery*/) noexcept
-    {
-        return {};
-    }
-
-    /// return the token that was read last to the lexer (see lexer::unget_token())
-    JSON_INTERNAL_ALWAYS_INLINE
-    void unget_token(std::true_type /*allow_recovery*/)
-    {
-        m_lexer.unget_token();
-    }
-
-    /// @copydoc unget_token(std::true_type)
-    JSON_INTERNAL_ALWAYS_INLINE
-    static void unget_token(std::false_type /*allow_recovery*/) noexcept {}
-
-    /// @copydoc skip_to_value
-    JSON_INTERNAL_ALWAYS_INLINE
-    static std::false_type skip_to_value(std::false_type /*allow_recovery*/) noexcept
-    {
-        return {};
-    }
-
-    /// @copydoc recover_missing_value
-    template<typename SAX>
-    JSON_INTERNAL_ALWAYS_INLINE
-    static std::false_type recover_missing_value(SAX* /*sax*/, const std::vector<bool>& /*states*/, std::false_type /*allow_recovery*/) noexcept
-    {
-        return {};
-    }
-
-    /// pass the end events of all open containers
-    template<typename SAX>
-    bool close_containers(SAX* sax, std::vector<bool>& states, std::true_type /*allow_recovery*/)
-    {
-        while (!states.empty())
-        {
-            const bool is_array = states.back();
-            states.pop_back();
-            if (JSON_HEDLEY_UNLIKELY(is_array ? !sax->end_array() : !sax->end_object()))
-            {
-                return false;
-            }
-        }
-        return true;
-    }
-
-    /// @copydoc close_containers
-    template<typename SAX>
-    JSON_INTERNAL_ALWAYS_INLINE
-    static std::false_type close_containers(SAX* /*sax*/, std::vector<bool>& /*states*/, std::false_type /*allow_recovery*/) noexcept
-    {
-        return {};
-    }
-
-    /*!
-    @brief read tokens until one begins a value, skipping everything before
-           the top-level value
-    @return whether a value begins with last_token
-    */
-    bool skip_to_value(std::true_type /*allow_recovery*/)
-    {
-        while (true)
-        {
-            switch (get_token())
-            {
-                case token_type::begin_array:
-                case token_type::begin_object:
-                case token_type::literal_false:
-                case token_type::literal_null:
-                case token_type::literal_true:
-                case token_type::value_float:
-                case token_type::value_integer:
-                case token_type::value_string:
-                case token_type::value_unsigned:
-                    return true;
-
-                case token_type::end_of_input:
-                    return false;
-
-                case token_type::parse_error:
-                    recover_token();
-                    if (last_token != token_type::uninitialized)
-                    {
-                        return true;
-                    }
-                    break;
-
-                case token_type::uninitialized:
-                case token_type::end_array:
-                case token_type::end_object:
-                case token_type::name_separator:
-                case token_type::value_separator:
-                case token_type::literal_or_value:
-                default:
-                    break;
-            }
-        }
-    }
-
-    /*!
-    @brief skip the rest of an object member that cannot be read
-
-    Reads tokens, beginning with last_token, until a ',', '}', or ']' that is
-    not inside a container that begins in the skipped tokens, or the end of
-    the input.
-    */
-    void skip_member()
-    {
-        std::size_t depth = 0;
-        while (true)
-        {
-            switch (last_token)
-            {
-                case token_type::begin_array:
-                case token_type::begin_object:
-                    ++depth;
-                    break;
-
-                case token_type::end_array:
-                case token_type::end_object:
-                    if (depth == 0)
-                    {
-                        return;
-                    }
-                    --depth;
-                    break;
-
-                case token_type::value_separator:
-                    if (depth == 0)
-                    {
-                        return;
-                    }
-                    break;
-
-                case token_type::end_of_input:
-                    return;
-
-                case token_type::parse_error:
-                    recover_token();
-                    break;
-
-                case token_type::uninitialized:
-                case token_type::literal_true:
-                case token_type::literal_false:
-                case token_type::literal_null:
-                case token_type::value_string:
-                case token_type::value_unsigned:
-                case token_type::value_integer:
-                case token_type::value_float:
-                case token_type::name_separator:
-                case token_type::literal_or_value:
-                default:
-                    break;
-            }
-            get_token();
-        }
-    }
-
-    /*!
-    @brief pass a value where it is missing
-
-    last_token is ',', ']', '}', or the end of the input, where a value was
-    expected. In an object, the key gets null; in an array, a ',' where a
-    value is missing stands for null (as in JavaScript), while an array that
-    ends there just ends.
-    */
-    template<typename SAX>
-    bool recover_missing_value(SAX* sax, const std::vector<bool>& states, std::true_type /*allow_recovery*/)
-    {
-        JSON_ASSERT(!states.empty());
-        if (!states.back() || last_token == token_type::value_separator)
-        {
-            return sax->null();
-        }
-        return true;
-    }
-
-    /// recover from a missing key; last_token is where it was expected
-    template<typename SAX>
-    next_step recover_key(SAX* sax)
-    {
-        switch (last_token)
-        {
-            case token_type::value_separator:
-            case token_type::end_object:
-            case token_type::end_array:
-            case token_type::end_of_input:
-                // no member: the object's state handles the token
-                return next_step::evaluate_state;
-
-            case token_type::parse_error:
-                recover_token();
-                if (last_token == token_type::value_string)
-                {
-                    // a key that could be repaired
-                    return parse_key(sax);
-                }
-                skip_member();
-                return next_step::evaluate_state;
-
-            case token_type::uninitialized:
-            case token_type::literal_true:
-            case token_type::literal_false:
-            case token_type::literal_null:
-            case token_type::value_string:
-            case token_type::value_unsigned:
-            case token_type::value_integer:
-            case token_type::value_float:
-            case token_type::begin_array:
-            case token_type::begin_object:
-            case token_type::name_separator:
-            case token_type::literal_or_value:
-            default:
-                // a member without a key
-                skip_member();
-                return next_step::evaluate_state;
-        }
-    }
-
-    /// recover from a missing name separator (:) after the key; last_token
-    /// is where it was expected
-    template<typename SAX>
-    next_step recover_name_separator(SAX* sax)
-    {
-        switch (last_token)
-        {
-            case token_type::value_separator:
-            case token_type::end_object:
-            case token_type::end_array:
-            case token_type::end_of_input:
-                // the value is missing as well
-                return sax->null() ? next_step::evaluate_state : next_step::stop;
-
-            case token_type::uninitialized:
-            case token_type::literal_true:
-            case token_type::literal_false:
-            case token_type::literal_null:
-            case token_type::value_string:
-            case token_type::value_unsigned:
-            case token_type::value_integer:
-            case token_type::value_float:
-            case token_type::begin_array:
-            case token_type::begin_object:
-            case token_type::name_separator:
-            case token_type::parse_error:
-            case token_type::literal_or_value:
-            default:
-                // a missing ':'; the value begins here
-                return next_step::parse_value;
-        }
-    }
-
-    /// recover from a token after an object member that is neither ',' nor
-    /// '}' (nor ']' or the end of the input, which the caller handles)
-    template<typename SAX>
-    next_step recover_member(SAX* sax, std::true_type /*allow_recovery*/)
-    {
-        if (last_token == token_type::parse_error)
-        {
-            recover_token();
-        }
-        if (last_token == token_type::value_string)
-        {
-            // a missing ','; the next key begins here
-            return parse_key(sax);
-        }
-        skip_member();
-        return next_step::evaluate_state;
-    }
-
-    /// the parser for parse() and accept() never recovers (and does not come
-    /// here, as report_error() returned false)
-    template<typename SAX>
-    JSON_INTERNAL_ALWAYS_INLINE
-    std::false_type recover_member(SAX* /*sax*/, std::false_type /*allow_recovery*/) const noexcept
-    {
-        return {};
-    }
-
     /// get next token from lexer
     token_type get_token()
     {
@@ -1246,12 +575,6 @@ class parser
     const bool allow_exceptions = true;
     /// whether trailing commas in objects and arrays should be ignored (true) or signaled as errors (false)
     const bool ignore_trailing_commas = false;
-    /// whether an error was reported to the SAX parser
-    bool error_reported = false;
-    /// the position of the last reported error
-    std::size_t last_error_position = 0;
-    /// the token of the last reported error
-    token_type last_error_token = token_type::uninitialized;
 };
 
 }  // namespace detail

include/nlohmann/detail/macro_scope.hpp

@@ -199,17 +199,6 @@
     #define JSON_NO_UNIQUE_ADDRESS
 #endif
 
-// Inlines small functions even in unoptimized builds, so that they are not
-// emitted. The parsers for parse(), accept(), and from_*() use it for the
-// functions that stand in for the code recovering from errors (see #3989).
-// MSVC is left to decide, as it warns (C4714) where it does not inline a
-// __forceinline function.
-#if defined(_MSC_VER) && !defined(__clang__)
-    #define JSON_INTERNAL_ALWAYS_INLINE
-#else
-    #define JSON_INTERNAL_ALWAYS_INLINE JSON_HEDLEY_ALWAYS_INLINE
-#endif
-
 // Clang targeting MinGW does not survive the thread_local storage the copy
 // constructor uses to bound its descent: every test that copies a value
 // segfaults with clang 11.0.1 and clang 18.1.8, while the same tests pass with

include/nlohmann/detail/macro_unscope.hpp

@@ -19,7 +19,6 @@
 #undef NLOHMANN_CAN_CALL_STD_FUNC_IMPL
 #undef JSON_INLINE_VARIABLE
 #undef JSON_NO_UNIQUE_ADDRESS
-#undef JSON_INTERNAL_ALWAYS_INLINE
 #undef JSON_DISABLE_ENUM_SERIALIZATION
 #undef JSON_DISABLE_TUPLE_REFERENCE_CONVERSION
 

include/nlohmann/detail/output/binary_writer.hpp

@@ -85,6 +85,12 @@ template<typename BasicJsonType, typename CharType, typename OutputSinkType = ou
 class binary_writer
 {
     using string_t = typename BasicJsonType::string_t;
+
+    /// an object key as string_t: a reference when object_t::key_type already is
+    /// string_t, otherwise a converted copy that outlives sanitize_utf8_for_write's result
+    using object_key_string_t = typename std::conditional <
+                                std::is_same<typename BasicJsonType::object_t::key_type, string_t>::value,
+                                const string_t&, string_t >::type;
     using binary_t = typename BasicJsonType::binary_t;
     using number_float_t = typename BasicJsonType::number_float_t;
 
@@ -819,8 +825,10 @@ class binary_writer
 
                 for (const auto& el : *j.m_data.m_value.object)
                 {
+                    // a converted key must outlive the reference returned by sanitize_utf8_for_write
+                    const object_key_string_t key_string = el.first;
                     string_t storage;
-                    const string_t& key = sanitize_utf8_for_write(el.first, j, storage);
+                    const string_t& key = sanitize_utf8_for_write(key_string, j, storage);
                     write_number_with_ubjson_prefix(key.size(), true, use_bjdata);
                     oa.write_characters(
                           reinterpret_cast<const CharType*>(key.data()),
@@ -1366,8 +1374,10 @@ class binary_writer
                     continue;
                 }
 
+                // a converted key must outlive the reference returned by sanitize_utf8_for_write
+                const object_key_string_t key_string = current.object_it->first;
                 string_t storage;
-                const string_t& key = sanitize_utf8_for_write(current.object_it->first, j, storage);
+                const string_t& key = sanitize_utf8_for_write(key_string, j, storage);
                 write_number_with_ubjson_prefix(key.size(), true, use_bjdata);
                 oa.write_characters(
                       reinterpret_cast<const CharType*>(key.data()),
@@ -2730,6 +2740,11 @@ class binary_writer
     itself in every case but a sanitized `replace`/`ignore` one, so @a
     storage must outlive the returned reference only then.
 
+    @a s must be an lvalue that outlives the returned reference. An object key
+    whose `key_type` is not @ref string_t must therefore first be converted
+    into a named string_t (see @ref object_key_string_t); the deleted overload
+    below enforces this at compile time.
+
     @param[in] s        the string (value or object key) to write
     @param[in] context  the value @a s belongs to (for diagnostics)
     @param[out] storage  backing storage for a sanitized copy
@@ -2759,6 +2774,10 @@ class binary_writer
         }
     }
 
+    /// deleted: anything but a string_t would bind a temporary that dies before the returned reference is used
+    template < typename T, enable_if_t < !std::is_same<T, string_t>::value, int > = 0 >
+    const string_t& sanitize_utf8_for_write(const T& /*s*/, const BasicJsonType& /*context*/, string_t& /*storage*/) const = delete;
+
     /*!
     @brief write an integer in the shortest encoding
 

include/nlohmann/detail/string_utils.hpp

@@ -13,7 +13,6 @@
 #include <cstddef> // size_t
 #include <cstdint> // uint8_t, uint32_t
 #include <string> // string, to_string
-#include <utility> // move
 
 #include <nlohmann/detail/abi_macros.hpp>
 #include <nlohmann/detail/macro_scope.hpp>

include/nlohmann/json.hpp

@@ -149,7 +149,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     friend class ::nlohmann::detail::iter_impl;
     template<typename BasicJsonType, typename CharType, typename OutputSinkType>
     friend class ::nlohmann::detail::binary_writer;
-    template<typename BasicJsonType, typename InputType, typename SAX, bool AllowRecovery>
+    template<typename BasicJsonType, typename InputType, typename SAX>
     friend class ::nlohmann::detail::binary_reader;
     template<typename BasicJsonType, typename InputAdapterType>
     friend class ::nlohmann::detail::json_sax_dom_parser;
@@ -5689,7 +5689,7 @@ public:
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         return format == input_format_t::json
                ? parser(std::move(ia), nullptr, true, ignore_comments, ignore_trailing_commas).sax_parse(sax, strict)
-               : detail::binary_reader<basic_json, decltype(ia), SAX, true>(std::move(ia), format).sax_parse(sax, strict, tag_handler);
+               : detail::binary_reader<basic_json, decltype(ia), SAX>(std::move(ia), format).sax_parse(sax, strict, tag_handler);
     }
 
     /// @brief generate SAX events (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -5707,7 +5707,7 @@ public:
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         return format == input_format_t::json
                ? parser(std::move(ia), nullptr, true, ignore_comments, ignore_trailing_commas).sax_parse(sax, strict)
-               : detail::binary_reader<basic_json, decltype(ia), SAX, true>(std::move(ia), format).sax_parse(sax, strict, tag_handler);
+               : detail::binary_reader<basic_json, decltype(ia), SAX>(std::move(ia), format).sax_parse(sax, strict, tag_handler);
     }
 
     /// @brief generate SAX events
@@ -5746,7 +5746,7 @@ public:
                // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
                ? parser(std::move(ia), nullptr, true, ignore_comments, ignore_trailing_commas).sax_parse(sax, strict)
                // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-               : detail::binary_reader<basic_json, decltype(ia), SAX, true>(std::move(ia), format).sax_parse(sax, strict, tag_handler);
+               : detail::binary_reader<basic_json, decltype(ia), SAX>(std::move(ia), format).sax_parse(sax, strict, tag_handler);
     }
 #endif
 #if defined(__clang__)

meson.build

@@ -2,24 +2,120 @@ project('nlohmann_json',
     'cpp',
     version : '3.12.0',
     license : 'MIT',
+    meson_version : '>= 0.64',
+    default_options: ['cpp_std=c++11'],
 )
 
+if get_option('MultipleHeaders')
+    incdir = 'include'
+else
+    incdir = 'single_include'
+endif
+
+# The same compile definitions as the CMake target (see target_compile_definitions
+# in CMakeLists.txt): only an option that differs from its default adds one.
+json_defines = []
+if not get_option('GlobalUDLs')
+    json_defines += 'JSON_USE_GLOBAL_UDLS=0'
+endif
+if not get_option('ImplicitConversions')
+    json_defines += 'JSON_USE_IMPLICIT_CONVERSIONS=0'
+endif
+if get_option('DisableEnumSerialization')
+    json_defines += 'JSON_DISABLE_ENUM_SERIALIZATION=1'
+endif
+if get_option('DisableTupleReferenceConversion')
+    json_defines += 'JSON_DISABLE_TUPLE_REFERENCE_CONVERSION=1'
+endif
+if get_option('Diagnostics')
+    json_defines += 'JSON_DIAGNOSTICS=1'
+endif
+if get_option('Diagnostic_Positions')
+    json_defines += 'JSON_DIAGNOSTIC_POSITIONS=1'
+endif
+if get_option('LegacyDiscardedValueComparison')
+    json_defines += 'JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON=1'
+endif
+if get_option('StrictNulHandling')
+    json_defines += 'JSON_STRICT_NUL_HANDLING=1'
+endif
+if get_option('StrictBinaryUTF8')
+    json_defines += 'JSON_STRICT_BINARY_UTF8=1'
+endif
+if get_option('DeleteDeprecatedFunctions')
+    json_defines += 'JSON_DELETE_DEPRECATED_FUNCTIONS=1'
+endif
+
+cpp_args = []
+foreach define : json_defines
+    cpp_args += '-D' + define
+endforeach
+
 nlohmann_json_dep = declare_dependency(
-    include_directories: include_directories('single_include')
+    compile_args: cpp_args,
+    include_directories: include_directories(incdir)
 )
+meson.override_dependency('nlohmann_json', nlohmann_json_dep)
 
+# The multi-header version under the name earlier versions of this file used
 nlohmann_json_multiple_headers = declare_dependency(
+    compile_args: cpp_args,
     include_directories: include_directories('include')
 )
 
 if not meson.is_subproject()
-install_headers('single_include/nlohmann/json.hpp', subdir: 'nlohmann')
-install_headers('single_include/nlohmann/json_fwd.hpp', subdir: 'nlohmann')
-install_headers('single_include/nlohmann/json_literals.hpp', subdir: 'nlohmann')
+    install_subdir(
+        incdir / 'nlohmann',
+        install_dir: get_option('includedir'),
+        install_tag: 'devel',
+    )
 
-pkgc = import('pkgconfig')
-pkgc.generate(name: 'nlohmann_json',
-    version: meson.project_version(),
-    description: 'JSON for Modern C++'
-)
+    pkgc = import('pkgconfig')
+    pkgc.generate(name: 'nlohmann_json',
+        version: meson.project_version(),
+        description: 'JSON for Modern C++',
+        extra_cflags: cpp_args,
+        install_dir: get_option('datadir') / 'pkgconfig',
+    )
+
+    # CMake package config files, so that find_package(nlohmann_json) works. The
+    # include directory is given relative to the config files, so that the
+    # installation can be relocated. This is not possible if includedir or datadir
+    # is an absolute path outside the prefix (e.g., with the separate outputs of
+    # Nix); then the absolute include directory is used, as CMake does.
+    fs = import('fs')
+    cmake_install_dir = get_option('datadir') / 'cmake' / meson.project_name()
+    cmake_to_prefix = []
+    if fs.is_absolute(get_option('includedir')) or fs.is_absolute(cmake_install_dir)
+        cmake_include_dir = (get_option('prefix') / get_option('includedir')).replace('\\', '/')
+    else
+        foreach component : cmake_install_dir.split('/')
+            cmake_to_prefix += '..'
+        endforeach
+        cmake_include_dir = '${_IMPORT_PREFIX}/' + get_option('includedir')
+    endif
+
+    cmake_conf = configuration_data()
+    cmake_conf.set('PROJECT_NAME', meson.project_name())
+    cmake_conf.set('PROJECT_VERSION', meson.project_version())
+    cmake_conf.set('PROJECT_VERSION_MAJOR', meson.project_version().split('.')[0])
+    cmake_conf.set('NLOHMANN_JSON_TARGET_NAME', meson.project_name())
+    cmake_conf.set('NLOHMANN_JSON_TARGETS_EXPORT_NAME', meson.project_name() + 'Targets')
+    cmake_conf.set('NLOHMANN_JSON_INCLUDE_DIR', cmake_include_dir)
+    cmake_conf.set('NLOHMANN_JSON_CONFIG_TO_PREFIX', '/'.join(cmake_to_prefix))
+    cmake_conf.set('NLOHMANN_JSON_COMPILE_DEFINITIONS', ';'.join(json_defines))
+
+    foreach cmake_file : [
+        ['cmake/config.cmake.in', 'nlohmann_jsonConfig.cmake'],
+        ['cmake/nlohmann_jsonConfigVersion.cmake.in', 'nlohmann_jsonConfigVersion.cmake'],
+        ['cmake/nlohmann_jsonTargets.cmake.in', 'nlohmann_jsonTargets.cmake'],
+    ]
+        configure_file(
+            input: cmake_file[0],
+            output: cmake_file[1],
+            configuration: cmake_conf,
+            format: 'cmake@',
+            install_dir: cmake_install_dir,
+        )
+    endforeach
 endif

meson_options.txt

@@ -0,0 +1,66 @@
+option(
+    'MultipleHeaders',
+    type: 'boolean',
+    value: false,
+    description: 'Use non-amalgamated version of the library',
+)
+option(
+    'GlobalUDLs',
+    type: 'boolean',
+    value: true,
+    description: 'Place user-defined string literals in the global namespace',
+)
+option(
+    'ImplicitConversions',
+    type: 'boolean',
+    value: true,
+    description: 'Enable implicit conversions',
+)
+option(
+    'DisableEnumSerialization',
+    type: 'boolean',
+    value: false,
+    description: 'Disable default integer enum serialization',
+)
+option(
+    'DisableTupleReferenceConversion',
+    type: 'boolean',
+    value: false,
+    description: 'Disable conversion from a one-element tuple of a JSON reference',
+)
+option(
+    'Diagnostics',
+    type: 'boolean',
+    value: false,
+    description: 'Use extended diagnostic messages',
+)
+option(
+    'Diagnostic_Positions',
+    type: 'boolean',
+    value: false,
+    description: 'Enable diagnostic positions',
+)
+option(
+    'LegacyDiscardedValueComparison',
+    type: 'boolean',
+    value: false,
+    description: 'Enable legacy discarded value comparison',
+)
+option(
+    'StrictNulHandling',
+    type: 'boolean',
+    value: false,
+    description: 'Enable strict NUL-byte handling',
+)
+option(
+    'StrictBinaryUTF8',
+    type: 'boolean',
+    value: false,
+    description: 'Enable UTF-8 checks in the CBOR, UBJSON, BJData, and BSON writers',
+)
+option(
+    'DeleteDeprecatedFunctions',
+    type: 'boolean',
+    value: false,
+    description: 'Delete the deprecated functions instead of only deprecating them',
+)

src/modules/json.cppm

@@ -47,7 +47,6 @@ inline namespace json_literals
 namespace detail
 {
     using NLOHMANN_JSON_NAMESPACE::detail::json_sax_dom_callback_parser;
-    using NLOHMANN_JSON_NAMESPACE::detail::json_sax_dom_parser;
     using NLOHMANN_JSON_NAMESPACE::detail::unknown_size;
 } // namespace detail
 

tests/CMakeLists.txt

@@ -138,7 +138,8 @@ json_test_set_test_options(test-disabled_exceptions
 # only the #972 regression test needs thirdparty/fifo_map on its include path
 json_test_set_test_options(test-regression1 LINK_LIBRARIES fifo_map_include)
 
-# GCC's false -Warray-bounds error with JSON_DIAGNOSTICS only shows up when optimizing (#5742).
+# Regression test for GCC's false -Warray-bounds error with JSON_DIAGNOSTICS (#5742, fixed in #5585). It only
+# showed up when optimizing, so build this test with -O3 and the warning as an error.
 # -O3 makes the optimizer-driven warnings of the ci_test_gcc flag set (-Winline,
 # -Wsuggest-attribute=...) fire on the library's inline functions; they are not
 # what this test checks, so turn them off for it.

tests/src/fuzzer-parse_bjdata.cpp

@@ -47,10 +47,6 @@ dumps is stable under exactly the same values that break operator==.
 The unit tests run the same checks on a fixed corpus (see the "BJData round-trip
 invariants" test case), so keep both in sync.
 
-Furthermore, it reads data with a SAX parser that recovers from every error
-and checks that the events are balanced, that reading ends, and that it
-reports an error exactly when from_bjdata() fails (see #3989).
-
 The provided function `LLVMFuzzerTestOneInput` can be used in different fuzzer
 drivers.
 */
@@ -63,8 +59,6 @@ drivers.
     #error "the fuzzer drivers must be built without NDEBUG"
 #endif
 
-#include "fuzzer-recovering_checker.hpp"
-
 using json = nlohmann::json;
 
 // compares dumps rather than values, because NaN != NaN; keep writes strings
@@ -84,9 +78,6 @@ static bool is_value_stable(const json& lhs, const json& rhs)
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
-    // recover from all errors, reading from memory and from a stream
-    const bool recovered_without_errors = check_recovering_parse(data, size, json::input_format_t::bjdata).errors == 0;
-
     std::vector<uint8_t> const vec1(data, data + size);
 
     // step 0: parse input without exceptions; a parse error must then be
@@ -119,9 +110,6 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
         // without exceptions, the same input must give the same value
         assert(!noexcept_threw && !j_noexcept.is_discarded() && same_value(j_noexcept, j1));
 
-        // the recovering parser must not have reported an error either
-        assert(recovered_without_errors);
-
         try
         {
             // step 2.1: round trip without adding size annotations to container types
@@ -155,7 +143,6 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // parse errors are ok, because input may be random bytes
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
-        assert(parsed || !recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -166,7 +153,6 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // out of range errors may happen if provided sizes are excessive
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
-        assert(parsed || !recovered_without_errors);
     }
 
     // return 0 - non-zero return values are reserved for future use

tests/src/fuzzer-parse_bon8.cpp

@@ -21,10 +21,6 @@ It also checks that reading the data from a stream, which reads strings byte by
 byte, gives the same value or error as reading it from contiguous memory, which
 copies strings in bulk.
 
-Furthermore, it reads data with a SAX parser that recovers from every error
-and checks that the events are balanced, that reading ends, and that it
-reports an error exactly when from_bon8() fails (see #3989).
-
 The provided function `LLVMFuzzerTestOneInput` can be used in different fuzzer
 drivers.
 */
@@ -38,8 +34,6 @@ drivers.
     #error "the fuzzer drivers must be built without NDEBUG"
 #endif
 
-#include "fuzzer-recovering_checker.hpp"
-
 using json = nlohmann::json;
 
 // compares dumps rather than values, because NaN != NaN; keep writes strings
@@ -70,9 +64,6 @@ std::string read_bon8(InputType&& input)
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
-    // recover from all errors, reading from memory and from a stream
-    const bool recovered_without_errors = check_recovering_parse(data, size, json::input_format_t::bon8).errors == 0;
-
     // contiguous and stream input must be read alike
     {
         std::istringstream stream(std::string(reinterpret_cast<const char*>(data), size));
@@ -111,9 +102,6 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
         // without exceptions, the same input must give the same value
         assert(!noexcept_threw && !j_noexcept.is_discarded() && same_value(j_noexcept, j1));
 
-        // the recovering parser must not have reported an error either
-        assert(recovered_without_errors);
-
         try
         {
             // step 2: round trip
@@ -135,7 +123,6 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // parse errors are ok, because input may be random bytes
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
-        assert(parsed || !recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -146,7 +133,6 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // out of range errors may happen if provided sizes are excessive
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
-        assert(parsed || !recovered_without_errors);
     }
 
     // return 0 - non-zero return values are reserved for future use

tests/src/fuzzer-parse_bson.cpp

@@ -17,10 +17,6 @@ array data, it performs the following steps:
 - j2 = from_bson(vec)
 - assert(to_bson(j2) == vec)
 
-Furthermore, it reads data with a SAX parser that recovers from every error
-and checks that the events are balanced, that reading ends, and that it
-reports an error exactly when from_bson() fails (see #3989).
-
 The provided function `LLVMFuzzerTestOneInput` can be used in different fuzzer
 drivers.
 */
@@ -33,8 +29,6 @@ drivers.
     #error "the fuzzer drivers must be built without NDEBUG"
 #endif
 
-#include "fuzzer-recovering_checker.hpp"
-
 using json = nlohmann::json;
 
 // compares dumps rather than values, because NaN != NaN; keep writes strings
@@ -47,9 +41,6 @@ static bool same_value(const json& lhs, const json& rhs)
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
-    // recover from all errors, reading from memory and from a stream
-    const bool recovered_without_errors = check_recovering_parse(data, size, json::input_format_t::bson).errors == 0;
-
     std::vector<uint8_t> const vec1(data, data + size);
 
     // step 0: parse input without exceptions; a parse error must then be
@@ -82,9 +73,6 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
         // without exceptions, the same input must give the same value
         assert(!noexcept_threw && !j_noexcept.is_discarded() && same_value(j_noexcept, j1));
 
-        // the recovering parser must not have reported an error either
-        assert(recovered_without_errors);
-
         try
         {
             // step 2: round trip
@@ -106,7 +94,6 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // parse errors are ok, because input may be random bytes
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
-        assert(parsed || !recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -117,7 +104,6 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // out of range errors can occur during parsing, too
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
-        assert(parsed || !recovered_without_errors);
     }
 
     // return 0 - non-zero return values are reserved for future use

tests/src/fuzzer-parse_cbor.cpp

@@ -17,10 +17,6 @@ array data, it performs the following steps:
 - j2 = from_cbor(vec)
 - assert(to_cbor(j2) == vec)
 
-Furthermore, it reads data with a SAX parser that recovers from every error
-and checks that the events are balanced, that reading ends, and that it
-reports an error exactly when from_cbor() fails (see #3989).
-
 The provided function `LLVMFuzzerTestOneInput` can be used in different fuzzer
 drivers.
 */
@@ -33,8 +29,6 @@ drivers.
     #error "the fuzzer drivers must be built without NDEBUG"
 #endif
 
-#include "fuzzer-recovering_checker.hpp"
-
 using json = nlohmann::json;
 
 // compares dumps rather than values, because NaN != NaN; keep writes strings
@@ -47,9 +41,6 @@ static bool same_value(const json& lhs, const json& rhs)
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
-    // recover from all errors, reading from memory and from a stream
-    const bool recovered_without_errors = check_recovering_parse(data, size, json::input_format_t::cbor).errors == 0;
-
     std::vector<uint8_t> const vec1(data, data + size);
 
     // step 0: parse input without exceptions; a parse error must then be
@@ -82,9 +73,6 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
         // without exceptions, the same input must give the same value
         assert(!noexcept_threw && !j_noexcept.is_discarded() && same_value(j_noexcept, j1));
 
-        // the recovering parser must not have reported an error either
-        assert(recovered_without_errors);
-
         try
         {
             // step 2: round trip
@@ -106,7 +94,6 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // parse errors are ok, because input may be random bytes
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
-        assert(parsed || !recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -117,7 +104,6 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // out of range errors can occur during parsing, too
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
-        assert(parsed || !recovered_without_errors);
     }
 
     // return 0 - non-zero return values are reserved for future use

tests/src/fuzzer-parse_json.cpp

@@ -18,10 +18,6 @@ array data, it performs the following steps:
 - s2 = serialize(j2)
 - assert(s1 == s2)
 
-Furthermore, it parses data with a SAX parser that recovers from every error
-and checks that the events are balanced, that parsing ends, and that valid
-input is parsed without errors (see #3989).
-
 The provided function `LLVMFuzzerTestOneInput` can be used in different fuzzer
 drivers.
 */
@@ -34,8 +30,6 @@ drivers.
     #error "the fuzzer drivers must be built without NDEBUG"
 #endif
 
-#include "fuzzer-recovering_checker.hpp"
-
 using json = nlohmann::json;
 
 // compares dumps rather than values, because NaN != NaN; keep writes strings
@@ -48,13 +42,6 @@ static bool same_value(const json& lhs, const json& rhs)
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
-    // recover from all errors, reading from memory and from a stream
-    {
-        const auto checker = check_recovering_parse(data, size, json::input_format_t::json);
-        assert(checker.events <= (4 * size) + 4);
-        assert((checker.errors == 0) == json::accept(data, data + size));
-    }
-
     // step 0: parse input without exceptions; a parse error must then be
     // reported as a discarded value, never thrown
     json j_noexcept;

tests/src/fuzzer-parse_msgpack.cpp

@@ -17,10 +17,6 @@ array data, it performs the following steps:
 - j2 = from_msgpack(vec)
 - assert(to_msgpack(j2) == vec)
 
-Furthermore, it reads data with a SAX parser that recovers from every error
-and checks that the events are balanced, that reading ends, and that it
-reports an error exactly when from_msgpack() fails (see #3989).
-
 The provided function `LLVMFuzzerTestOneInput` can be used in different fuzzer
 drivers.
 */
@@ -33,8 +29,6 @@ drivers.
     #error "the fuzzer drivers must be built without NDEBUG"
 #endif
 
-#include "fuzzer-recovering_checker.hpp"
-
 using json = nlohmann::json;
 
 // compares dumps rather than values, because NaN != NaN; keep writes strings
@@ -47,9 +41,6 @@ static bool same_value(const json& lhs, const json& rhs)
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
-    // recover from all errors, reading from memory and from a stream
-    const bool recovered_without_errors = check_recovering_parse(data, size, json::input_format_t::msgpack).errors == 0;
-
     std::vector<uint8_t> const vec1(data, data + size);
 
     // step 0: parse input without exceptions; a parse error must then be
@@ -82,9 +73,6 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
         // without exceptions, the same input must give the same value
         assert(!noexcept_threw && !j_noexcept.is_discarded() && same_value(j_noexcept, j1));
 
-        // the recovering parser must not have reported an error either
-        assert(recovered_without_errors);
-
         try
         {
             // step 2: round trip
@@ -106,7 +94,6 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // parse errors are ok, because input may be random bytes
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
-        assert(parsed || !recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -117,7 +104,6 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // out of range errors may happen if provided sizes are excessive
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
-        assert(parsed || !recovered_without_errors);
     }
 
     // return 0 - non-zero return values are reserved for future use

tests/src/fuzzer-parse_ubjson.cpp

@@ -26,10 +26,6 @@ array data, it performs the following steps:
 The unit tests run the same checks on a fixed corpus (see the "UBJSON round-trip
 invariants" test case), so keep both in sync.
 
-Furthermore, it reads data with a SAX parser that recovers from every error
-and checks that the events are balanced, that reading ends, and that it
-reports an error exactly when from_ubjson() fails (see #3989).
-
 The provided function `LLVMFuzzerTestOneInput` can be used in different fuzzer
 drivers.
 */
@@ -42,8 +38,6 @@ drivers.
     #error "the fuzzer drivers must be built without NDEBUG"
 #endif
 
-#include "fuzzer-recovering_checker.hpp"
-
 using json = nlohmann::json;
 
 // compares dumps rather than values, because NaN != NaN; keep writes strings
@@ -56,9 +50,6 @@ static bool same_value(const json& lhs, const json& rhs)
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
-    // recover from all errors, reading from memory and from a stream
-    const bool recovered_without_errors = check_recovering_parse(data, size, json::input_format_t::ubjson).errors == 0;
-
     std::vector<uint8_t> const vec1(data, data + size);
 
     // step 0: parse input without exceptions; a parse error must then be
@@ -91,9 +82,6 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
         // without exceptions, the same input must give the same value
         assert(!noexcept_threw && !j_noexcept.is_discarded() && same_value(j_noexcept, j1));
 
-        // the recovering parser must not have reported an error either
-        assert(recovered_without_errors);
-
         try
         {
             // step 2.1: round trip without adding size annotations to container types
@@ -125,7 +113,6 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // parse errors are ok, because input may be random bytes
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
-        assert(parsed || !recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -136,7 +123,6 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // out of range errors may happen if provided sizes are excessive
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
-        assert(parsed || !recovered_without_errors);
     }
 
     // return 0 - non-zero return values are reserved for future use

tests/src/fuzzer-recovering_checker.hpp

@@ -1,154 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  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
-
-#pragma once
-
-#include <cassert>
-#include <cstddef>
-#include <cstdint>
-#include <sstream>
-#include <string>
-#include <vector>
-#include <nlohmann/json.hpp>
-
-namespace
-{
-// a SAX parser that recovers from every error and checks that the events are
-// balanced and that every key is followed by exactly one value
-class recovering_checker : public nlohmann::json_sax<nlohmann::json>
-{
-  public:
-    bool null() override
-    {
-        return value();
-    }
-
-    bool boolean(bool /*val*/) override
-    {
-        return value();
-    }
-
-    bool number_integer(number_integer_t /*val*/) override
-    {
-        return value();
-    }
-
-    bool number_unsigned(number_unsigned_t /*val*/) override
-    {
-        return value();
-    }
-
-    bool number_float(number_float_t /*val*/, const string_t& /*s*/) override
-    {
-        return value();
-    }
-
-    bool string(string_t& /*val*/) override
-    {
-        return value();
-    }
-
-    bool binary(binary_t& /*val*/) override
-    {
-        return value();
-    }
-
-    bool start_object(std::size_t /*elements*/) override
-    {
-        value();
-        stack.push_back('o');
-        return true;
-    }
-
-    bool key(string_t& /*val*/) override
-    {
-        ++events;
-        assert(!stack.empty() && stack.back() == 'o');
-        stack.back() = 'v';
-        return true;
-    }
-
-    bool end_object() override
-    {
-        ++events;
-        assert(!stack.empty() && stack.back() == 'o');
-        stack.pop_back();
-        return true;
-    }
-
-    bool start_array(std::size_t /*elements*/) override
-    {
-        value();
-        stack.push_back('a');
-        return true;
-    }
-
-    bool end_array() override
-    {
-        ++events;
-        assert(!stack.empty() && stack.back() == 'a');
-        stack.pop_back();
-        return true;
-    }
-
-    bool parse_error(std::size_t /*position*/, const std::string& /*last_token*/, const nlohmann::detail::exception& /*ex*/) override
-    {
-        ++errors;
-        return true;
-    }
-
-    bool complete() const
-    {
-        return stack.empty();
-    }
-
-    std::size_t events = 0;
-    std::size_t errors = 0;
-
-  private:
-    bool value()
-    {
-        ++events;
-        if (!stack.empty())
-        {
-            // an array element, or the value of a key
-            assert(stack.back() != 'o');
-            if (stack.back() == 'v')
-            {
-                stack.back() = 'o';
-            }
-        }
-        return true;
-    }
-
-    // 'a' for an array, 'o' for an object that expects a key, 'v' for an
-    // object that expects the value of a key
-    std::vector<char> stack {}; // NOLINT(readability-redundant-member-init)
-};
-
-/// parses @a data with a recovering_checker from memory and from a stream,
-/// checks that both see the same, that the events are balanced, and that the
-/// number of errors is bounded, and returns the checker (see #3989)
-inline recovering_checker check_recovering_parse(const std::uint8_t* data, const std::size_t size, const nlohmann::json::input_format_t format)
-{
-    recovering_checker checker;
-    const bool ok = nlohmann::json::sax_parse(data, data + size, &checker, format);
-    assert(checker.complete());
-    assert(checker.errors <= size + 1);
-    assert(ok == (checker.errors == 0));
-
-    std::istringstream stream(std::string(reinterpret_cast<const char*>(data), size));
-    recovering_checker stream_checker;
-    assert(nlohmann::json::sax_parse(stream, &stream_checker, format) == ok);
-    assert(stream_checker.complete());
-    assert(stream_checker.events == checker.events);
-    assert(stream_checker.errors == checker.errors);
-
-    return checker;
-}
-} // namespace

tests/src/unit-allocator.cpp

@@ -370,14 +370,7 @@ TEST_CASE("copy of a deeply nested value survives a failing allocation (#5640)")
 #if !(defined(_ITERATOR_DEBUG_LEVEL) && _ITERATOR_DEBUG_LEVEL > 0)
     SECTION("std::map-backed object_t")
     {
-        using bad_alloc_json = nlohmann::basic_json<std::map,
-              std::vector,
-              std::string,
-              bool,
-              std::int64_t,
-              std::uint64_t,
-              double,
-              nth_alloc_fails_allocator>;
+        using bad_alloc_json = nlohmann::json::with_allocator_t<nth_alloc_fails_allocator>;
 
         check_deep_copy_survives_failing_allocation<bad_alloc_json>(false);
         check_deep_copy_survives_failing_allocation<bad_alloc_json>(true);
@@ -385,14 +378,7 @@ TEST_CASE("copy of a deeply nested value survives a failing allocation (#5640)")
 
     SECTION("ordered_map-backed object_t")
     {
-        using bad_alloc_ordered_json = nlohmann::basic_json<nlohmann::ordered_map,
-              std::vector,
-              std::string,
-              bool,
-              std::int64_t,
-              std::uint64_t,
-              double,
-              nth_alloc_fails_allocator>;
+        using bad_alloc_ordered_json = nlohmann::ordered_json::with_allocator_t<nth_alloc_fails_allocator>;
 
         check_deep_copy_survives_failing_allocation<bad_alloc_ordered_json>(false);
         check_deep_copy_survives_failing_allocation<bad_alloc_ordered_json>(true);
@@ -450,14 +436,7 @@ struct scratch_counting_allocator : std::allocator<T>
 
 TEST_CASE("deep copy uses the provided allocator")
 {
-    using counting_json = nlohmann::basic_json<std::map,
-          std::vector,
-          std::string,
-          bool,
-          std::int64_t,
-          std::uint64_t,
-          double,
-          scratch_counting_allocator>;
+    using counting_json = nlohmann::json::with_allocator_t<scratch_counting_allocator>;
 
     // deeper than the 128 levels the copy constructor descends into, so the
     // innermost objects are copied by the iterative deep copy
@@ -516,14 +495,7 @@ TEST_CASE("converting a deeply nested value from another specialization fails cl
     // the allocator in noexcept constructors, so a failing construction crashes
     // the program there instead of throwing std::bad_alloc. Nothing to check.
 #if !(defined(_MSC_VER) && _MSC_VER < 1910 && defined(_ITERATOR_DEBUG_LEVEL) && _ITERATOR_DEBUG_LEVEL > 0)
-    using countdown_json = nlohmann::basic_json<std::map,
-          std::vector,
-          std::string,
-          bool,
-          std::int64_t,
-          std::uint64_t,
-          double,
-          countdown_allocator>;
+    using countdown_json = nlohmann::json::with_allocator_t<countdown_allocator>;
 
     // deeper than the 128 levels the converting constructor descends into, so
     // that failures land on both sides of the bound - or, built with
@@ -631,14 +603,7 @@ TEST_CASE("destructor performs no allocation, only deallocation")
     // Since that stack could itself throw bad_alloc from inside the
     // noexcept destructor (#5135), destroy() no longer allocates anything:
     // it only ever frees what is already there.
-    using counting_json = nlohmann::basic_json<std::map,
-          std::vector,
-          std::string,
-          bool,
-          std::int64_t,
-          std::uint64_t,
-          double,
-          counting_allocator>;
+    using counting_json = nlohmann::json::with_allocator_t<counting_allocator>;
 
     SECTION("array")
     {
@@ -683,14 +648,7 @@ TEST_CASE("destructor performs no allocation, only deallocation")
 TEST_CASE("a failed allocation leaves the value unchanged")
 {
     // create JSON type using the throwing allocator
-    using my_json = nlohmann::basic_json<std::map,
-          std::vector,
-          std::string,
-          bool,
-          std::int64_t,
-          std::uint64_t,
-          double,
-          my_allocator>;
+    using my_json = nlohmann::json::with_allocator_t<my_allocator>;
 
     // Each of these creates a string, array, object, or binary value. The
     // value must be created before the type is changed: otherwise, a failed

tests/src/unit-alt-string.cpp

@@ -415,46 +415,6 @@ TEST_CASE("alternative string type")
         CHECK(j2.dump() == R"({"/foo/0":"bar","/foo/1":"baz"})");
     }
 
-    SECTION("error recovery")
-    {
-        // a SAX parser that recovers from every error (see #3989)
-        struct recovering_parser : nlohmann::detail::json_sax_dom_parser<alt_json>
-        {
-            explicit recovering_parser(alt_json& j)
-                : nlohmann::detail::json_sax_dom_parser<alt_json>(j, false)
-            {}
-
-            // sax_parse() calls the SAX parser's own parse_error(), so hiding
-            // the one of the base class is what recovering takes
-            // NOLINTNEXTLINE(bugprone-derived-method-shadowing-base-method)
-            bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/, const nlohmann::detail::exception& /*unused*/)
-            {
-                ++errors;
-                return true;
-            }
-
-            std::size_t errors = 0;
-        };
-
-        alt_json j;
-        recovering_parser sax(j);
-        // not inside CHECK(): MSVC reads the escape in a stringized raw string
-        const std::string input = R"([1., "a\qb", tru, {"k" 2}])";
-        CHECK(!alt_json::sax_parse(input, &sax));
-        CHECK(sax.errors == 4);
-        CHECK(j.dump() == R"([1,"aqb",null,{"k":2}])");
-
-        // a UBJSON high-precision number, a CBOR key that is not a string
-        alt_json u;
-        recovering_parser ubjson_sax(u);
-        CHECK(!alt_json::sax_parse(std::vector<std::uint8_t> {'[', 'H', 'i', 2, '1', '.', ']'}, &ubjson_sax, alt_json::input_format_t::ubjson));
-        CHECK(u.dump() == "[1]");
-        alt_json c;
-        recovering_parser cbor_sax(c);
-        CHECK(!alt_json::sax_parse(std::vector<std::uint8_t> {0xA2, 0x01, 0x02, 0x61, 'a', 0x03}, &cbor_sax, alt_json::input_format_t::cbor));
-        CHECK(c.dump() == R"({"a":3})");
-    }
-
     SECTION("conversion between basic_json specializations (#2649)")
     {
         // explicit conversions are always possible

tests/src/unit-binary_formats.cpp

@@ -237,7 +237,7 @@ namespace
 // the binary formats as function pointers for "Binary formats with narrow number types";
 // named functions rather than lambdas, because clang 3.5 cannot convert a lambda
 // to a function pointer in the braced initializer of the format table
-using narrow_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int32_t, std::uint32_t, float>;
+using narrow_json = nlohmann::json::with_integers_t<std::int32_t, std::uint32_t>::with_float_t<float>;
 using bytes = std::vector<std::uint8_t>;
 
 bytes encode_cbor(const json& j)

tests/src/unit-binary_utf8_error_handler.cpp

@@ -12,7 +12,10 @@
 #include <nlohmann/json.hpp>
 using nlohmann::json;
 
+#include <map>
+#include <memory>
 #include <string>
+#include <utility>
 #include <vector>
 
 namespace
@@ -55,6 +58,49 @@ std::string dump_and_parse(const std::string& raw, eh error_handler)
     return json::parse(json(raw).dump(-1, ' ', false, error_handler)).get<std::string>();
 }
 
+// an object key type that is not string_t, but converts implicitly to it
+class converting_key
+{
+  public:
+    converting_key(const char* s) : m_value(s) {} // NOLINT(google-explicit-constructor,hicpp-explicit-conversions)
+    converting_key(std::string s) : m_value(std::move(s)) {} // NOLINT(google-explicit-constructor,hicpp-explicit-conversions)
+
+    // the conversion yields a temporary string_t
+    operator std::string() const // NOLINT(google-explicit-constructor,hicpp-explicit-conversions)
+    {
+        return m_value;
+    }
+
+    // read by the exception messages when JSON_DIAGNOSTICS is enabled
+    const char* data() const noexcept
+    {
+        return m_value.data();
+    }
+
+    friend bool operator<(const converting_key& lhs, const converting_key& rhs)
+    {
+        return lhs.m_value < rhs.m_value;
+    }
+
+  private:
+    std::string m_value;
+};
+
+// ObjectType using converting_key; the Key template argument is ignored
+template<typename Key, typename Value, typename Compare, typename Allocator>
+class converting_key_object : public std::map<converting_key, Value, std::less<converting_key>, // NOLINT(modernize-use-transparent-functors)
+    typename std::allocator_traits<Allocator>::template rebind_alloc<std::pair<const converting_key, Value>>>
+{
+    using base_type = std::map<converting_key, Value, std::less<converting_key>, // NOLINT(modernize-use-transparent-functors)
+                               typename std::allocator_traits<Allocator>::template rebind_alloc<std::pair<const converting_key, Value>>>;
+
+                             public:
+                               using base_type::base_type;
+                               using base_type::operator=;
+};
+
+using converting_key_json = nlohmann::basic_json<converting_key_object>;
+
 } // namespace
 
 TEST_CASE("UTF-8 error_handler for the binary readers and writers")
@@ -370,3 +416,109 @@ TEST_CASE("UTF-8 error_handler for the binary readers and writers")
         CHECK(json::from_bson(bson_bytes)["k"].get<std::string>() == ill_formed_cases()[0].bytes);
     }
 }
+
+// The UBJSON and BJData writers bind the (possibly sanitized) key to a const
+// string_t&. If key_type is not string_t but converts to it, the converted
+// temporary must outlive that reference; this was a use-after-scope found by
+// AddressSanitizer. Keys exceed the small string optimization on purpose.
+TEST_CASE("UBJSON and BJData writers with an object_t whose key_type is not string_t")
+{
+    const std::string long_prefix(70, 'k');
+
+    SECTION("well-formed keys, every error_handler")
+    {
+        const std::string key1 = long_prefix + "-first";
+        const std::string key2 = long_prefix + "-second";
+
+        converting_key_json::object_t o;
+        o.emplace(converting_key(key1), 1);
+        o.emplace(converting_key(key2), "value");
+        const converting_key_json v(std::move(o));
+
+        json expected;
+        expected[key1] = 1;
+        expected[key2] = "value";
+
+        const bool combos[3][2] = {{false, false}, {true, false}, {true, true}};
+        for (const auto h : all_handlers())
+        {
+            CAPTURE(static_cast<int>(h))
+            for (const auto& combo : combos)
+            {
+                const bool use_count = combo[0];
+                const bool use_type = combo[1];
+                CAPTURE(use_count)
+                CAPTURE(use_type)
+
+                CHECK(json::from_ubjson(converting_key_json::to_ubjson(v, use_count, use_type, h)) == expected);
+                CHECK(json::from_bjdata(converting_key_json::to_bjdata(v, use_count, use_type, json::bjdata_version_t::draft2, h)) == expected);
+                CHECK(json::from_bjdata(converting_key_json::to_bjdata(v, use_count, use_type, json::bjdata_version_t::draft3, h)) == expected);
+            }
+        }
+    }
+
+    SECTION("ill-formed keys")
+    {
+        for (const auto& c : ill_formed_cases())
+        {
+            CAPTURE(c.name)
+            const std::string key = long_prefix + c.bytes;
+
+            converting_key_json::object_t o;
+            o.emplace(converting_key(key), 1);
+            const converting_key_json v(std::move(o));
+
+            CHECK_THROWS_AS(converting_key_json::to_ubjson(v, false, false, eh::strict), converting_key_json::type_error&);
+            CHECK_THROWS_AS(converting_key_json::to_bjdata(v, false, false, json::bjdata_version_t::draft2, eh::strict), converting_key_json::type_error&);
+
+            for (const auto h :
+                    {
+                        eh::replace, eh::ignore
+                    })
+            {
+                CAPTURE(static_cast<int>(h))
+                const std::string expected = dump_and_parse(key, h);
+
+                CHECK(json::from_ubjson(converting_key_json::to_ubjson(v, false, false, h)).begin().key() == expected);
+                CHECK(json::from_bjdata(converting_key_json::to_bjdata(v, false, false, json::bjdata_version_t::draft2, h)).begin().key() == expected);
+            }
+
+            CHECK(json::from_ubjson(converting_key_json::to_ubjson(v, false, false, eh::keep)).begin().key() == key);
+            CHECK(json::from_bjdata(converting_key_json::to_bjdata(v, false, false, json::bjdata_version_t::draft2, eh::keep)).begin().key() == key);
+        }
+    }
+
+    SECTION("nested deeper than the recursion limit")
+    {
+        // wrap the previous value, innermost first
+        converting_key_json v = 42;
+        json expected = 42;
+        for (int i = 199; i >= 0; --i)
+        {
+            const std::string key = "level-" + std::to_string(i) + "-" + std::string(64, 'x');
+
+            converting_key_json::object_t o;
+            o.emplace(converting_key(key), std::move(v));
+            v = converting_key_json(std::move(o));
+
+            json e;
+            e[key] = std::move(expected);
+            expected = std::move(e);
+        }
+
+        for (const auto h : all_handlers())
+        {
+            CAPTURE(static_cast<int>(h))
+            for (const bool use_count :
+                    {
+                        false, true
+                    })
+            {
+                CAPTURE(use_count)
+
+                CHECK(json::from_ubjson(converting_key_json::to_ubjson(v, use_count, false, h)) == expected);
+                CHECK(json::from_bjdata(converting_key_json::to_bjdata(v, use_count, false, json::bjdata_version_t::draft2, h)) == expected);
+            }
+        }
+    }
+}

tests/src/unit-class_lexer.cpp

@@ -17,6 +17,7 @@ using nlohmann::json;
 #include <cstdint> // uint32_t, uint64_t
 #include <cstdlib> // strtod
 #include <cstring> // memcpy
+#include <limits> // numeric_limits
 #include <sstream> // stringstream
 #include <string> // string
 #include <utility> // pair
@@ -891,8 +892,39 @@ TEST_CASE("Eisel-Lemire float conversion")
 
     SECTION("128-bit products and leading zeros")
     {
+        const auto check_product = [](std::uint64_t a, std::uint64_t b)
+        {
+            const auto product = nlohmann::detail::full_multiplication(a, b);
+            CHECK(big_from(product.high, product.low) == big_mul(big_from(0, a), big_from(0, b)));
+        };
+
+        const std::uint64_t max = (std::numeric_limits<std::uint64_t>::max)();
+        const std::array<std::pair<std::uint64_t, std::uint64_t>, 13> edge_cases =
+        {
+            {
+                {0, 0},
+                {0, 1},
+                {1, 1},
+                {1, max},
+                {0xFFFFFFFFu, 0x100000000u},
+                {0x100000000u, 0x100000000u},
+                {0x100000001u, 0x100000001u},
+                {max, max},
+                {max, 2},
+                {0xFFFFFFFF00000000u, 0x100000001u},
+                {0x100000001u, 0xFFFFFFFF00000000u},
+                {max, 1},
+                {2, max},
+            }
+        };
+
+        for (const auto& test : edge_cases)
+        {
+            check_product(test.first, test.second);
+        }
+
         // whichever implementation the compiler gets (with or without a
-        // 128-bit integer type or a builtin)
+        // 128-bit integer type or a builtin / intrinsic)
         std::uint64_t state = 42;
         for (int i = 0; i < 10000; ++i)
         {
@@ -901,8 +933,7 @@ TEST_CASE("Eisel-Lemire float conversion")
             state ^= state << 17u;
             const std::uint64_t a = state;
             const std::uint64_t b = (state * 0x9E3779B97F4A7C15u) >> (i % 64);
-            const auto product = nlohmann::detail::full_multiplication(a, b);
-            CHECK(big_from(product.high, product.low) == big_mul(big_from(0, a), big_from(0, b)));
+            check_product(a, b);
 
             const int k = i % 64;
             const std::uint64_t x = (std::uint64_t{1} << k) | (a & ((std::uint64_t{1} << k) - 1));

tests/src/unit-class_parser.cpp

@@ -143,13 +143,11 @@ class SaxEventLogger
     {
         errored = true;
         events.push_back("parse_error(" + std::to_string(position) + ")");
-        return recover;
+        return false;
     }
 
     std::vector<std::string> events {}; // NOLINT(readability-redundant-member-init)
     bool errored = false;
-    /// whether parse_error() asks the parser to recover from the error (see #3989)
-    bool recover = false;
 };
 
 class SaxCountdown : public nlohmann::json::json_sax_t
@@ -3028,583 +3026,3 @@ TEST_CASE("diagnostic positions: value lifetime, input adapters, and SAX")
     }
 }
 #endif
-
-namespace
-{
-/// builds a value like json::parse(), but asks the parser to recover from
-/// errors (see #3989), and checks that the events it receives are balanced
-class RecoveringDomParser
-{
-  public:
-    explicit RecoveringDomParser(json& j, std::size_t max_errors_ = static_cast<std::size_t>(-1))
-        : dom(j, false)
-        , max_errors(max_errors_)
-    {}
-
-    bool null()
-    {
-        value();
-        return dom.null();
-    }
-
-    bool boolean(bool val)
-    {
-        value();
-        return dom.boolean(val);
-    }
-
-    bool number_integer(json::number_integer_t val)
-    {
-        value();
-        return dom.number_integer(val);
-    }
-
-    bool number_unsigned(json::number_unsigned_t val)
-    {
-        value();
-        return dom.number_unsigned(val);
-    }
-
-    bool number_float(json::number_float_t val, const std::string& s)
-    {
-        value();
-        return dom.number_float(val, s);
-    }
-
-    bool string(std::string& val)
-    {
-        value();
-        return dom.string(val);
-    }
-
-    bool binary(json::binary_t& val)
-    {
-        value();
-        return dom.binary(val);
-    }
-
-    bool start_object(std::size_t elements)
-    {
-        value();
-        stack.push_back('o');
-        return dom.start_object(elements);
-    }
-
-    bool key(std::string& val)
-    {
-        ++events;
-        if (stack.empty() || stack.back() != 'o')
-        {
-            well_formed = false;
-            return false;
-        }
-        stack.back() = 'v';
-        return dom.key(val);
-    }
-
-    bool end_object()
-    {
-        ++events;
-        if (stack.empty() || stack.back() != 'o')
-        {
-            well_formed = false;
-            return false;
-        }
-        stack.pop_back();
-        return dom.end_object();
-    }
-
-    bool start_array(std::size_t elements)
-    {
-        value();
-        stack.push_back('a');
-        return dom.start_array(elements);
-    }
-
-    bool end_array()
-    {
-        ++events;
-        if (stack.empty() || stack.back() != 'a')
-        {
-            well_formed = false;
-            return false;
-        }
-        stack.pop_back();
-        return dom.end_array();
-    }
-
-    bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/, const json::exception& ex)
-    {
-        errors.emplace_back(ex.what());
-        return errors.size() < max_errors;
-    }
-
-    /// whether the events were balanced and every key was followed by a value
-    bool balanced() const
-    {
-        return well_formed && stack.empty();
-    }
-
-    /// builds the value
-    nlohmann::detail::json_sax_dom_parser<json> dom;
-    std::vector<std::string> errors {}; // NOLINT(readability-redundant-member-init)
-    std::size_t events = 0;
-    /// the open containers: 'a' for an array, 'o' for an object that expects
-    /// a key, 'v' for an object that expects the value of a key
-    std::vector<char> stack {}; // NOLINT(readability-redundant-member-init)
-    bool well_formed = true;
-    std::size_t max_errors;
-
-  private:
-    /// a value is passed: it is an array element, or the value of a key
-    void value()
-    {
-        ++events;
-        if (!stack.empty())
-        {
-            if (stack.back() == 'v')
-            {
-                stack.back() = 'o';
-            }
-            else if (stack.back() == 'o')
-            {
-                // a value without a key
-                well_formed = false;
-            }
-        }
-    }
-
-};
-
-struct RecoveryResult
-{
-    json value;
-    std::vector<std::string> errors;
-    std::size_t events;
-    bool ok;
-    bool balanced;
-};
-
-template<typename InputType>
-RecoveryResult parse_recovering(InputType&& input, const bool strict = true,
-                                const bool ignore_comments = false, const bool ignore_trailing_commas = false)
-{
-    json j;
-    RecoveringDomParser sax(j);
-    const bool ok = json::sax_parse(std::forward<InputType>(input), &sax, json::input_format_t::json,
-                                    strict, ignore_comments, ignore_trailing_commas);
-    return {j, sax.errors, sax.events, ok, sax.balanced()};
-}
-
-/// stops after a number of events, but recovers from errors
-class RecoveringCountdown : public SaxCountdown
-{
-  public:
-    using SaxCountdown::SaxCountdown;
-
-    bool parse_error(std::size_t /*position*/, const std::string& /*last_token*/, const json::exception& /*ex*/) override
-    {
-        return true;
-    }
-};
-
-/// a repaired input: the value it is repaired to, and the number of errors
-struct Repair
-{
-    const char* input;
-    const char* expected;
-    std::size_t errors;
-};
-} // namespace
-
-TEST_CASE("parser error recovery (#3989)")
-{
-    SECTION("repairs")
-    {
-        const std::vector<Repair> repairs =
-        {
-            // a missing separator is inserted
-            {"[1 2]", "[1,2]", 1},
-            {R"({"a":1 "b":2})", R"({"a":1,"b":2})", 1},
-            {R"({"a" 1})", R"({"a":1})", 1},
-            {"[1 tru 2]", "[1,null,2]", 2},
-            {R"({"a" "b": 1})", R"({"a":"b"})", 2},
-
-            // a missing value is null in an object; in an array, a ',' stands
-            // for null, while an array that ends there just ends
-            {R"({"a":})", R"({"a":null})", 1},
-            {R"({"a"})", R"({"a":null})", 1},
-            {R"({"a","b":1})", R"({"a":null,"b":1})", 1},
-            {"[1,,2]", "[1,null,2]", 1},
-            {"[,1]", "[null,1]", 1},
-            {"[1,]", "[1]", 1},
-            {"[1,2,3,]", "[1,2,3]", 1},
-            {R"({"a":1,})", R"({"a":1})", 1},
-
-            // a broken string keeps what can be read
-            {R"(["a\qb"])", R"(["aqb"])", 1},
-            {R"({"na\me":1})", R"({"name":1})", 1},
-            {"[\"\xFF\"]", R"(["\uFFFD"])", 1},
-            {"[\"a\xC3(\"]", R"(["a\uFFFD("])", 1},
-            {"[\"\xE2\x82\"]", R"(["\uFFFD"])", 1},
-            {"[\"\xC3\\\\\", 1]", R"(["\uFFFD\\",1])", 1},
-            {R"(["\u12"])", R"(["\uFFFD"])", 1},
-            {R"(["\u12G4"])", R"(["\uFFFDG4"])", 1},
-            {R"(["\uDC00x"])", R"(["\uFFFDx"])", 1},
-            {R"(["\uD800x"])", R"(["\uFFFDx"])", 1},
-            {R"(["\uD800\u0041"])", R"(["\uFFFDA"])", 1},
-            {R"(["\uD800\uD800\uDC00"])", R"(["\uFFFD\uD800\uDC00"])", 1},
-            {R"(["\uD800\uD800\uD800x"])", R"(["\uFFFD\uFFFD\uFFFDx"])", 1},
-            {
-                R"(["\uD800\"x", 1])", R"(["\uFFFD\"x",1])", 1
-            },
-            {R"(["\uD800\q"])", R"(["\uFFFDq"])", 1},
-            {"[\"a\tb\"]", R"(["a\tb"])", 1},
-            {R"(["a\qb\u0041\x"])", R"(["aqbAx"])", 1},
-
-            // a broken number keeps its longest valid prefix
-            {"[1.]", "[1]", 1},
-            {"[-2.]", "[-2]", 1},
-            {"[1.5e]", "[1.5]", 1},
-            {"[1e+]", "[1]", 1},
-            {"[1.x2, 3]", "[1,3]", 1},
-
-            // what cannot be read at all is null
-            {"[1,NaN,3]", "[1,null,3]", 1},
-            {"[tru]", "[null]", 1},
-            {"[-]", "[null]", 1},
-            {R"({"a":Infinity})", R"({"a":null})", 1},
-
-            // a stray token is dropped
-            {"[:1]", "[1]", 1},
-            {R"(["a":1])", R"(["a",1])", 1},
-            {R"({"a"::1})", R"({"a":1})", 1},
-
-            // a member that cannot be read is skipped
-            {R"({1:2,"b":3})", R"({"b":3})", 1},
-            {R"({"a":1 2})", R"({"a":1})", 1},
-            {R"({,"a":1})", R"({"a":1})", 1},
-            {R"({"a":1,,"b":2})", R"({"a":1,"b":2})", 1},
-            {"{a:1}", "{}", 1},
-            {R"({"a":1 [1,{"b":2}], "c":3})", R"({"a":1,"c":3})", 1},
-            {R"([{1}, "a"])", R"([{},"a"])", 1},
-
-            // a wrong closing bracket closes the innermost container
-            {R"({"a":[1,2}, "b":3})", R"({"a":[1,2],"b":3})", 1},
-            {R"([{"a":1], 2])", R"([{"a":1},2])", 1},
-            {"{]", "{}", 1},
-            {"[}", "[]", 1},
-
-            // the end of the input closes all containers
-            {R"({"a":[1,2)", R"({"a":[1,2]})", 1},
-            {"[", "[]", 1},
-            {"{", "{}", 1},
-            {R"({"a")", R"({"a":null})", 1},
-            {R"({"a":)", R"({"a":null})", 1},
-            {"[1,", "[1]", 1},
-            {"[[[1", "[[[1]]]", 1},
-            {
-                R"(["abc)", R"(["abc"])", 2
-            },
-            {"[1,tr", "[1,null]", 2},
-            {"\"abc", "\"abc\"", 1},
-            {"[\"ab\ncd\"]", R"(["ab",null,"]"])", 4},
-
-            // what comes before the top-level value is skipped
-            {")]}'\n{\"a\":1}", R"({"a":1})", 1},
-            {R"(data: {"a":1})", R"({"a":1})", 1},
-            {"\xEF\xBB[1]", "[1]", 1},
-
-            // what comes after it is an error that ends parsing
-            {R"({"a":1}})", R"({"a":1})", 1},
-            {"[1}]", "[1]", 2},
-            {"[1] [2]", "[1]", 1},
-        };
-
-        for (const auto& repair : repairs)
-        {
-            CAPTURE(repair.input)
-            const auto result = parse_recovering(std::string(repair.input));
-            CHECK(!result.ok);
-            CHECK(result.balanced);
-            CHECK(result.value == json::parse(repair.expected));
-            CHECK(result.errors.size() == repair.errors);
-        }
-    }
-
-    SECTION("number overflow")
-    {
-        const auto result = parse_recovering(std::string("[1e999,-1e999]"));
-        CHECK(!result.ok);
-        CHECK(result.balanced);
-        CHECK(result.errors.size() == 2);
-        CHECK(result.errors[0] == "[json.exception.out_of_range.406] number overflow parsing '1e999'");
-        REQUIRE(result.value.size() == 2);
-        CHECK(result.value[0].is_number_float());
-        CHECK(result.value[0].get<double>() == std::numeric_limits<double>::infinity());
-        CHECK(result.value[1].get<double>() == -std::numeric_limits<double>::infinity());
-
-        // the SAX parser gets the number's text
-        SaxEventLogger logger;
-        logger.recover = true;
-        CHECK(!json::sax_parse("1e999", &logger));
-        CHECK(logger.events == std::vector<std::string>({"parse_error(5)", "number_float(1e999)"}));
-    }
-
-    SECTION("nothing to recover")
-    {
-        for (const std::string s :
-                {
-                    "", "   ", "]", "tru", "NaN", ",:", "/* comment"
-                })
-        {
-            CAPTURE(s)
-            const auto result = parse_recovering(s, true, true);
-            CHECK(!result.ok);
-            CHECK(result.balanced);
-            CHECK(result.events == 0);
-            CHECK(result.value == nullptr);
-            CHECK(result.errors.size() == 1);
-        }
-    }
-
-    SECTION("error messages")
-    {
-        // the first error is reported as without recovery
-        for (const std::string s :
-                {
-                    "[1 2]", R"({"a":1 "b":2})", R"({"a" 1})", R"({"a":})", "[1,]", "[1.]",
-                    R"(["a\qb"])", "[1e999]", "{1:2}", R"({"a":[1,2}})", "[1,", "[1] [2]", "{a:1}"
-                })
-        {
-            CAPTURE(s)
-            const auto result = parse_recovering(s);
-            REQUIRE(!result.errors.empty());
-            json _;
-            CHECK_THROWS_WITH_STD_STR(_ = json::parse(s), result.errors.front());
-        }
-
-        // the token of an error begins where the previous error was
-        const auto result = parse_recovering(std::string("[tru, fals, nul]"));
-        CHECK(result.errors == std::vector<std::string>(
-        {
-            "[json.exception.parse_error.101] parse error at line 1, column 5: syntax error while parsing value - invalid literal; last read: '[tru,'",
-            "[json.exception.parse_error.101] parse error at line 1, column 11: syntax error while parsing value - invalid literal; last read: ', fals,'",
-            "[json.exception.parse_error.101] parse error at line 1, column 16: syntax error while parsing value - invalid literal; last read: ', nul]'"
-        }));
-        CHECK(result.value == json::parse("[null,null,null]"));
-    }
-
-    SECTION("events")
-    {
-        // see #4522
-        SaxEventLogger logger;
-        logger.recover = true;
-        CHECK(!json::sax_parse(R"([{1}, "a"])", &logger));
-        CHECK(logger.events == std::vector<std::string>(
-        {
-            "start_array()", "start_object()", "parse_error(3)", "end_object()", "string(a)", "end_array()"
-        }));
-    }
-
-    SECTION("options")
-    {
-        SECTION("strict")
-        {
-            const auto result = parse_recovering(std::string("[1 2] [3]"), false);
-            CHECK(!result.ok);
-            CHECK(result.value == json::parse("[1,2]"));
-            CHECK(result.errors.size() == 1);
-        }
-
-        SECTION("ignore_trailing_commas")
-        {
-            for (const std::string s :
-                    {
-                        "[1,]", R"({"a":1,})", "[[1,],]"
-                    })
-            {
-                CAPTURE(s)
-                const auto result = parse_recovering(s, true, false, true);
-                CHECK(result.ok);
-                CHECK(result.errors.empty());
-            }
-
-            auto result = parse_recovering(std::string("[1,,]"), true, false, true);
-            CHECK(result.value == json::parse("[1,null]"));
-            CHECK(result.errors.size() == 1);
-
-            result = parse_recovering(std::string(R"({"a":1,,})"), true, false, true);
-            CHECK(result.value == json::parse(R"({"a":1})"));
-            CHECK(result.errors.size() == 1);
-        }
-
-        SECTION("ignore_comments")
-        {
-            auto result = parse_recovering(std::string("[1 /* one */ 2]"), true, true);
-            CHECK(result.value == json::parse("[1,2]"));
-            CHECK(result.errors.size() == 1);
-
-            // a comment that is not closed runs to the end of the input, which
-            // is not reported again
-            result = parse_recovering(std::string("[1, 2 /* unterminated"), true, true);
-            CHECK(result.balanced);
-            CHECK(result.value == json::parse("[1,2]"));
-            CHECK(result.errors.size() == 1);
-
-            // a '/' that does not begin a comment is garbage
-            result = parse_recovering(std::string("[1, /x, 2]"), true, true);
-            CHECK(result.balanced);
-            CHECK(result.value == json::parse("[1,null,2]"));
-            CHECK(result.errors.size() == 1);
-        }
-    }
-
-    SECTION("null bytes")
-    {
-        // a null byte ends the input, unless JSON_STRICT_NUL_HANDLING is set
-        const auto result = parse_recovering(std::string("[1,\0x", 5));
-        CHECK(result.balanced);
-        CHECK(!result.ok);
-#ifdef JSON_TEST_STRICT_NUL_HANDLING_ENABLED
-        CHECK(result.value == json::parse("[1,null]"));
-#else
-        CHECK(result.value == json::parse("[1]"));
-        CHECK(result.errors.size() == 1);
-#endif
-
-        const auto in_string = parse_recovering(std::string("[\"a\0b\"]", 7));
-        CHECK(in_string.balanced);
-#ifdef JSON_TEST_STRICT_NUL_HANDLING_ENABLED
-        CHECK(in_string.value == json::array({std::string("a\0b", 3)}));
-#else
-        CHECK(in_string.value == json::parse(R"(["a"])"));
-#endif
-    }
-
-    SECTION("the SAX parser stops recovering")
-    {
-        json j;
-        RecoveringDomParser sax(j, 2);
-        CHECK(!json::sax_parse("[1 2 3 4 5]", &sax));
-        CHECK(sax.errors.size() == 2);
-
-        // an error at a delimiter that an invalid token consumed is reported
-        // to the SAX parser, too
-        json j2;
-        RecoveringDomParser sax2(j2, 2);
-        CHECK(!json::sax_parse("[tru}, 1]", &sax2));
-        CHECK(sax2.errors.size() == 2);
-    }
-
-    SECTION("an event stops parsing during a repair")
-    {
-        // start_object() and key() are passed, then null() for the missing
-        // value returns false
-        RecoveringCountdown countdown(2);
-        CHECK(!json::sax_parse(R"({"a":})", &countdown));
-
-        // the end of the input: end_array() for the second array returns false
-        RecoveringCountdown countdown2(4);
-        CHECK(!json::sax_parse("[[1", &countdown2));
-    }
-
-    SECTION("input adapters")
-    {
-        // the lexer reads contiguous and streaming input differently, and it
-        // puts back a character that ended an invalid token
-        for (const std::string s :
-                {
-                    "[1 2]", "[tru}, 1]", R"({"a" "b\q", "c":[1.x, 2}})", "[\"\xFF\xC3(\", -, 1e+]", "{a:1,\"b\":2", ")]}' [1]"
-                })
-        {
-            CAPTURE(s)
-            const auto reference = parse_recovering(s);
-            CHECK(reference.balanced);
-
-            const auto from_c_string = parse_recovering(s.c_str());
-            CHECK(from_c_string.value == reference.value);
-            CHECK(from_c_string.errors == reference.errors);
-
-            const std::list<char> l(s.begin(), s.end());
-            json j;
-            RecoveringDomParser sax(j);
-            CHECK(!json::sax_parse(l.begin(), l.end(), &sax));
-            CHECK(j == reference.value);
-            CHECK(sax.errors == reference.errors);
-
-            std::istringstream ss(s);
-            const auto from_stream = parse_recovering(ss);
-            CHECK(from_stream.value == reference.value);
-            CHECK(from_stream.errors == reference.errors);
-        }
-    }
-
-    SECTION("long runs of errors")
-    {
-        // no error may copy all the input read before it
-        const auto closing = parse_recovering("[" + std::string(100000, '}'));
-        CHECK(closing.balanced);
-        CHECK(closing.value == json::array());
-
-        const auto garbage = parse_recovering("[" + std::string(100000, 'x') + "]");
-        CHECK(garbage.balanced);
-        CHECK(garbage.errors.size() == 1);
-
-        const auto commas = parse_recovering("{" + std::string(100000, ',') + "}");
-        CHECK(commas.balanced);
-        CHECK(commas.value == json::object());
-    }
-
-    SECTION("mutations of valid input")
-    {
-        // whatever the input, the events are balanced, every error is reported
-        // at most once, and valid input is parsed as usual
-        const std::vector<std::string> documents =
-        {
-            R"({"name": "value", "list": [1, -2.5, true, null, {"x": [[]]}], "e": "\u00e9"})",
-            R"([{"a": [1, 2, {"b": "c"}]}, [], {}, "\ud83d\ude00", 1e10])",
-            "{\"\xC3\xA9\": \"\xF0\x9F\x98\x80\"}",
-            R"(  {"k" : [ "v" , 0 ] }  )",
-        };
-        // each character that can be inserted, including a null byte
-        const std::string insertions("[]{},:\"x\\\0\xFF", 11);
-
-        std::vector<std::string> inputs;
-        for (const auto& doc : documents)
-        {
-            for (std::size_t i = 0; i <= doc.size(); ++i)
-            {
-                inputs.push_back(doc.substr(0, i));
-                if (i < doc.size())
-                {
-                    inputs.push_back(doc.substr(0, i) + doc.substr(i + 1));
-                }
-                for (const char c : insertions)
-                {
-                    inputs.push_back(doc.substr(0, i) + c + doc.substr(i));
-                }
-            }
-        }
-
-        for (const auto& s : inputs)
-        {
-            CAPTURE(s)
-            const auto result = parse_recovering(s);
-            CHECK(result.balanced);
-            CHECK(result.errors.size() <= s.size() + 1);
-            CHECK(result.events <= (4 * s.size()) + 4);
-            if (json::accept(s))
-            {
-                CHECK(result.ok);
-                CHECK(result.errors.empty());
-                CHECK(result.value == json::parse(s));
-            }
-            else
-            {
-                CHECK(!result.ok);
-                CHECK(!result.errors.empty());
-            }
-        }
-    }
-}

tests/src/unit-comparison.cpp

@@ -824,7 +824,7 @@ struct unordered_object_t : std::map<Key, Value, directed_less<Key>, Allocator>
         return !(lhs == rhs);
     }
 };
-using unordered_json = nlohmann::basic_json<unordered_object_t>;
+using unordered_json = nlohmann::json::with_object_t<unordered_object_t>;
 
 // the entries "0" to "9", enumerated in ascending or in descending order
 unordered_json make_unordered_object(const bool descending)
@@ -875,7 +875,7 @@ struct key_case_less
 
 template<class Key, class Value, class /*Compare*/, class Allocator>
 using key_case_map = std::map<Key, Value, key_case_less, Allocator>;
-using key_case_json = nlohmann::basic_json<key_case_map>;
+using key_case_json = nlohmann::json::with_object_t<key_case_map>;
 
 // the innermost value of a chain of single-element arrays
 template<typename Json>
@@ -905,7 +905,7 @@ struct case_insensitive_less
 
 template<class Key, class Value, class /*Compare*/, class Allocator>
 using case_insensitive_map = std::map<Key, Value, case_insensitive_less, Allocator>;
-using ci_json = nlohmann::basic_json<case_insensitive_map>;
+using ci_json = nlohmann::json::with_object_t<case_insensitive_map>;
 } // namespace
 
 TEST_CASE("equality of objects whose entries have no fixed order")

tests/src/unit-custom-array-type.cpp

@@ -22,7 +22,7 @@ namespace
 
 // std::deque has no capacity() member function, which the library only needs
 // to detect a reallocation for JSON_DIAGNOSTICS
-using deque_json = nlohmann::basic_json<std::map, std::deque>;
+using deque_json = nlohmann::json::with_array_t<std::deque>;
 
 // a std::vector whose at() is hidden: the library performs its own bounds
 // check and must not fall back to the container's checked accessor
@@ -39,7 +39,7 @@ class vector_without_at : public std::vector<T, Allocator>
     void at() = delete;
 };
 
-using no_at_json = nlohmann::basic_json<std::map, vector_without_at>;
+using no_at_json = nlohmann::json::with_array_t<vector_without_at>;
 
 } // namespace
 

tests/src/unit-custom-object-type.cpp

@@ -179,7 +179,7 @@ class no_key_compare_map
     }
 };
 
-using no_key_compare_json = nlohmann::basic_json<no_key_compare_map>;
+using no_key_compare_json = nlohmann::json::with_object_t<no_key_compare_map>;
 
 // An ObjectType whose erase(iterator) returns void rather than the following
 // iterator, as for instance Abseil's hash maps do
@@ -196,7 +196,7 @@ struct void_erase_map : std::map<Key, T, Compare, Allocator>
     }
 };
 
-using void_erase_json = nlohmann::basic_json<void_erase_map>;
+using void_erase_json = nlohmann::json::with_object_t<void_erase_map>;
 
 // wraps an iterator, but only offers the LegacyForwardIterator operations,
 // like the iterators of std::unordered_map and other hash maps
@@ -388,7 +388,7 @@ class forward_only_map
     }
 };
 
-using forward_only_json = nlohmann::basic_json<forward_only_map>;
+using forward_only_json = nlohmann::json::with_object_t<forward_only_map>;
 
 } // namespace
 

tests/src/unit-hash.cpp

@@ -157,13 +157,13 @@ TEST_CASE("hash<nlohmann::json>")
     // the ends of the integer ranges, which equal floats exactly
     const auto int_min = (std::numeric_limits<json::number_integer_t>::min)();
     const auto int_max = (std::numeric_limits<json::number_integer_t>::max)();
-    const auto two_63 = json::number_unsigned_t(1) << 63U;
+    const auto two_63 = static_cast<json::number_unsigned_t>(1) << 63U;
     CHECK(json(int_min) == json(-9223372036854775808.0));
     CHECK(std::hash<json> {}(json(int_min)) == std::hash<json> {}(json(-9223372036854775808.0)));
     CHECK(json(two_63) == json(9223372036854775808.0));
     CHECK(std::hash<json> {}(json(two_63)) == std::hash<json> {}(json(9223372036854775808.0)));
-    CHECK(json(json::number_unsigned_t(int_max)) == json(int_max));
-    CHECK(std::hash<json> {}(json(json::number_unsigned_t(int_max))) == std::hash<json> {}(json(int_max)));
+    CHECK(json(static_cast<json::number_unsigned_t>(int_max)) == json(int_max));
+    CHECK(std::hash<json> {}(json(static_cast<json::number_unsigned_t>(int_max))) == std::hash<json> {}(json(int_max)));
 }
 
 TEST_CASE("hash<nlohmann::ordered_json>")

tests/src/unit-large_json.cpp

@@ -426,7 +426,7 @@ TEST_CASE("issue #5392 - binary writers on deeply nested values")
     {
         for (std::size_t depth = 120; depth <= 140; ++depth)
         {
-            CAPTURE(depth);
+            CAPTURE(depth)
 
             const json array = nested_array(depth, json(7));
             CHECK(json::from_cbor(json::to_cbor(array)) == array);
@@ -464,7 +464,7 @@ TEST_CASE("issue #5392 - binary writers on deeply nested values")
                     nlohmann::detail::recursion_depth_limit() + 1, nlohmann::detail::recursion_depth_limit() + 2
                 })
         {
-            CAPTURE(depth);
+            CAPTURE(depth)
             const json array = nested_array(depth, json(0));
 
             std::vector<std::uint8_t> expected_cbor(depth, 0x81);
@@ -505,10 +505,22 @@ TEST_CASE("issue #5392 - binary writers on deeply nested values")
         const json discarded_leaf(json::value_t::discarded);
         const json deep_discarded = nested_array(depth, discarded_leaf);
 
-        CHECK_THROWS_WITH_AS(json::to_cbor(deep_discarded), "[json.exception.type_error.321] cannot serialize discarded value to CBOR", json::type_error);
-        CHECK_THROWS_WITH_AS(json::to_msgpack(deep_discarded), "[json.exception.type_error.321] cannot serialize discarded value to MessagePack", json::type_error);
-        CHECK_THROWS_WITH_AS(json::to_ubjson(deep_discarded), "[json.exception.type_error.321] cannot serialize discarded value to UBJSON", json::type_error);
-        CHECK_THROWS_WITH_AS(json::to_bjdata(deep_discarded), "[json.exception.type_error.321] cannot serialize discarded value to BJData", json::type_error);
+        // with diagnostics, the message names the path to the discarded leaf
+#if JSON_DIAGNOSTICS
+        std::string path;
+        for (std::size_t i = 0; i < depth; ++i)
+        {
+            path += "/0";
+        }
+        const std::string prefix = "[json.exception.type_error.321] (" + path + ") ";
+#else
+        const std::string prefix = "[json.exception.type_error.321] ";
+#endif
+
+        CHECK_THROWS_WITH_AS(json::to_cbor(deep_discarded), (prefix + "cannot serialize discarded value to CBOR").c_str(), json::type_error);
+        CHECK_THROWS_WITH_AS(json::to_msgpack(deep_discarded), (prefix + "cannot serialize discarded value to MessagePack").c_str(), json::type_error);
+        CHECK_THROWS_WITH_AS(json::to_ubjson(deep_discarded), (prefix + "cannot serialize discarded value to UBJSON").c_str(), json::type_error);
+        CHECK_THROWS_WITH_AS(json::to_bjdata(deep_discarded), (prefix + "cannot serialize discarded value to BJData").c_str(), json::type_error);
     }
 
     SECTION("does not overflow the C++ stack")

tests/src/unit-locale-cpp.cpp

@@ -172,7 +172,7 @@ TEST_CASE("locale-dependent test (LC_NUMERIC=de_DE)")
             // a floating-point type that is not a float or a double is written
             // with snprintf, whose locale-specific decimal point and thousands
             // separator are undone afterwards
-            using long_double_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t, long double>;
+            using long_double_json = nlohmann::json::with_float_t<long double>;
             CHECK(long_double_json(12345.5L).dump() == "12345.5");
             CHECK(long_double_json(1.0L).dump() == "1.0");
             CHECK(long_double_json(-0.25L).dump() == "-0.25");
@@ -272,7 +272,7 @@ TEST_CASE("locale changes between lexer construction and number conversion (#519
     }
     text += "]";
 
-    using long_double_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t, long double>;
+    using long_double_json = nlohmann::json::with_float_t<long double>;
 
     // reference values, parsed without a locale switch
     REQUIRE(std::setlocale(LC_NUMERIC, "C") != nullptr);
@@ -432,7 +432,7 @@ TEST_CASE("locale changes during a single dump() (#5709 item 3)")
     // long double on 64-bit Arm, where it is IEEE-754 double) takes the
     // locale-independent to_chars() path instead, and this test is a no-op
     // there.
-    using long_double_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t, long double>;
+    using long_double_json = nlohmann::json::with_float_t<long double>;
     using ld_limits = std::numeric_limits<long_double_json::number_float_t>;
     const bool is_ieee_single_or_double =
         (ld_limits::is_iec559 && ld_limits::digits == 24 && ld_limits::max_exponent == 128) ||

tests/src/unit-msgpack.cpp

@@ -2432,8 +2432,8 @@ TEST_CASE("MessagePack numbers use the active union member (see #5644)")
     // used to read the union member that was not the active one, writing
     // wrong bytes for some values; std::int64_t/std::uint64_t (the default
     // types, where both members have the same width) were not affected
-    using int32_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int32_t, std::uint64_t, double>;
-    using int16_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int16_t, std::uint64_t, double>;
+    using int32_json = nlohmann::json::with_integers_t<std::int32_t, std::uint64_t>;
+    using int16_json = nlohmann::json::with_integers_t<std::int16_t, std::uint64_t>;
 
     SECTION("number_integer_t = std::int32_t")
     {

tests/src/unit-regression1.cpp

@@ -39,7 +39,7 @@ using nlohmann::json;
 
 template<class K, class V, class dummy_compare, class A>
 using my_workaround_fifo_map = nlohmann::fifo_map<K, V, nlohmann::fifo_map_compare<K>, A>;
-using my_json = nlohmann::basic_json<my_workaround_fifo_map>;
+using my_json = nlohmann::json::with_object_t<my_workaround_fifo_map>;
 
 /////////////////////////////////////////////////////////////////////
 // for #977
@@ -86,8 +86,7 @@ struct foo_serializer < T, typename std::enable_if < !std::is_same<foo, T>::valu
 };
 } // namespace ns
 
-using foo_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t,
-      std::uint64_t, double, std::allocator, ns::foo_serializer, std::vector<std::uint8_t>>;
+using foo_json = nlohmann::json::with_json_serializer_t<ns::foo_serializer>;
 
 /////////////////////////////////////////////////////////////////////
 // for #805
@@ -254,7 +253,7 @@ TEST_CASE("regression tests 1")
     {
         // create JSON class with nonstandard integer number type
         using custom_json =
-            nlohmann::basic_json<std::map, std::vector, std::string, bool, int32_t, uint32_t, float>;
+            nlohmann::json::with_integers_t<std::int32_t, std::uint32_t>::with_float_t<float>;
         custom_json j;
         j["int_1"] = 1;
         CHECK(j["int_1"] == 1);
@@ -470,18 +469,17 @@ TEST_CASE("regression tests 1")
         // create JSON class with nonstandard float number type
 
         // float
-        nlohmann::basic_json<std::map, std::vector, std::string, bool, int32_t, uint32_t, float> const j_float =
+        nlohmann::json::with_integers_t<std::int32_t, std::uint32_t>::with_float_t<float> const j_float =
             1.23e25f;
         CHECK(j_float.get<float>() == 1.23e25f);
 
         // double
-        nlohmann::basic_json<std::map, std::vector, std::string, bool, int64_t, uint64_t, double> const j_double =
+        nlohmann::json const j_double =
             1.23e35;
         CHECK(j_double.get<double>() == 1.23e35);
 
         // long double
-        nlohmann::basic_json<std::map, std::vector, std::string, bool, int64_t, uint64_t, long double>
-        const j_long_double = 1.23e45L;
+        nlohmann::json::with_float_t<long double> const j_long_double = 1.23e45L;
         CHECK(j_long_double.get<long double>() == 1.23e45L);
     }
 

tests/src/unit-regression2.cpp

@@ -64,18 +64,7 @@ using ordered_json = nlohmann::ordered_json;
     /////////////////////////////////////////////////////////////////////
     // for #4804
     /////////////////////////////////////////////////////////////////////
-    using json_4804 = nlohmann::basic_json<std::map,        // ObjectType
-    std::vector,     // ArrayType
-    std::string,     // StringType
-    bool,            // BooleanType
-    std::int64_t,    // NumberIntegerType
-    std::uint64_t,   // NumberUnsignedType
-    double,          // NumberFloatType
-    std::allocator,  // AllocatorType
-    nlohmann::adl_serializer,  // JSONSerializer
-    std::vector<std::byte>,    // BinaryType
-    void                       // CustomBaseClass
-    >;
+    using json_4804 = nlohmann::json::with_binary_t<std::vector<std::byte>>;
 #endif
 
 #ifdef JSON_HAS_CPP_20
@@ -107,7 +96,7 @@ DOCTEST_CLANG_SUPPRESS_WARNING("-Wexit-time-destructors")
 // for #1021
 /////////////////////////////////////////////////////////////////////
 
-using float_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t, float>;
+using float_json = nlohmann::json::with_float_t<float>;
 
 #if (defined(__cpp_exceptions) || defined(__EXCEPTIONS) || defined(_CPPUNWIND)) && !defined(JSON_NOEXCEPTION)
 namespace
@@ -155,10 +144,8 @@ struct failing_allocator : std::allocator<T>
     };
 };
 
-using failing_json = nlohmann::basic_json<std::map, std::vector, std::string, bool,
-      std::int64_t, std::uint64_t, double, failing_allocator>;
-using failing_ordered_json = nlohmann::basic_json<nlohmann::ordered_map, std::vector, std::string, bool,
-      std::int64_t, std::uint64_t, double, failing_allocator>;
+using failing_json = nlohmann::json::with_allocator_t<failing_allocator>;
+using failing_ordered_json = nlohmann::ordered_json::with_allocator_t<failing_allocator>;
 
 // builds `depth` levels of nesting around a scalar, iteratively (never
 // recursing: each wrap only moves the previous, already-built value, which

tests/src/unit-regression3.cpp

@@ -22,6 +22,14 @@
 // scoped enum, so get<std::byte>() (needed below to get<std::vector<std::byte>>()
 // from a plain JSON array, not just from an already-binary value) relies on
 // enum serialization being enabled
+// capture whether JSON_DELETE_DEPRECATED_FUNCTIONS was enabled on the command
+// line *before* including json.hpp, since the library #undefs it once the header
+// has been fully processed (see include/nlohmann/detail/macro_unscope.hpp); the
+// tests of deprecated functions are skipped if these functions are deleted
+#if defined(JSON_DELETE_DEPRECATED_FUNCTIONS) && (JSON_DELETE_DEPRECATED_FUNCTIONS == 1)
+    #define JSON_TEST_DEPRECATED_FUNCTIONS_DELETED
+#endif
+
 #if defined(JSON_DISABLE_ENUM_SERIALIZATION) && (JSON_DISABLE_ENUM_SERIALIZATION == 1)
     #define SKIP_TESTS_FOR_ENUM_SERIALIZATION
 #endif
@@ -54,18 +62,7 @@ using ordered_json = nlohmann::ordered_json;
     /////////////////////////////////////////////////////////////////////
     // for #4804
     /////////////////////////////////////////////////////////////////////
-    using json_4804 = nlohmann::basic_json<std::map,        // ObjectType
-    std::vector,     // ArrayType
-    std::string,     // StringType
-    bool,            // BooleanType
-    std::int64_t,    // NumberIntegerType
-    std::uint64_t,   // NumberUnsignedType
-    double,          // NumberFloatType
-    std::allocator,  // AllocatorType
-    nlohmann::adl_serializer,  // JSONSerializer
-    std::vector<std::byte>,    // BinaryType
-    void                       // CustomBaseClass
-    >;
+    using json_4804 = nlohmann::json::with_binary_t<std::vector<std::byte>>;
 #endif
 
 #ifdef JSON_HAS_CPP_20
@@ -862,6 +859,50 @@ TEST_CASE("issue #5338 - truncated CBOR tagged binary subtype is rejected")
     }
 }
 
+TEST_CASE("issue #5676 - SAX parsing of CBOR tags")
+{
+    const json expected = json::binary({1, 2, 3}, 42);
+    const auto cbor = json::to_cbor(expected);
+
+    nlohmann::detail::json_sax_acceptor<json> acceptor;
+    CHECK_FALSE(json::sax_parse(cbor, &acceptor, json::input_format_t::cbor));
+    CHECK_FALSE(json::sax_parse(cbor, &acceptor, json::input_format_t::cbor,
+                                true, false, false, json::cbor_tag_handler_t::error));
+
+    CHECK(json::sax_parse(cbor, &acceptor, json::input_format_t::cbor,
+                          true, false, false, json::cbor_tag_handler_t::ignore));
+
+    json parsed;
+    nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type> sax(parsed);
+    CHECK(json::sax_parse(cbor, &sax, json::input_format_t::cbor,
+                          true, false, false, json::cbor_tag_handler_t::store));
+    CHECK(parsed == expected);
+
+    json iterator_parsed;
+    nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type> iterator_sax(iterator_parsed);
+    CHECK(json::sax_parse(cbor.begin(), cbor.end(), &iterator_sax, json::input_format_t::cbor,
+                          true, false, false, json::cbor_tag_handler_t::store));
+    CHECK(iterator_parsed == expected);
+
+#ifndef JSON_TEST_DEPRECATED_FUNCTIONS_DELETED
+    json span_parsed;
+    nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type> span_sax(span_parsed);
+    CHECK(json::sax_parse(nlohmann::detail::span_input_adapter(cbor.data(), cbor.size()), &span_sax,
+                          json::input_format_t::cbor, true, false, false, json::cbor_tag_handler_t::store));
+    CHECK(span_parsed == expected);
+#endif
+
+    const std::string text = "null";
+    CHECK(json::sax_parse(text, &acceptor, json::input_format_t::json,
+                          true, false, false, json::cbor_tag_handler_t::store));
+    CHECK(json::sax_parse(text.begin(), text.end(), &acceptor, json::input_format_t::json,
+                          true, false, false, json::cbor_tag_handler_t::store));
+#ifndef JSON_TEST_DEPRECATED_FUNCTIONS_DELETED
+    CHECK(json::sax_parse(nlohmann::detail::span_input_adapter(text.data(), text.size()), &acceptor,
+                          json::input_format_t::json, true, false, false, json::cbor_tag_handler_t::store));
+#endif
+}
+
 TEST_CASE("issue #5402 - update(merge_objects=true) overwrites a primitive with an object")
 {
     json t = {{"k", 1}};
@@ -878,7 +919,7 @@ TEST_CASE("regression test #5476 - array type without reserve()")
 {
     // the capacity reserved for definite-length arrays must not require the
     // array type to have a reserve() member function
-    using deque_json = nlohmann::basic_json<std::map, std::deque>;
+    using deque_json = nlohmann::json::with_array_t<std::deque>;
 
     SECTION("std::deque")
     {

tests/src/unit-sax_parse.cpp

@@ -1,689 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  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
-
-/////////////////////////////////////////////////////////////////////
-// Tests that call basic_json::sax_parse have a file of their own: every
-// sax_parse call instantiates the parser and binary reader that recover from
-// errors (see #3989), and in unit-regression2.cpp and unit-regression3.cpp
-// this made the objects too large for the MinGW linker to relocate (see
-// #5511).
-/////////////////////////////////////////////////////////////////////
-
-#include "doctest_compatibility.h"
-
-// capture whether JSON_DELETE_DEPRECATED_FUNCTIONS was enabled on the command
-// line *before* including json.hpp, since the library #undefs it once the header
-// has been fully processed (see include/nlohmann/detail/macro_unscope.hpp); the
-// tests of deprecated functions are skipped if these functions are deleted
-#if defined(JSON_DELETE_DEPRECATED_FUNCTIONS) && (JSON_DELETE_DEPRECATED_FUNCTIONS == 1)
-    #define JSON_TEST_DEPRECATED_FUNCTIONS_DELETED
-#endif
-
-#include <nlohmann/json.hpp>
-using json = nlohmann::json;
-
-#include <cmath>
-#include <cstddef>
-#include <cstdint>
-#include <map>
-#include <string>
-#include <utility>
-#include <vector>
-
-// a narrow number_float_t, so that a double read from binary input can
-// overflow it
-using float_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t, float>;
-
-DOCTEST_CLANG_SUPPRESS_WARNING_PUSH
-DOCTEST_CLANG_SUPPRESS_WARNING("-Wexit-time-destructors")
-
-namespace
-{
-/// builds a value from SAX events, asks the parser to recover from its first
-/// 100 errors, and checks that the events are balanced (see #3989)
-template<typename BasicJsonType>
-class BasicRecoveringParser
-{
-  public:
-    explicit BasicRecoveringParser(BasicJsonType& j)
-        : dom(j, false)
-    {}
-
-    bool null()
-    {
-        value();
-        return dom.null();
-    }
-
-    bool boolean(bool val)
-    {
-        value();
-        return dom.boolean(val);
-    }
-
-    bool number_integer(typename BasicJsonType::number_integer_t val)
-    {
-        value();
-        return dom.number_integer(val);
-    }
-
-    bool number_unsigned(typename BasicJsonType::number_unsigned_t val)
-    {
-        value();
-        return dom.number_unsigned(val);
-    }
-
-    bool number_float(typename BasicJsonType::number_float_t val, const std::string& s)
-    {
-        value();
-        return dom.number_float(val, s);
-    }
-
-    bool string(std::string& val)
-    {
-        value();
-        return dom.string(val);
-    }
-
-    bool binary(typename BasicJsonType::binary_t& val)
-    {
-        value();
-        return dom.binary(val);
-    }
-
-    bool start_object(std::size_t elements)
-    {
-        value();
-        stack.push_back('o');
-        return dom.start_object(elements);
-    }
-
-    bool key(std::string& val)
-    {
-        if (stack.empty() || stack.back() != 'o')
-        {
-            well_formed = false;
-            return false;
-        }
-        stack.back() = 'v';
-        return dom.key(val);
-    }
-
-    bool end_object()
-    {
-        if (stack.empty() || stack.back() != 'o')
-        {
-            well_formed = false;
-            return false;
-        }
-        stack.pop_back();
-        return dom.end_object();
-    }
-
-    bool start_array(std::size_t elements)
-    {
-        value();
-        stack.push_back('a');
-        return dom.start_array(elements);
-    }
-
-    bool end_array()
-    {
-        if (stack.empty() || stack.back() != 'a')
-        {
-            well_formed = false;
-            return false;
-        }
-        stack.pop_back();
-        return dom.end_array();
-    }
-
-    bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/, const json::exception& ex)
-    {
-        messages.emplace_back(ex.what());
-        // a limit, so that a reader that does not stop fails the test
-        // instead of making it hang
-        return ++errors < 100;
-    }
-
-    /// whether the events were balanced and every key was followed by a value
-    bool balanced() const
-    {
-        return well_formed && stack.empty();
-    }
-
-    /// builds the value
-    nlohmann::detail::json_sax_dom_parser<BasicJsonType> dom;
-    std::size_t errors = 0;
-    std::vector<std::string> messages {}; // NOLINT(readability-redundant-member-init)
-    std::vector<char> stack {}; // NOLINT(readability-redundant-member-init)
-    bool well_formed = true;
-
-  private:
-    void value()
-    {
-        if (!stack.empty())
-        {
-            if (stack.back() == 'v')
-            {
-                stack.back() = 'o';
-            }
-            else if (stack.back() == 'o')
-            {
-                well_formed = false;
-            }
-        }
-    }
-
-};
-
-using RecoveringParser = BasicRecoveringParser<json>;
-
-struct BinaryParseResult
-{
-    json value;
-    std::size_t errors;
-    std::vector<std::string> messages;
-    bool ok;
-    bool balanced;
-};
-
-BinaryParseResult parse_binary_recovering(const std::vector<std::uint8_t>& input, const json::input_format_t format)
-{
-    json j;
-    RecoveringParser sax(j);
-    const bool ok = json::sax_parse(input, &sax, format);
-    return {j, sax.errors, sax.messages, ok, sax.balanced()};
-}
-
-#if !defined(JSON_NOEXCEPTION)
-/// the message of the exception that reading @a input into a JSON value
-/// throws, or an empty string if reading succeeds
-std::string binary_error_message(const std::vector<std::uint8_t>& input, const json::input_format_t format)
-{
-    try
-    {
-        json _;
-        switch (format)
-        {
-            case json::input_format_t::cbor:
-                _ = json::from_cbor(input);
-                break;
-            case json::input_format_t::msgpack:
-                _ = json::from_msgpack(input);
-                break;
-            case json::input_format_t::ubjson:
-                _ = json::from_ubjson(input);
-                break;
-            case json::input_format_t::bjdata:
-                _ = json::from_bjdata(input);
-                break;
-            case json::input_format_t::bson:
-                _ = json::from_bson(input);
-                break;
-            case json::input_format_t::bon8:
-                _ = json::from_bon8(input);
-                break;
-            case json::input_format_t::json:
-            default:
-                break;
-        }
-    }
-    catch (const json::exception& e)
-    {
-        return e.what();
-    }
-    return "";
-}
-#endif
-
-/// a BSON element: its type, its name, and its value
-std::vector<std::uint8_t> bson_element(const std::uint8_t type, const std::string& name, const std::vector<std::uint8_t>& value)
-{
-    std::vector<std::uint8_t> result = {type};
-    result.insert(result.end(), name.begin(), name.end());
-    result.push_back(0x00);
-    result.insert(result.end(), value.begin(), value.end());
-    return result;
-}
-
-/// a BSON document of the given elements; @a size_offset is added to the
-/// size it declares
-std::vector<std::uint8_t> bson_document(const std::vector<std::vector<std::uint8_t>>& elements, const int size_offset = 0)
-{
-    std::vector<std::uint8_t> body;
-    for (const auto& element : elements)
-    {
-        body.insert(body.end(), element.begin(), element.end());
-    }
-    const auto size = static_cast<std::uint32_t>(static_cast<int>(body.size()) + 5 + size_offset);
-    std::vector<std::uint8_t> result = {static_cast<std::uint8_t>(size & 0xFFu), static_cast<std::uint8_t>((size >> 8u) & 0xFFu),
-                                        static_cast<std::uint8_t>((size >> 16u) & 0xFFu), static_cast<std::uint8_t>((size >> 24u) & 0xFFu)
-                                       };
-    result.insert(result.end(), body.begin(), body.end());
-    result.push_back(0x00);
-    return result;
-}
-
-/// a BSON int32 value
-std::vector<std::uint8_t> bson_int32(const std::int32_t value)
-{
-    const auto u = static_cast<std::uint32_t>(value);
-    return {static_cast<std::uint8_t>(u & 0xFFu), static_cast<std::uint8_t>((u >> 8u) & 0xFFu),
-            static_cast<std::uint8_t>((u >> 16u) & 0xFFu), static_cast<std::uint8_t>((u >> 24u) & 0xFFu)};
-}
-
-/// a BSON string value, whose length is @a length_offset off
-std::vector<std::uint8_t> bson_string(const std::string& value, const std::int32_t length_offset = 0)
-{
-    auto result = bson_int32(static_cast<std::int32_t>(value.size() + 1) + length_offset);
-    result.insert(result.end(), value.begin(), value.end());
-    result.push_back(0x00);
-    return result;
-}
-
-/// @a count bytes of value 0xAB
-std::vector<std::uint8_t> bytes(const std::size_t count)
-{
-    return std::vector<std::uint8_t>(count, 0xAB);
-}
-
-template<typename... Parts>
-std::vector<std::uint8_t> concatenated(const std::vector<std::uint8_t>& first, const Parts& ... rest)
-{
-    std::vector<std::uint8_t> result = first;
-    for (const auto& part : std::initializer_list<std::vector<std::uint8_t>> {rest...})
-    {
-        result.insert(result.end(), part.begin(), part.end());
-    }
-    return result;
-}
-
-/// U+FFFD REPLACEMENT CHARACTER
-std::string replacement_character()
-{
-    return "\xEF\xBF\xBD";
-}
-}  // namespace
-
-TEST_CASE("regression test - #3989 SAX parse_error() returning true")
-{
-    SECTION("binary formats complete what was read before the input ends")
-    {
-        const json j = {{"a", {1, -2, {{"b", "c"}}, json::array()}}, {"d", {{"e", nullptr}, {"f", true}}}, {"g", 1.5}, {"h", json::binary({1, 2, 3})}};
-
-        const std::vector<std::pair<json::input_format_t, std::vector<std::uint8_t>>> encodings =
-        {
-            {json::input_format_t::cbor, json::to_cbor(j)},
-            {json::input_format_t::msgpack, json::to_msgpack(j)},
-            {json::input_format_t::ubjson, json::to_ubjson(j)},
-            {json::input_format_t::ubjson, json::to_ubjson(j, true, true)},
-            {json::input_format_t::bjdata, json::to_bjdata(j)},
-            {json::input_format_t::bjdata, json::to_bjdata(j, true, true)},
-            {json::input_format_t::bson, json::to_bson(j)},
-            {json::input_format_t::bon8, json::to_bon8(j)},
-        };
-
-        for (const auto& encoding : encodings)
-        {
-            const auto format = encoding.first;
-            const auto& bytes = encoding.second;
-            CAPTURE(format)
-
-            // every prefix is truncated input
-            for (std::size_t length = 0; length < bytes.size(); ++length)
-            {
-                CAPTURE(length)
-                const auto result = parse_binary_recovering(std::vector<std::uint8_t>(bytes.begin(), bytes.begin() + static_cast<std::ptrdiff_t>(length)), format);
-                CHECK(!result.ok);
-                CHECK(result.errors == 1);
-                CHECK(result.balanced);
-            }
-
-            // the complete input is read as usual (binary values do not
-            // round-trip through every format, so compare with a plain parse)
-            json expected;
-            nlohmann::detail::json_sax_dom_parser<json> dom(expected);
-            CHECK(json::sax_parse(bytes, &dom, format));
-            const auto complete = parse_binary_recovering(bytes, format);
-            CHECK(complete.ok);
-            CHECK(complete.errors == 0);
-            CHECK(complete.value == expected);
-
-            // a byte after the value
-            auto trailing_bytes = bytes;
-            trailing_bytes.push_back(0x01);
-            const auto trailing = parse_binary_recovering(trailing_bytes, format);
-            CHECK(!trailing.ok);
-            CHECK(trailing.errors == 1);
-            CHECK(trailing.value == expected);
-        }
-    }
-
-    SECTION("containers without an end")
-    {
-        // these made the readers loop, or read on, after the error
-        const auto cbor_array = parse_binary_recovering({0x9F}, json::input_format_t::cbor);
-        CHECK(cbor_array.errors == 1);
-        CHECK(cbor_array.value == json::array());
-
-        const auto cbor_map = parse_binary_recovering({0xBF, 0x61, 'a'}, json::input_format_t::cbor);
-        CHECK(cbor_map.errors == 1);
-        CHECK(cbor_map.value == json({{"a", nullptr}}));
-
-        const auto msgpack_array = parse_binary_recovering({0xDD, 0xFF, 0xFF, 0xFF, 0xFF}, json::input_format_t::msgpack);
-        CHECK(msgpack_array.errors == 1);
-        CHECK(msgpack_array.value == json::array());
-
-        const auto msgpack_map = parse_binary_recovering({0x81, 0xA1, 'a', 0x92, 0x01}, json::input_format_t::msgpack);
-        CHECK(msgpack_map.errors == 1);
-        CHECK(msgpack_map.value == json({{"a", {1}}}));
-    }
-
-    SECTION("BJData ndarray")
-    {
-        // a 2x3 int8 array with two of its six elements; the annotated array
-        // format opens an object and two arrays of its own
-        const auto result = parse_binary_recovering({'[', '$', 'i', '#', '[', '$', 'i', '#', 'i', 2, 2, 3, 1, 2}, json::input_format_t::bjdata);
-        CHECK(result.errors == 1);
-        CHECK(result.balanced);
-        CHECK(result.value == json({{"_ArrayType_", "int8"}, {"_ArraySize_", {2, 3}}, {"_ArrayData_", {1, 2}}}));
-    }
-
-    SECTION("binary formats repair items whose end is known")
-    {
-        struct Repair
-        {
-            json::input_format_t format;
-            std::vector<std::uint8_t> input;
-            json expected;
-            std::size_t errors;
-        };
-
-        const std::vector<Repair> repairs =
-        {
-            // CBOR: tags are ignored (here tag 1 and the self-describe tag 55799)
-            {json::input_format_t::cbor, {0x82, 0xC1, 0x05, 0xD9, 0xD9, 0xF7, 0x06}, {5, 6}, 2},
-            // CBOR: undefined and other simple values become null
-            {json::input_format_t::cbor, {0x84, 0xF7, 0xE0, 0xF8, 0x20, 0x01}, {nullptr, nullptr, nullptr, 1}, 3},
-            // CBOR: members whose key is not a string are skipped, whatever their key and value
-            {json::input_format_t::cbor, {0xA4, 0x01, 0x02, 0x82, 0x01, 0x02, 0xA1, 0x61, 'x', 0x9F, 0xFF, 0xC1, 0x01, 0x5F, 0x41, 0x00, 0xFF, 0x61, 'a', 0x03}, {{"a", 3}}, 3},
-            {json::input_format_t::cbor, {0xBF, 0xF5, 0xBF, 0x61, 'x', 0x7F, 0x61, 'y', 0xFF, 0xFF, 0x61, 'a', 0x03, 0xFF}, {{"a", 3}}, 1},
-            // MessagePack: members whose key is not a string are skipped
-            {json::input_format_t::msgpack, {0x84, 0x01, 0x02, 0x81, 0xA1, 'x', 0x01, 0x92, 0x01, 0x02, 0xD4, 0x01, 0x02, 0xC0, 0xA1, 'a', 0x04}, {{"a", 4}}, 3},
-            // UBJSON: a char that is not ASCII becomes U+FFFD
-            {json::input_format_t::ubjson, {'[', 'C', 0x80, 'C', 'A', ']'}, {replacement_character(), "A"}, 1},
-            // UBJSON: the longest beginning of a high-precision number is kept
-            {json::input_format_t::ubjson, {'[', 'H', 'i', 5, '1', '2', 'a', 'b', 'c', 'H', 'i', 2, '1', '.', 'H', 'i', 3, 'a', 'b', 'c', 'H', 'i', 3, '4', '.', '5', ']'}, {12, 1, nullptr, 4.5}, 3},
-            // BJData, too
-            {json::input_format_t::bjdata, {'[', 'C', 0xFF, 'H', 'i', 2, '-', '1', 'H', 'i', 2, '-', 'x', ']'}, {replacement_character(), -1, nullptr}, 2},
-            // a NUL ends a high-precision number, as it ends JSON text
-            {json::input_format_t::ubjson, {'[', 'H', 'i', 4, '1', '2', 0, '9', 'H', 'i', 2, 0, '1', 'i', 3, ']'}, {12, nullptr, 3}, 2},
-            // BON8: members whose key is not a string are skipped
-            {json::input_format_t::bon8, {0x89, 0x91, 0x92, 0xC9, 0x40, 0x82, 0x91, 0x92, 0x61, 0x93}, {{"a", 3}}, 2},
-            {json::input_format_t::bon8, {0x8B, 0x91, 0x85, 0x91, 0xFE, 0xFA, 0x8B, 'x', 0x91, 0xFE, 0x61, 0x93, 0xFE}, {{"a", 3}}, 2},
-            // BSON: elements of types the library does not read become null
-            {
-                json::input_format_t::bson, bson_document(
-                {
-                    bson_element(0x07, "_id", bytes(12)),                         // ObjectId
-                    bson_element(0x09, "date", bytes(8)),                         // UTC datetime
-                    bson_element(0x13, "decimal", bytes(16)),                     // 128-bit decimal
-                    bson_element(0x0B, "regex", {'a', '+', 0, 'i', 0}),           // regular expression
-                    bson_element(0x0D, "code", bson_string("f()")),               // JavaScript code
-                    bson_element(0x0E, "symbol", bson_string("s")),               // symbol
-                    bson_element(0x0C, "pointer", concatenated(bson_string("c"), bytes(12))), // DBPointer
-                    bson_element(0x0F, "scope", concatenated(bson_int32(15), bson_string("g"), bson_document({}))), // code with scope
-                    bson_element(0x06, "undefined", {}),                          // undefined
-                    bson_element(0xFF, "min", {}),                                // min key
-                    bson_element(0x7F, "max", {}),                                // max key
-                    bson_element(0x10, "z", bson_int32(7)),
-                }),
-                {{"_id", nullptr}, {"date", nullptr}, {"decimal", nullptr}, {"regex", nullptr}, {"code", nullptr}, {"symbol", nullptr}, {"pointer", nullptr}, {"scope", nullptr}, {"undefined", nullptr}, {"min", nullptr}, {"max", nullptr}, {"z", 7}},
-                11
-            },
-            // BSON: an element of an unknown type becomes null, and the rest of its document is skipped
-            {
-                json::input_format_t::bson, bson_document(
-                {
-                    bson_element(0x03, "inner", bson_document({bson_element(0x10, "a", bson_int32(1)), bson_element(0x42, "x", bytes(3)), bson_element(0x10, "b", bson_int32(2))})),
-                    bson_element(0x04, "array", bson_document({bson_element(0x10, "0", bson_int32(1)), bson_element(0x42, "1", bytes(3))})),
-                    bson_element(0x10, "after", bson_int32(3)),
-                }),
-                {{"inner", {{"a", 1}, {"x", nullptr}}}, {"array", {1, nullptr}}, {"after", 3}},
-                2
-            },
-            // BSON: so does a string or byte array whose length cannot be right
-            {
-                json::input_format_t::bson, bson_document(
-                {
-                    bson_element(0x03, "inner", bson_document({bson_element(0x02, "s", bson_string("abc", -10)), bson_element(0x10, "b", bson_int32(2))})),
-                    bson_element(0x03, "bin", bson_document({bson_element(0x05, "b", concatenated(bson_int32(-1), bytes(1))), bson_element(0x10, "b", bson_int32(2))})),
-                    bson_element(0x10, "after", bson_int32(3)),
-                }),
-                {{"inner", {{"s", nullptr}}}, {"bin", {{"b", nullptr}}}, {"after", 3}},
-                2
-            },
-            // BSON: a string without its terminator, and a document whose size does not match, are kept
-            {
-                json::input_format_t::bson, bson_document(
-                {
-                    bson_element(0x02, "s", {2, 0, 0, 0, 'a', 'X'}),
-                    bson_element(0x03, "inner", bson_document({bson_element(0x10, "a", bson_int32(1))}, 1)),
-                }),
-                {{"s", "a"}, {"inner", {{"a", 1}}}},
-                2
-            },
-        };
-
-        for (const auto& repair : repairs)
-        {
-            CAPTURE(repair.format)
-            CAPTURE(repair.input)
-            const auto result = parse_binary_recovering(repair.input, repair.format);
-            CHECK(!result.ok);
-            CHECK(result.balanced);
-            CHECK(result.errors == repair.errors);
-            CHECK(result.value == repair.expected);
-            REQUIRE(!result.messages.empty());
-#if !defined(JSON_NOEXCEPTION)
-            // the first error is the one reported without recovering; under
-            // JSON_NOEXCEPTION, reading without recovering aborts instead of
-            // throwing, so there is no message to compare with
-            CHECK(result.messages.front() == binary_error_message(repair.input, repair.format));
-#endif
-        }
-    }
-
-    SECTION("binary formats repair numbers that are out of range")
-    {
-        // CBOR: a double too large for a float number_float_t
-        float_json cbor;
-        BasicRecoveringParser<float_json> sax(cbor);
-        const std::vector<std::uint8_t> cbor_input = {0x82, 0xFB, 0x7E, 0x37, 0xE4, 0x3C, 0x88, 0x00, 0x75, 0x9C, 0x01}; // [1e300, 1]
-        CHECK(!float_json::sax_parse(cbor_input, &sax, float_json::input_format_t::cbor));
-        CHECK(sax.errors == 1);
-        CHECK(sax.messages.front() == "[json.exception.out_of_range.406] syntax error while parsing CBOR value: number overflow");
-        REQUIRE(cbor.size() == 2);
-        CHECK(std::isinf(cbor[0].get<float>()));
-        CHECK(cbor[1] == 1);
-
-        // UBJSON: a high-precision number too large for number_float_t
-        const auto ubjson = parse_binary_recovering({'H', 'i', 5, '1', 'e', '9', '9', '9'}, json::input_format_t::ubjson);
-        CHECK(ubjson.errors == 1);
-        CHECK(ubjson.value.is_number_float());
-        CHECK(std::isinf(ubjson.value.get<double>()));
-    }
-
-    SECTION("binary formats stop where the end of an item is not known")
-    {
-        // a byte that begins no item
-        const auto cbor = parse_binary_recovering({0x82, 0x01, 0x1C, 0x02}, json::input_format_t::cbor);
-        CHECK(cbor.errors == 1);
-        CHECK(cbor.value == json({1}));
-
-        // a key that is no item: the unused MessagePack byte, a CBOR break
-        // in a map of known size, and the end of a BON8 container
-        const auto msgpack = parse_binary_recovering({0x82, 0xA1, 'a', 0x01, 0xC1, 0x02}, json::input_format_t::msgpack);
-        CHECK(msgpack.errors == 1);
-        CHECK(msgpack.value == json({{"a", 1}}));
-        const auto cbor_break = parse_binary_recovering({0xA2, 0x61, 'a', 0x01, 0xFF, 0x02}, json::input_format_t::cbor);
-        CHECK(cbor_break.errors == 1);
-        CHECK(cbor_break.value == json({{"a", 1}}));
-        const auto bon8 = parse_binary_recovering({0x88, 0x61, 0x91, 0xFE}, json::input_format_t::bon8);
-        CHECK(bon8.errors == 1);
-        CHECK(bon8.value == json({{"a", 1}}));
-
-        // an indefinite-length string inside an indefinite-length string
-        const auto nested = parse_binary_recovering({0x82, 0x01, 0x7F, 0x7F, 0x61, 'a', 0xFF, 0xFF}, json::input_format_t::cbor);
-        CHECK(nested.errors == 1);
-        CHECK(nested.value == json({1}));
-
-        // a BJData ndarray whose element type has no name: the object that
-        // holds the ndarray was already begun
-        const auto ndarray = parse_binary_recovering({'[', '$', 0x01, '#', '[', '$', 'i', '#', 'i', 2, 2, 3}, json::input_format_t::bjdata);
-        CHECK(ndarray.errors == 1);
-        CHECK(ndarray.balanced);
-        CHECK(ndarray.value == json::object());
-
-        // a skipped member that the input ends in
-        const auto truncated = parse_binary_recovering({0xA2, 0x01, 0x82, 0x01}, json::input_format_t::cbor);
-        CHECK(truncated.errors == 2);
-        CHECK(truncated.balanced);
-        CHECK(truncated.value == json::object());
-
-        // a BSON element of an unknown type in a document whose size cannot be right
-        const auto bson = parse_binary_recovering(bson_document({bson_element(0x10, "a", bson_int32(1)), bson_element(0x42, "x", bytes(3))}, -10), json::input_format_t::bson);
-        CHECK(bson.errors == 1);
-        CHECK(bson.value == json({{"a", 1}, {"x", nullptr}}));
-    }
-
-    SECTION("changed bytes in binary input")
-    {
-        const json j = {{"a", {1, -2, {{"b", "c"}}, json::array()}}, {"d", {{"e", nullptr}, {"f", true}}}, {"g", 1.5}, {"h", json::binary({1, 2, 3})}, {"i", "\xC3\xA4"}};
-
-        const std::vector<std::pair<json::input_format_t, std::vector<std::uint8_t>>> encodings =
-        {
-            {json::input_format_t::cbor, json::to_cbor(j)},
-            {json::input_format_t::msgpack, json::to_msgpack(j)},
-            {json::input_format_t::ubjson, json::to_ubjson(j)},
-            {json::input_format_t::ubjson, json::to_ubjson(j, true, true)},
-            {json::input_format_t::bjdata, json::to_bjdata(j)},
-            {json::input_format_t::bjdata, json::to_bjdata(j, true, true)},
-            {json::input_format_t::bson, json::to_bson(j)},
-            {json::input_format_t::bon8, json::to_bon8(j)},
-        };
-        const std::vector<std::uint8_t> replacements = {0x00, 0x01, 0x7F, 0x80, 0xC1, 0xD9, 0xE0, 0xF7, 0xFE, 0xFF};
-
-        for (const auto& encoding : encodings)
-        {
-            const auto format = encoding.first;
-            const auto& original = encoding.second;
-            CAPTURE(format)
-
-            std::vector<std::vector<std::uint8_t>> inputs;
-            for (std::size_t position = 0; position < original.size(); ++position)
-            {
-                for (const auto replacement : replacements)
-                {
-                    auto changed = original;
-                    changed[position] = replacement;
-                    inputs.push_back(changed);
-                }
-                auto removed = original;
-                removed.erase(removed.begin() + static_cast<std::ptrdiff_t>(position));
-                inputs.push_back(removed);
-            }
-
-            for (const auto& input : inputs)
-            {
-                CAPTURE(input)
-                const auto result = parse_binary_recovering(input, format);
-                CHECK(result.balanced);
-                CHECK(result.errors <= input.size() + 1);
-#if !defined(JSON_NOEXCEPTION)
-                // an error is reported exactly if reading into a JSON value
-                // fails, and the first one is the same (under JSON_NOEXCEPTION,
-                // that reading aborts instead of throwing)
-                const auto message = binary_error_message(input, format);
-                CHECK(result.ok == message.empty());
-                if (!result.ok && result.errors < 100)
-                {
-                    CHECK(result.messages.front() == message);
-                }
-#endif
-            }
-        }
-    }
-
-    SECTION("JSON text")
-    {
-        // the parser stopped, but reported success
-        json j;
-        RecoveringParser sax(j);
-        CHECK(!json::sax_parse("[1,2,3,]", &sax));
-        CHECK(sax.errors == 1);
-        CHECK(j == json({1, 2, 3}));
-    }
-
-    SECTION("the SAX parsers of the library stop")
-    {
-        json _;
-        CHECK(json::from_cbor(std::vector<std::uint8_t> {0x9F}, true, false).is_discarded());
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<std::uint8_t> {0x9F}), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR value: unexpected end of input", json::parse_error&);
-        CHECK(json::parse("[1,2,3,]", nullptr, false).is_discarded());
-        CHECK(!json::accept("[1,2,3,]"));
-    }
-}
-
-
-TEST_CASE("issue #5676 - SAX parsing of CBOR tags")
-{
-    const json expected = json::binary({1, 2, 3}, 42);
-    const auto cbor = json::to_cbor(expected);
-
-    nlohmann::detail::json_sax_acceptor<json> acceptor;
-    CHECK_FALSE(json::sax_parse(cbor, &acceptor, json::input_format_t::cbor));
-    CHECK_FALSE(json::sax_parse(cbor, &acceptor, json::input_format_t::cbor,
-                                true, false, false, json::cbor_tag_handler_t::error));
-
-    CHECK(json::sax_parse(cbor, &acceptor, json::input_format_t::cbor,
-                          true, false, false, json::cbor_tag_handler_t::ignore));
-
-    json parsed;
-    nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type> sax(parsed);
-    CHECK(json::sax_parse(cbor, &sax, json::input_format_t::cbor,
-                          true, false, false, json::cbor_tag_handler_t::store));
-    CHECK(parsed == expected);
-
-    json iterator_parsed;
-    nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type> iterator_sax(iterator_parsed);
-    CHECK(json::sax_parse(cbor.begin(), cbor.end(), &iterator_sax, json::input_format_t::cbor,
-                          true, false, false, json::cbor_tag_handler_t::store));
-    CHECK(iterator_parsed == expected);
-
-#ifndef JSON_TEST_DEPRECATED_FUNCTIONS_DELETED
-    json span_parsed;
-    nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type> span_sax(span_parsed);
-    CHECK(json::sax_parse(nlohmann::detail::span_input_adapter(cbor.data(), cbor.size()), &span_sax,
-                          json::input_format_t::cbor, true, false, false, json::cbor_tag_handler_t::store));
-    CHECK(span_parsed == expected);
-#endif
-
-    const std::string text = "null";
-    CHECK(json::sax_parse(text, &acceptor, json::input_format_t::json,
-                          true, false, false, json::cbor_tag_handler_t::store));
-    CHECK(json::sax_parse(text.begin(), text.end(), &acceptor, json::input_format_t::json,
-                          true, false, false, json::cbor_tag_handler_t::store));
-#ifndef JSON_TEST_DEPRECATED_FUNCTIONS_DELETED
-    CHECK(json::sax_parse(nlohmann::detail::span_input_adapter(text.data(), text.size()), &acceptor,
-                          json::input_format_t::json, true, false, false, json::cbor_tag_handler_t::store));
-#endif
-}
-
-DOCTEST_CLANG_SUPPRESS_WARNING_POP

tests/src/unit-serialization.cpp

@@ -367,8 +367,7 @@ TEST_CASE("dump for basic_json with long double number_float_t")
     // serializer::dump_float(x, std::false_type). That branch must use the
     // "%.*Lg" format specifier; using "%.*g" with a long double argument is
     // undefined behavior and corrupts the output.
-    using long_double_json = nlohmann::basic_json<std::map, std::vector, std::string,
-          bool, std::int64_t, std::uint64_t, long double>;
+    using long_double_json = nlohmann::json::with_float_t<long double>;
 
     SECTION("round-trip dump/parse")
     {

tools/check_build_options/README.md

@@ -0,0 +1,21 @@
+# check_build_options
+
+Checks that the Meson build and the pkg-config files offer the same options as the CMake target, so that a new CMake
+option is not forgotten in one of them.
+
+The compile definitions of the CMake target (`target_compile_definitions` in [`CMakeLists.txt`](../../CMakeLists.txt))
+are the reference. When you add an option there, also add it to
+
+- the pkg-config block in `CMakeLists.txt` (`NLOHMANN_JSON_PKGCONFIG_CFLAGS`),
+- [`meson_options.txt`](../../meson_options.txt), named without the `JSON_` prefix and with the same default,
+- [`meson.build`](../../meson.build) (`json_defines`), and
+- the list of Meson options in
+  [`docs/mkdocs/docs/integration/package_managers.md`](../../docs/mkdocs/docs/integration/package_managers.md).
+
+Run the check with
+
+```shell
+make check_build_options
+```
+
+It needs only Python 3 and runs in the `ci_meson_install` CI job.

tools/check_build_options/check_build_options.py

@@ -0,0 +1,144 @@
+#!/usr/bin/env python3
+"""Check that the Meson build and the pkg-config files offer the CMake options.
+
+The compile definitions of the CMake target (target_compile_definitions in
+CMakeLists.txt) are the reference. For every option used there, the script
+checks that
+
+- the CMake pkg-config file adds the same definition under the same condition,
+- meson_options.txt has a boolean option of the same name without the "JSON_"
+  prefix and with the same default,
+- meson.build adds the same definition under the same condition, and
+- the Meson section of the package manager documentation lists the option.
+
+Meson's MultipleHeaders option selects the include directory and adds no
+definition; it is the only Meson option without a definition.
+"""
+
+import argparse
+import os
+import re
+import sys
+
+REPO_ROOT = os.path.normpath(os.path.join(sys.path[0], '..', '..'))
+DOCS = os.path.join('docs', 'mkdocs', 'docs', 'integration', 'package_managers.md')
+
+# Meson options that add no compile definition, with their default
+MESON_ONLY = {'MultipleHeaders': 'false'}
+
+
+def read(root, path):
+    with open(os.path.join(root, path), encoding='utf-8') as f:
+        return f.read()
+
+
+def cmake_target_definitions(cmake):
+    """Return {option: (definition, add_if_on)} from target_compile_definitions."""
+    block = re.search(r'target_compile_definitions\(\s*\$\{NLOHMANN_JSON_TARGET_NAME\}\s*INTERFACE(.*?)\n\)', cmake, re.S)
+    if not block:
+        sys.exit('CMakeLists.txt: target_compile_definitions of the target not found')
+    result = {}
+    for line in block.group(1).split('\n'):
+        line = line.strip()
+        if not line:
+            continue
+        m = re.fullmatch(r'\$<\$<NOT:\$<BOOL:\$\{JSON_(\w+)\}>>:(\w+=\w+)>', line)
+        if m:
+            result[m.group(1)] = (m.group(2), False)
+            continue
+        m = re.fullmatch(r'\$<\$<BOOL:\$\{JSON_(\w+)\}>:(\w+=\w+)>', line)
+        if m:
+            result[m.group(1)] = (m.group(2), True)
+            continue
+        sys.exit(f'CMakeLists.txt: unexpected line in target_compile_definitions: {line}')
+    return result
+
+
+def cmake_defaults(cmake):
+    """Return {option: 'true'/'false'} for the option() calls of the form JSON_<name>."""
+    return {m.group(1): 'true' if m.group(2) == 'ON' else 'false'
+            for m in re.finditer(r'^option\(JSON_(\w+)\s+"[^"]*"\s+(ON|OFF)\)', cmake, re.M)}
+
+
+def cmake_pkgconfig_definitions(cmake):
+    """Return {option: (definition, add_if_on)} from the pkg-config block."""
+    return {m.group(2): (m.group(3), m.group(1) is None)
+            for m in re.finditer(r'if \((NOT )?JSON_(\w+)\)\s*\n\s*string\(APPEND NLOHMANN_JSON_PKGCONFIG_CFLAGS " -D(\w+=\w+)"\)', cmake)}
+
+
+def meson_options(options):
+    """Return {option: default} for the boolean options in meson_options.txt."""
+    result = {}
+    for block in re.findall(r'option\((.*?)\)', options, re.S):
+        name = re.search(r"'(\w+)'", block).group(1)
+        kind = re.search(r"type\s*:\s*'(\w+)'", block)
+        value = re.search(r'value\s*:\s*(\w+)', block)
+        result[name] = value.group(1) if kind and kind.group(1) == 'boolean' and value else None
+    return result
+
+
+def meson_definitions(meson):
+    """Return {option: (definition, add_if_on)} from meson.build."""
+    return {m.group(2): (m.group(3), m.group(1) is None)
+            for m in re.finditer(r"if (not )?get_option\('(\w+)'\)\s*\n\s*json_defines \+= '(\w+=\w+)'", meson)}
+
+
+def describe(definition):
+    name, add_if_on = definition
+    return f'{name} if {"enabled" if add_if_on else "disabled"}'
+
+
+def compare(errors, where, expected, actual):
+    for option, definition in expected.items():
+        if option not in actual:
+            errors.append(f'{where}: no definition for option {option} (expected {describe(definition)})')
+        elif actual[option] != definition:
+            errors.append(f'{where}: option {option} adds {describe(actual[option])}, expected {describe(definition)}')
+    for option in actual.keys() - expected.keys():
+        errors.append(f'{where}: definition for option {option}, which the CMake target does not have')
+
+
+def main():
+    parser = argparse.ArgumentParser(description=__doc__.split('\n')[0])
+    parser.add_argument('root', nargs='?', default=REPO_ROOT, help='repository root (default: %(default)s)')
+    root = parser.parse_args().root
+
+    cmake = read(root, 'CMakeLists.txt')
+    reference = cmake_target_definitions(cmake)
+    defaults = cmake_defaults(cmake)
+    errors = []
+
+    compare(errors, 'CMakeLists.txt (pkg-config)', reference, cmake_pkgconfig_definitions(cmake))
+    compare(errors, 'meson.build', reference, meson_definitions(read(root, 'meson.build')))
+
+    options = meson_options(read(root, 'meson_options.txt'))
+    for option in reference:
+        if option not in defaults:
+            errors.append(f'CMakeLists.txt: no option(JSON_{option} ... ON|OFF)')
+        elif option not in options:
+            errors.append(f'meson_options.txt: option {option} missing')
+        elif options[option] != defaults[option]:
+            errors.append(f'meson_options.txt: option {option} must be boolean with value {defaults[option]} as in CMake')
+    for option, default in MESON_ONLY.items():
+        if options.get(option) != default:
+            errors.append(f'meson_options.txt: option {option} must be boolean with value {default}')
+    for option in options.keys() - reference.keys() - MESON_ONLY.keys():
+        errors.append(f'meson_options.txt: option {option} has no counterpart in the CMake target')
+
+    docs = read(root, DOCS)
+    for option in sorted(set(options) & (reference.keys() | MESON_ONLY.keys())):
+        if f'`{option}`' not in docs:
+            errors.append(f'{DOCS}: Meson option {option} not listed')
+
+    for error in errors:
+        print(error, file=sys.stderr)
+    if errors:
+        print('The Meson build and the pkg-config files must offer the options of the CMake target; see '
+              'tools/check_build_options/README.md.', file=sys.stderr)
+        return 1
+    print(f'OK: {len(reference)} options with compile definitions agree between CMake, pkg-config, and Meson.')
+    return 0
+
+
+if __name__ == '__main__':
+    sys.exit(main())