Merge remote-tracking branch 'origin/develop' into claude/fix-issue-3989-db7e45

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

# Conflicts:
#	include/nlohmann/detail/input/binary_reader.hpp
#	include/nlohmann/json.hpp
#	single_include/nlohmann/json.hpp

.cirrus.yml

@@ -0,0 +1,17 @@
+arm_container:
+  image: gcc:latest
+
+check_task:
+  check_script:
+  # the gcc image ships an outdated CMake, so fetch a recent prebuilt binary
+  # instead of compiling CMake from source
+  - wget -q https://github.com/Kitware/CMake/releases/download/v4.3.4/cmake-4.3.4-linux-aarch64.tar.gz
+  - tar xfz cmake-4.3.4-linux-aarch64.tar.gz
+  - export PATH="$(pwd)/cmake-4.3.4-linux-aarch64/bin:$PATH"
+  - cmake --version
+  - mkdir build
+  - cd build
+  - cmake .. -DJSON_FastTests=ON
+  - make -j4
+  - cd tests
+  - ctest -j4

.github/dependabot.yml

@@ -24,10 +24,6 @@ updates:
       interval: daily
     cooldown:
       default-days: 7
-    ignore:
-      # astyle is deliberately pinned (see tools/astyle/requirements.txt): newer versions
-      # reformat the code, and the pinned version defines the formatting CI enforces
-      - dependency-name: astyle
 
   - package-ecosystem: pip
     directory: /tools/generate_natvis

.github/external_ci/appveyor.yml

@@ -30,6 +30,14 @@ environment:
       CMAKE_OPTIONS: ""
       GENERATOR: Visual Studio 14 2015
 
+    - APPVEYOR_BUILD_WORKER_IMAGE: Visual Studio 2015
+      configuration: Release
+      platform: x86
+      name: with_win_header
+      CXX_FLAGS: "/W4 /WX"
+      CMAKE_OPTIONS: ""
+      GENERATOR: Visual Studio 14 2015
+
     - APPVEYOR_BUILD_WORKER_IMAGE: Visual Studio 2017
       configuration: Release
       platform: x86
@@ -66,6 +74,9 @@ install:
   - if "%platform%"=="x86"    set GENERATOR_PLATFORM=Win32
 
 before_build:
+  # for with_win_header build, inject the inclusion of Windows.h to the single-header library
+  - ps: if ($env:name -Eq "with_win_header") { $header_path = "single_include\nlohmann\json.hpp" }
+  - ps: if ($env:name -Eq "with_win_header") { "#include <Windows.h>`n" + (Get-Content $header_path | Out-String) | Set-Content $header_path }
   - cmake . -G "%GENERATOR%" -A "%GENERATOR_PLATFORM%" -DCMAKE_CXX_FLAGS="%CXX_FLAGS%" -DCMAKE_IGNORE_PATH="C:/Program Files/Git/usr/bin" -DJSON_BuildTests=On "%CMAKE_OPTIONS%"
 
 build_script:

.github/workflows/ubuntu.yml

@@ -52,13 +52,6 @@ jobs:
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
         run: cmake --build build --target ci_infer
-      - name: Archive Infer report
-        if: always()
-        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
-        with:
-          name: infer-report
-          path: ${{ github.workspace }}/build/build_infer/infer-out/report.txt
-          if-no-files-found: ignore
 
   ci_static_analysis_ubuntu:
     runs-on: ubuntu-latest
@@ -104,13 +97,13 @@ jobs:
 
   ci_cmake_options:
     runs-on: ubuntu-latest
-    container: ubuntu:24.04
+    container: ubuntu:focal
     strategy:
       matrix:
         target: [ci_cmake_flags, ci_test_diagnostics, ci_test_diagnostic_positions, ci_test_noexceptions, ci_test_noimplicitconversions, ci_test_legacycomparison, ci_test_noglobaludls, ci_test_disableenumserialization, ci_test_disabletuplereferenceconversion, ci_test_skiplibraryversioncheck, ci_test_simdutf, ci_test_strict_nul_handling, ci_test_no_thread_local]
     steps:
       - name: Install build-essential
-        run: apt-get update ; apt-get install -y build-essential unzip wget git
+        run: apt-get update ; apt-get install -y build-essential unzip wget git libssl-dev
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           persist-credentials: false
@@ -414,21 +407,3 @@ jobs:
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
         run: cmake --build build --target ${{ matrix.target }}
-
-  # Native Linux ARM64 runner with the latest GCC. The ubuntu-24.04-arm label is
-  # only available for public repositories.
-  ci_test_arm64:
-    runs-on: ubuntu-24.04-arm
-    container: gcc:latest
-    steps:
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
-        with:
-          persist-credentials: false
-      - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
-      - name: Check that the job runs natively on arm64
-        run: uname -m && test "$(uname -m)" = aarch64
-      - name: Run CMake
-        run: cmake -S . -B build -DJSON_CI=On
-      - name: Build
-        run: cmake --build build --target ci_test_compiler_default

.inferconfig

@@ -1,12 +0,0 @@
-{
-  "_comment": "Used by the ci_infer CMake target (#5715 item 4b). fail-on-issue makes CI fail on Infer findings; disable-issue-type is a type-level baseline for the ~174 pre-existing findings (all PULSE_UNNECESSARY_COPY*/PULSE_RESOURCE_LEAK/PULSE_CONST_REFABLE, mostly in test code) triaged in run https://github.com/nlohmann/json/actions/runs/35829411620 on commit 1054b2097, so CI fails only on a NEW issue type. Remove an entry here once its findings have been fixed or explicitly accepted.",
-  "fail-on-issue": true,
-  "disable-issue-type": [
-    "PULSE_UNNECESSARY_COPY_ASSIGNMENT",
-    "PULSE_UNNECESSARY_COPY",
-    "PULSE_UNNECESSARY_COPY_INTERMEDIATE",
-    "PULSE_UNNECESSARY_COPY_OPTIONAL",
-    "PULSE_RESOURCE_LEAK",
-    "PULSE_CONST_REFABLE"
-  ]
-}

FILES.md

@@ -33,6 +33,17 @@ Further documentation:
 > [!IMPORTANT]
 > The folder `.github/workflows` is predetermined by GitHub.
 
+### `.cirrus.yml`
+
+Configuration file for the pipeline at [Cirrus CI](https://cirrus-ci.com/github/nlohmann/json).
+
+Further documentation:
+
+- [Writing tasks](https://cirrus-ci.org/guide/writing-tasks/)
+
+> [!IMPORTANT]
+> The filename `.cirrus.yml` and position (root of the repository) are predetermined by Cirrus CI.
+
 ### `.github/external_ci/appveyor.yml`
 
 Configuration for the pipelines at [AppVeyor](https://ci.appveyor.com/project/nlohmann/json).

Makefile

@@ -87,7 +87,7 @@ install_astyle:
 
 # call the Artistic Style pretty printer on all source files
 pretty: install_astyle
-	$(ASTYLE) --project=tools/astyle/.astylerc $(SRCS) $(TESTS_SRCS) $(AMALGAMATED_FILE) $(AMALGAMATED_FWD_FILE) $(AMALGAMATED_LITERALS_FILE) docs/mkdocs/docs/examples/*.cpp docs/mkdocs/docs/examples/*.hpp
+	$(ASTYLE) --project=tools/astyle/.astylerc $(SRCS) $(TESTS_SRCS) $(AMALGAMATED_FILE) $(AMALGAMATED_FWD_FILE) $(AMALGAMATED_LITERALS_FILE) docs/mkdocs/docs/examples/*.cpp
 
 # create single header files and pretty print
 amalgamate: $(AMALGAMATED_FILE) $(AMALGAMATED_FWD_FILE) $(AMALGAMATED_LITERALS_FILE)

README.md

@@ -7,6 +7,7 @@
 [![Coverage Status](https://coveralls.io/repos/github/nlohmann/json/badge.svg?branch=develop)](https://coveralls.io/github/nlohmann/json?branch=develop)
 [![Coverity Scan Build Status](https://scan.coverity.com/projects/5550/badge.svg)](https://scan.coverity.com/projects/nlohmann-json)
 [![Codacy Badge](https://app.codacy.com/project/badge/Grade/e0d1a9d5d6fd46fcb655c4cb930bb3e8)](https://app.codacy.com/gh/nlohmann/json/dashboard?utm_source=gh&utm_medium=referral&utm_content=&utm_campaign=Badge_grade)
+[![Cirrus CI](https://api.cirrus-ci.com/github/nlohmann/json.svg)](https://cirrus-ci.com/github/nlohmann/json)
 [![Fuzzing Status](https://oss-fuzz-build-logs.storage.googleapis.com/badges/json.svg)](https://bugs.chromium.org/p/oss-fuzz/issues/list?sort=-opened&can=1&q=proj:json)
 [![Try online](https://img.shields.io/badge/try-online-blue.svg)](https://wandbox.org/permlink/1mp10JbaANo6FUc7)
 [![Documentation](https://img.shields.io/badge/docs-mkdocs-blue.svg)](https://json.nlohmann.me)
@@ -495,7 +496,7 @@ 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.
+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.
 
 To implement your own SAX handler, proceed as follows:
 
@@ -503,7 +504,7 @@ 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 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).
+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).
 
 ### STL-like access
 

cmake/ci.cmake

@@ -40,14 +40,6 @@ execute_process(COMMAND ${IWYU_TOOL} --version OUTPUT_VARIABLE IWYU_TOOL_VERSION
 string(REGEX MATCH "[0-9]+(\\.[0-9]+)+" IWYU_TOOL_VERSION "${IWYU_TOOL_VERSION}")
 message(STATUS "🔖 include-what-you-use ${IWYU_TOOL_VERSION} (${IWYU_TOOL})")
 
-# CMake's CXX_INCLUDE_WHAT_YOU_USE launcher runs IWYU during the normal compile step (useful to see
-# diagnostics inline), but CMake's own __run_co_compile wrapper does not propagate the launched
-# tool's exit code to the build, so IWYU's own "-Xiwyu --error" cannot fail that step (verified: a
-# deliberately-unused #include in a header still lets `cmake --build` finish with exit code 0).
-# iwyu_tool.py, which ships with IWYU, reads compile_commands.json and does return a non-zero exit
-# code for any analyzed file with findings; ci_single_binaries uses it to actually fail on findings.
-find_program(IWYU_TOOL_PY NAMES iwyu_tool iwyu_tool.py iwyu-tool)
-
 find_program(INFER_TOOL NAMES infer)
 execute_process(COMMAND ${INFER_TOOL} --version OUTPUT_VARIABLE INFER_TOOL_VERSION ERROR_VARIABLE INFER_TOOL_VERSION)
 string(REGEX MATCH "[0-9]+(\\.[0-9]+)+" INFER_TOOL_VERSION "${INFER_TOOL_VERSION}")
@@ -63,6 +55,12 @@ execute_process(COMMAND ${NINJA_TOOL} --version OUTPUT_VARIABLE NINJA_TOOL_VERSI
 string(REGEX MATCH "[0-9]+(\\.[0-9]+)+" NINJA_TOOL_VERSION "${NINJA_TOOL_VERSION}")
 message(STATUS "🔖 Ninja ${NINJA_TOOL_VERSION} (${NINJA_TOOL})")
 
+find_program(OCLINT_TOOL NAMES oclint-json-compilation-database)
+find_program(OCLINT_VERSION_TOOL NAMES oclint)
+execute_process(COMMAND ${OCLINT_VERSION_TOOL} --version OUTPUT_VARIABLE OCLINT_TOOL_VERSION ERROR_VARIABLE OCLINT_TOOL_VERSION)
+string(REGEX MATCH "[0-9]+(\\.[0-9]+)+" OCLINT_TOOL_VERSION "${OCLINT_TOOL_VERSION}")
+message(STATUS "🔖 OCLint ${OCLINT_TOOL_VERSION} (${OCLINT_TOOL})")
+
 find_program(VALGRIND_TOOL NAMES valgrind)
 execute_process(COMMAND ${VALGRIND_TOOL} --version OUTPUT_VARIABLE VALGRIND_TOOL_VERSION ERROR_VARIABLE VALGRIND_TOOL_VERSION)
 string(REGEX MATCH "[0-9]+(\\.[0-9]+)+" VALGRIND_TOOL_VERSION "${VALGRIND_TOOL_VERSION}")
@@ -130,16 +128,16 @@ foreach(CXX_STANDARD 11 14 17 20 23 26)
         COMMENT "Compile and test with Clang for C++${CXX_STANDARD}"
     )
 
-    # pass -stdlib=libc++ through CXXFLAGS: an explicit -DCMAKE_CXX_FLAGS would make CMake ignore CXXFLAGS
     add_custom_target(ci_test_clang_libcxx_cxx${CXX_STANDARD}
-        COMMAND CXX=${CLANG_TOOL} CXXFLAGS="${CLANG_CXXFLAGS};-stdlib=libc++" ${CMAKE_COMMAND}
+        COMMAND CXX=${CLANG_TOOL} CXXFLAGS="${CLANG_CXXFLAGS}" ${CMAKE_COMMAND}
             -DCMAKE_BUILD_TYPE=Debug -GNinja
             -DJSON_BuildTests=ON -DJSON_FastTests=ON
             -DJSON_TestStandards=${CXX_STANDARD}
+            -DCMAKE_CXX_FLAGS="-stdlib=libc++"
             -DCMAKE_EXE_LINKER_FLAGS="-lc++abi"
-            -S${PROJECT_SOURCE_DIR} -B${PROJECT_BINARY_DIR}/build_clang_libcxx_cxx${CXX_STANDARD}
+            -S${PROJECT_SOURCE_DIR} -B${PROJECT_BINARY_DIR}/build_clang_cxx${CXX_STANDARD}
-        COMMAND ${CMAKE_COMMAND} --build ${PROJECT_BINARY_DIR}/build_clang_libcxx_cxx${CXX_STANDARD}
+        COMMAND ${CMAKE_COMMAND} --build ${PROJECT_BINARY_DIR}/build_clang_cxx${CXX_STANDARD}
-        COMMAND cd ${PROJECT_BINARY_DIR}/build_clang_libcxx_cxx${CXX_STANDARD} && ${CMAKE_CTEST_COMMAND} --parallel ${N} --output-on-failure
+        COMMAND cd ${PROJECT_BINARY_DIR}/build_clang_cxx${CXX_STANDARD} && ${CMAKE_CTEST_COMMAND} --parallel ${N} --output-on-failure
         COMMENT "Compile and test with Clang for C++${CXX_STANDARD} (libc++)"
     )
 endforeach()
@@ -378,20 +376,13 @@ add_custom_target(ci_test_clang_sanitizer
 # Check if header is amalgamated and sources are properly indented.
 ###############################################################################
 
-# Same file set as .github/workflows/check_amalgamation.yml, so a direct push to develop/master/release/*
-# (which only this CMake target checks, not the pull_request-only workflow) is held to the same standard.
 file(GLOB_RECURSE INDENT_FILES
-    ${PROJECT_SOURCE_DIR}/docs/mkdocs/docs/examples/*.hpp
+    ${PROJECT_SOURCE_DIR}/include/nlohmann/*.hpp
+        ${PROJECT_SOURCE_DIR}/tests/src/*.cpp
+        ${PROJECT_SOURCE_DIR}/tests/src/*.hpp
+        ${PROJECT_SOURCE_DIR}/tests/benchmarks/src/benchmarks.cpp
     ${PROJECT_SOURCE_DIR}/docs/mkdocs/docs/examples/*.cpp
-    ${PROJECT_SOURCE_DIR}/docs/mkdocs/docs/examples/*.cu
-    ${PROJECT_SOURCE_DIR}/include/*.hpp
-    ${PROJECT_SOURCE_DIR}/include/*.cpp
-    ${PROJECT_SOURCE_DIR}/include/*.cu
-    ${PROJECT_SOURCE_DIR}/tests/*.hpp
-    ${PROJECT_SOURCE_DIR}/tests/*.cpp
-    ${PROJECT_SOURCE_DIR}/tests/*.cu
 )
-list(FILTER INDENT_FILES EXCLUDE REGEX "/tests/thirdparty/|/tests/abi/include/nlohmann/")
 
 set(include_dir ${PROJECT_SOURCE_DIR}/single_include/nlohmann)
 set(tool_dir ${PROJECT_SOURCE_DIR}/tools/amalgamate)
@@ -400,7 +391,6 @@ add_custom_target(ci_test_amalgamation
     COMMAND cp ${include_dir}/json.hpp ${include_dir}/json.hpp~
     COMMAND cp ${include_dir}/json_fwd.hpp ${include_dir}/json_fwd.hpp~
     COMMAND cp ${include_dir}/json_literals.hpp ${include_dir}/json_literals.hpp~
-    COMMAND cp ${PROJECT_SOURCE_DIR}/BUILD.bazel ${PROJECT_SOURCE_DIR}/BUILD.bazel~
 
     COMMAND ${Python3_EXECUTABLE} -mvenv venv_astyle
     COMMAND venv_astyle/bin/pip3 --quiet install -r ${CMAKE_SOURCE_DIR}/tools/astyle/requirements.txt
@@ -410,18 +400,16 @@ add_custom_target(ci_test_amalgamation
     COMMAND ${Python3_EXECUTABLE} ${tool_dir}/amalgamate.py -c ${tool_dir}/config_json_fwd.json -s .
     COMMAND cp ${PROJECT_SOURCE_DIR}/include/nlohmann/json_literals.hpp ${include_dir}/json_literals.hpp
     COMMAND venv_astyle/bin/astyle --project=tools/astyle/.astylerc --suffix=none ${include_dir}/json.hpp ${include_dir}/json_fwd.hpp
-    COMMAND ${CMAKE_COMMAND} -P ${PROJECT_SOURCE_DIR}/cmake/scripts/gen_bazel_build_file.cmake
 
     COMMAND diff ${include_dir}/json.hpp~ ${include_dir}/json.hpp
     COMMAND diff ${include_dir}/json_fwd.hpp~ ${include_dir}/json_fwd.hpp
     COMMAND diff ${include_dir}/json_literals.hpp~ ${include_dir}/json_literals.hpp
-    COMMAND diff ${PROJECT_SOURCE_DIR}/BUILD.bazel~ ${PROJECT_SOURCE_DIR}/BUILD.bazel
 
     COMMAND venv_astyle/bin/astyle --project=tools/astyle/.astylerc --suffix=orig ${INDENT_FILES}
     COMMAND for FILE in `find . -name '*.orig'`\; do false \; done
 
     WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}
-    COMMENT "Check amalgamation, formatting, and BUILD.bazel"
+    COMMENT "Check amalgamation and indentation"
 )
 
 ###############################################################################
@@ -456,14 +444,14 @@ add_custom_target(ci_test_valgrind
 # Check code with Clang Static Analyzer.
 ###############################################################################
 
-set(CLANG_ANALYZER_CHECKS "nullability.NullableDereferenced,nullability.NullablePassedToNonnull,nullability.NullableReturnedFromNonnull,optin.cplusplus.UninitializedObject,optin.cplusplus.VirtualCall,optin.performance.Padding,optin.portability.UnixAPI,security.FloatLoopCounter,security.insecureAPI.DeprecatedOrUnsafeBufferHandling,security.insecureAPI.bcmp,security.insecureAPI.bcopy,security.insecureAPI.bzero,security.insecureAPI.rand,security.insecureAPI.strcpy,valist.CopyToSelf,valist.Uninitialized,valist.Unterminated,core.CallAndMessage,core.DivideZero,core.NonNullParamChecker,core.NullDereference,core.StackAddressEscape,core.UndefinedBinaryOperatorResult,core.VLASize,core.uninitialized.ArraySubscript,core.uninitialized.Assign,core.uninitialized.Branch,core.uninitialized.CapturedBlockVariable,core.uninitialized.UndefReturn,cplusplus.InnerPointer,cplusplus.Move,cplusplus.NewDelete,cplusplus.NewDeleteLeaks,cplusplus.PlacementNew,cplusplus.PureVirtualCall,deadcode.DeadStores,nullability.NullPassedToNonnull,nullability.NullReturnedFromNonnull,security.insecureAPI.UncheckedReturn,security.insecureAPI.decodeValueOfObjCType,security.insecureAPI.getpw,security.insecureAPI.gets,security.insecureAPI.mkstemp,security.insecureAPI.mktemp,security.insecureAPI.vfork,unix.API,unix.Malloc,unix.MallocSizeof,unix.MismatchedDeallocator,unix.Vfork,unix.cstring.BadSizeArg,unix.cstring.NullArg")
+set(CLANG_ANALYZER_CHECKS "fuchsia.HandleChecker,nullability.NullableDereferenced,nullability.NullablePassedToNonnull,nullability.NullableReturnedFromNonnull,optin.cplusplus.UninitializedObject,optin.cplusplus.VirtualCall,optin.mpi.MPI-Checker,optin.osx.OSObjectCStyleCast,optin.osx.cocoa.localizability.EmptyLocalizationContextChecker,optin.osx.cocoa.localizability.NonLocalizedStringChecker,optin.performance.GCDAntipattern,optin.performance.Padding,optin.portability.UnixAPI,security.FloatLoopCounter,security.insecureAPI.DeprecatedOrUnsafeBufferHandling,security.insecureAPI.bcmp,security.insecureAPI.bcopy,security.insecureAPI.bzero,security.insecureAPI.rand,security.insecureAPI.strcpy,valist.CopyToSelf,valist.Uninitialized,valist.Unterminated,webkit.NoUncountedMemberChecker,webkit.RefCntblBaseVirtualDtor,core.CallAndMessage,core.DivideZero,core.NonNullParamChecker,core.NullDereference,core.StackAddressEscape,core.UndefinedBinaryOperatorResult,core.VLASize,core.uninitialized.ArraySubscript,core.uninitialized.Assign,core.uninitialized.Branch,core.uninitialized.CapturedBlockVariable,core.uninitialized.UndefReturn,cplusplus.InnerPointer,cplusplus.Move,cplusplus.NewDelete,cplusplus.NewDeleteLeaks,cplusplus.PlacementNew,cplusplus.PureVirtualCall,deadcode.DeadStores,nullability.NullPassedToNonnull,nullability.NullReturnedFromNonnull,osx.API,osx.MIG,osx.NumberObjectConversion,osx.OSObjectRetainCount,osx.ObjCProperty,osx.SecKeychainAPI,osx.cocoa.AtSync,osx.cocoa.AutoreleaseWrite,osx.cocoa.ClassRelease,osx.cocoa.Dealloc,osx.cocoa.IncompatibleMethodTypes,osx.cocoa.Loops,osx.cocoa.MissingSuperCall,osx.cocoa.NSAutoreleasePool,osx.cocoa.NSError,osx.cocoa.NilArg,osx.cocoa.NonNilReturnValue,osx.cocoa.ObjCGenerics,osx.cocoa.RetainCount,osx.cocoa.RunLoopAutoreleaseLeak,osx.cocoa.SelfInit,osx.cocoa.SuperDealloc,osx.cocoa.UnusedIvars,osx.cocoa.VariadicMethodTypes,osx.coreFoundation.CFError,osx.coreFoundation.CFNumber,osx.coreFoundation.CFRetainRelease,osx.coreFoundation.containers.OutOfBounds,osx.coreFoundation.containers.PointerSizedValues,security.insecureAPI.UncheckedReturn,security.insecureAPI.decodeValueOfObjCType,security.insecureAPI.getpw,security.insecureAPI.gets,security.insecureAPI.mkstemp,security.insecureAPI.mktemp,security.insecureAPI.vfork,unix.API,unix.Malloc,unix.MallocSizeof,unix.MismatchedDeallocator,unix.Vfork,unix.cstring.BadSizeArg,unix.cstring.NullArg")
 
 add_custom_target(ci_clang_analyze
     COMMAND CXX=${CLANG_TOOL} ${CMAKE_COMMAND}
         -DCMAKE_BUILD_TYPE=Debug -GNinja
         -DJSON_BuildTests=ON
         -S${PROJECT_SOURCE_DIR} -B${PROJECT_BINARY_DIR}/build_clang_analyze
-    COMMAND cd ${PROJECT_BINARY_DIR}/build_clang_analyze && ${SCAN_BUILD_TOOL} -enable-checker ${CLANG_ANALYZER_CHECKS} --use-c++=${CLANG_TOOL} --use-analyzer=${CLANG_TOOL} -analyze-headers --status-bugs -o ${PROJECT_BINARY_DIR}/report ninja
+    COMMAND cd ${PROJECT_BINARY_DIR}/build_clang_analyze && ${SCAN_BUILD_TOOL} -enable-checker ${CLANG_ANALYZER_CHECKS} --use-c++=${CLANG_TOOL} -analyze-headers -o ${PROJECT_BINARY_DIR}/report ninja
     COMMENT "Check code with Clang Analyzer"
 )
 
@@ -479,7 +467,7 @@ add_custom_target(ci_cppcheck
     COMMAND venv_cppcheck/bin/cppcheck --enable=warning --check-level=exhaustive --inline-suppr --inconclusive --force
             --std=c++11 ${PROJECT_SOURCE_DIR}/include/nlohmann/json.hpp -I ${CMAKE_SOURCE_DIR}/include
             --error-exitcode=1 --relative-paths=${PROJECT_SOURCE_DIR} -j ${N} --include=default_defines.hpp
-            --cppcheck-build-dir=cppcheck
+            --cppcheck-build-dir=cppcheck --check-level=exhaustive
             -UJSON_CATCH_USER -UJSON_TRY_USER -UJSON_ASSERT -UJSON_INTERNAL_CATCH -UJSON_THROW
             -DJSON_HAS_CPP_11 -UJSON_HAS_CPP_14 -UJSON_HAS_CPP_17 -UJSON_HAS_CPP_20 -UJSON_HAS_THREE_WAY_COMPARISON
     COMMENT "Check code with Cppcheck"
@@ -497,6 +485,34 @@ add_custom_target(ci_cpplint
     WORKING_DIRECTORY ${PROJECT_BINARY_DIR}
 )
 
+###############################################################################
+# Check code with OCLint.
+###############################################################################
+
+file(COPY ${PROJECT_SOURCE_DIR}/single_include/nlohmann/json.hpp DESTINATION ${PROJECT_BINARY_DIR}/src_single)
+file(RENAME ${PROJECT_BINARY_DIR}/src_single/json.hpp ${PROJECT_BINARY_DIR}/src_single/all.cpp)
+file(APPEND "${PROJECT_BINARY_DIR}/src_single/all.cpp" "\n\nint main()\n{}\n")
+
+add_executable(single_all ${PROJECT_BINARY_DIR}/src_single/all.cpp)
+target_compile_features(single_all PRIVATE cxx_std_11)
+
+add_custom_target(ci_oclint
+    COMMAND ${CMAKE_COMMAND}
+        -DCMAKE_BUILD_TYPE=Debug
+        -DCMAKE_EXPORT_COMPILE_COMMANDS=ON
+        -DJSON_BuildTests=OFF -DJSON_CI=ON
+        -S${PROJECT_SOURCE_DIR} -B${PROJECT_BINARY_DIR}/build_oclint
+    COMMAND ${OCLINT_TOOL} -i ${PROJECT_BINARY_DIR}/build_oclint/src_single/all.cpp -p ${PROJECT_BINARY_DIR}/build_oclint --
+        -report-type html -enable-global-analysis --max-priority-1=0 --max-priority-2=1000 --max-priority-3=2000
+        --disable-rule=MultipleUnaryOperator
+        --disable-rule=DoubleNegative
+        --disable-rule=ShortVariableName
+        --disable-rule=GotoStatement
+        --disable-rule=LongLine
+        -o ${PROJECT_BINARY_DIR}/build_oclint/oclint_report.html
+    COMMENT "Check code with OCLint"
+)
+
 ###############################################################################
 # Check code with Clang-Tidy.
 ###############################################################################
@@ -511,16 +527,29 @@ add_custom_target(ci_clang_tidy
     COMMENT "Check code with Clang-Tidy"
 )
 
+###############################################################################
+# Check code with PVS-Studio Analyzer <https://www.viva64.com/en/pvs-studio/>.
+###############################################################################
+
+add_custom_target(ci_pvs_studio
+    COMMAND CXX=${CLANG_TOOL} ${CMAKE_COMMAND}
+        -DCMAKE_BUILD_TYPE=Debug
+        -DCMAKE_EXPORT_COMPILE_COMMANDS=ON
+        -DJSON_BuildTests=ON
+        -S${PROJECT_SOURCE_DIR} -B${PROJECT_BINARY_DIR}/build_pvs_studio
+    COMMAND cd ${PROJECT_BINARY_DIR}/build_pvs_studio && ${PVS_STUDIO_ANALYZER_TOOL} analyze -j 10
+    COMMAND cd ${PROJECT_BINARY_DIR}/build_pvs_studio && ${PLOG_CONVERTER_TOOL} -a'GA:1,2;64:1;CS' -t fullhtml PVS-Studio.log -o pvs
+    COMMENT "Check code with PVS Studio"
+)
+
 ###############################################################################
 # Check code with Infer <https://fbinfer.com> static analyzer.
 ###############################################################################
 
-# .inferconfig (repository root) pins --fail-on-issue and the currently-triaged issue types that
-# are disabled until they are addressed separately; see #5715 item 4b.
 add_custom_target(ci_infer
     COMMAND mkdir -p ${PROJECT_BINARY_DIR}/build_infer
     COMMAND cd ${PROJECT_BINARY_DIR}/build_infer && ${INFER_TOOL} compile -- ${CMAKE_COMMAND} -DCMAKE_BUILD_TYPE=Debug ${PROJECT_SOURCE_DIR} -DJSON_BuildTests=ON
-    COMMAND cd ${PROJECT_BINARY_DIR}/build_infer && ${INFER_TOOL} run --project-root ${PROJECT_SOURCE_DIR} -- make
+    COMMAND cd ${PROJECT_BINARY_DIR}/build_infer && ${INFER_TOOL} run -- make
     COMMENT "Check code with Infer"
 )
 
@@ -576,13 +605,7 @@ add_custom_target(ci_reproducible_tests
 # be compiled individually.
 ###############################################################################
 
-set(iwyu_options -Xiwyu --error -Xiwyu --max_line_length=300)
+set(iwyu_path_and_options ${IWYU_TOOL} -Xiwyu --max_line_length=300)
-set(iwyu_path_and_options ${IWYU_TOOL} ${iwyu_options})
-
-# CMake needs to know the exact flags used to compile each src_single/*.cpp below to hand them to
-# iwyu_tool.py; JSON_CI already implies a from-scratch configure, so enabling this project-wide has
-# no downside here.
-set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
 
 foreach(SRC_FILE ${SRC_FILES})
     # get relative path of the header file
@@ -597,34 +620,14 @@ foreach(SRC_FILE ${SRC_FILES})
     target_include_directories(single_${RELATIVE_SRC_FILE} PRIVATE ${PROJECT_SOURCE_DIR}/include)
     target_compile_features(single_${RELATIVE_SRC_FILE} PRIVATE cxx_std_11)
     set_property(TARGET single_${RELATIVE_SRC_FILE} PROPERTY CXX_INCLUDE_WHAT_YOU_USE "${iwyu_path_and_options}")
-    # remember binary for ci_single_binaries
+    # remember binary for ci_single_binaries target
     list(APPEND single_binaries single_${RELATIVE_SRC_FILE})
-    # json.hpp pulls together the whole library behind heavily templated, SFINAE-based code, and
-    # IWYU's suggestion for its one truly ambiguous symbol (a container-comparison "swap,
-    # operator!=") is not deterministic between runs (observed <set>, <unordered_map>, and <map>
-    # for the exact same source across otherwise-identical local and containerized builds). Keep
-    # reporting its diagnostics (informational, via CXX_INCLUDE_WHAT_YOU_USE above) but exclude it
-    # from the hard gate below so a fresh IWYU/compiler combination does not fail this target on a
-    # nondeterministic suggestion for a header that already re-exports everything on purpose.
-    if(NOT RELATIVE_SRC_FILE STREQUAL "json")
-        list(APPEND single_binaries_tus src_single/${RELATIVE_SRC_FILE}.cpp)
-    endif()
 endforeach()
 
-if(IWYU_TOOL_PY)
-    add_custom_target(ci_single_binaries
-        DEPENDS ${single_binaries}
-        COMMAND ${IWYU_TOOL_PY} -p ${PROJECT_BINARY_DIR} ${single_binaries_tus} -- ${iwyu_options}
-        COMMENT "Check if headers are self-contained"
-    )
-else()
-    # iwyu_tool.py (ships with IWYU, e.g. as /usr/bin/iwyu_tool on Debian/Ubuntu) was not found;
-    # fall back to building the self-containment check without enforcing the IWYU findings.
 add_custom_target(ci_single_binaries
     DEPENDS ${single_binaries}
     COMMENT "Check if headers are self-contained"
 )
-endif()
 
 ###############################################################################
 # Benchmarks
@@ -646,29 +649,10 @@ add_custom_target(ci_benchmarks
 # we test the project with different CMake versions:
 # - CMake 3.5 (the earliest supported)
 # - CMake 3.31.6 (the latest 3.x release)
-# - CMake 4.0.0 (the first 4.x release)
+# - CMake 4.0.0 (the latest release)
-# - the CMake version running this build (usually the latest release)
 
 function(ci_get_cmake version var)
     set(${var} ${PROJECT_BINARY_DIR}/cmake-${version}/bin/cmake)
-    if(CMAKE_HOST_SYSTEM_NAME STREQUAL "Linux" AND CMAKE_HOST_SYSTEM_PROCESSOR MATCHES "^(x86_64|amd64)$")
-        # Kitware publishes a prebuilt Linux x86_64 archive for every release; unpacking it is far
-        # cheaper than compiling all of CMake (including its own test helpers) from source.
-        add_custom_command(
-            OUTPUT ${${var}}
-            COMMAND wget -nc https://github.com/Kitware/CMake/releases/download/v${version}/cmake-${version}-linux-x86_64.tar.gz
-            COMMAND wget -nc https://github.com/Kitware/CMake/releases/download/v${version}/cmake-${version}-SHA-256.txt
-            # verify the archive against Kitware's published SHA-256 sums before unpacking it
-            COMMAND sh -c "grep ' cmake-${version}-linux-x86_64[.]tar[.]gz$' cmake-${version}-SHA-256.txt | sha256sum -c -"
-            COMMAND tar xfz cmake-${version}-linux-x86_64.tar.gz
-            COMMAND rm cmake-${version}-linux-x86_64.tar.gz cmake-${version}-SHA-256.txt
-            COMMAND ${CMAKE_COMMAND} -E rm -rf cmake-${version}
-            COMMAND ${CMAKE_COMMAND} -E rename cmake-${version}-linux-x86_64 cmake-${version}
-            WORKING_DIRECTORY ${PROJECT_BINARY_DIR}
-            COMMENT "Download prebuilt CMake ${version}"
-        )
-    else()
-        # no prebuilt archive for this platform (e.g. macOS or Linux aarch64): build from source
     add_custom_command(
         OUTPUT ${${var}}
         COMMAND wget -nc https://github.com/Kitware/CMake/releases/download/v${version}/cmake-${version}.tar.gz
@@ -678,9 +662,8 @@ function(ci_get_cmake version var)
         COMMAND cmake -S cmake-${version} -B cmake-${version} -DCMAKE_POLICY_VERSION_MINIMUM=3.5
         COMMAND cmake --build cmake-${version} --parallel 10
         WORKING_DIRECTORY ${PROJECT_BINARY_DIR}
-            COMMENT "Download and build CMake ${version} from source"
+        COMMENT "Download CMake ${version}"
     )
-    endif()
     set(${var} ${${var}} PARENT_SCOPE)
 endfunction()
 
@@ -690,24 +673,30 @@ ci_get_cmake(4.0.0  CMAKE_4_0_0_BINARY)
 
 # the tests require CMake 3.13 or later, so they are excluded for CMake 3.5.0
 set(JSON_CMAKE_FLAGS_3_5_0 JSON_Diagnostics JSON_Diagnostic_Positions JSON_GlobalUDLs JSON_ImplicitConversions JSON_DisableEnumSerialization
-    JSON_LegacyDiscardedValueComparison JSON_Install JSON_MultipleHeaders JSON_SystemInclude JSON_Valgrind
+    JSON_LegacyDiscardedValueComparison JSON_Install JSON_MultipleHeaders JSON_SystemInclude JSON_Valgrind)
-    JSON_StrictNulHandling)
+set(JSON_CMAKE_FLAGS_3_31_6 JSON_BuildTests ${JSON_CMAKE_FLAGS_3_31_6})
-set(JSON_CMAKE_FLAGS_3_31_6 JSON_BuildTests ${JSON_CMAKE_FLAGS_3_5_0})
 set(JSON_CMAKE_FLAGS_4_0_0 JSON_BuildTests ${JSON_CMAKE_FLAGS_3_5_0})
 
 function(ci_add_cmake_flags_targets flag min_version)
     string(TOLOWER "ci_cmake_flag_${flag}" flag_target)
     string(REPLACE . _ min_version_var ${min_version})
     set(cmake_binary ${CMAKE_${min_version_var}_BINARY})
+    add_custom_target(${flag_target}_${min_version}_2
+        COMMENT "Check CMake flag ${flag} (CMake ${CMAKE_VERSION})"
+        COMMAND ${CMAKE_COMMAND}
+            -Werror=dev
+            -D${flag}=ON
+            -S${PROJECT_SOURCE_DIR} -B${PROJECT_BINARY_DIR}/build_${flag_target}
+    )
     add_custom_target(${flag_target}_${min_version_var}
-        COMMENT "Check CMake flag ${flag} (CMake ${min_version})"
+        COMMENT "Check CMake flag ${JSON_CMAKE_FLAG} (CMake ${min_version})"
         COMMAND mkdir -pv ${PROJECT_BINARY_DIR}/build_${flag_target}_${min_version_var}
         COMMAND cd ${PROJECT_BINARY_DIR}/build_${flag_target}_${min_version_var}
             && ${cmake_binary} -Werror=dev ${PROJECT_SOURCE_DIR} -D${flag}=ON
         DEPENDS ${cmake_binary}
     )
-    list(APPEND JSON_CMAKE_FLAG_TARGETS ${flag_target}_${min_version_var})
+    list(APPEND JSON_CMAKE_FLAG_TARGETS ${JSON_CMAKE_FLAG_TARGET} ${flag_target}_${min_version_var})
-    list(APPEND JSON_CMAKE_FLAG_BUILD_DIRS ${PROJECT_BINARY_DIR}/build_${flag_target}_${min_version_var})
+    list(APPEND JSON_CMAKE_FLAG_BUILD_DIRS ${PROJECT_BINARY_DIR}/build_${flag_target} ${PROJECT_BINARY_DIR}/build_${flag_target}_${min_version_var})
     set(JSON_CMAKE_FLAG_TARGETS ${JSON_CMAKE_FLAG_TARGETS} PARENT_SCOPE)
     set(JSON_CMAKE_FLAG_BUILD_DIRS ${JSON_CMAKE_FLAG_BUILD_DIRS} PARENT_SCOPE)
 endfunction()
@@ -724,20 +713,6 @@ foreach(JSON_CMAKE_FLAG ${JSON_CMAKE_FLAGS_4_0_0})
     ci_add_cmake_flags_targets(${JSON_CMAKE_FLAG} 4.0.0)
 endforeach()
 
-# check the same flags with the CMake version running this build
-foreach(JSON_CMAKE_FLAG ${JSON_CMAKE_FLAGS_4_0_0})
-    string(TOLOWER "ci_cmake_flag_${JSON_CMAKE_FLAG}" flag_target)
-    add_custom_target(${flag_target}
-        COMMENT "Check CMake flag ${JSON_CMAKE_FLAG} (CMake ${CMAKE_VERSION})"
-        COMMAND ${CMAKE_COMMAND}
-            -Werror=dev
-            -D${JSON_CMAKE_FLAG}=ON
-            -S${PROJECT_SOURCE_DIR} -B${PROJECT_BINARY_DIR}/build_${flag_target}
-    )
-    list(APPEND JSON_CMAKE_FLAG_TARGETS ${flag_target})
-    list(APPEND JSON_CMAKE_FLAG_BUILD_DIRS ${PROJECT_BINARY_DIR}/build_${flag_target})
-endforeach()
-
 add_custom_target(ci_cmake_flags
     DEPENDS ${JSON_CMAKE_FLAG_TARGETS}
     COMMENT "Check CMake flags"
@@ -896,6 +871,6 @@ add_custom_target(ci_test_build_documentation
 ###############################################################################
 
 add_custom_target(ci_clean
-    COMMAND rm -fr ${PROJECT_BINARY_DIR}/build_* ${PROJECT_BINARY_DIR}/cmake-3.5.0 ${PROJECT_BINARY_DIR}/cmake-3.31.6 ${PROJECT_BINARY_DIR}/cmake-4.0.0 ${JSON_CMAKE_FLAG_BUILD_DIRS} ${single_binaries}
+    COMMAND rm -fr ${PROJECT_BINARY_DIR}/build_* cmake-3.5.0-Darwin64 ${JSON_CMAKE_FLAG_BUILD_DIRS} ${single_binaries}
     COMMENT "Clean generated directories"
 )

docs/mkdocs/docs/api/basic_json/merge_patch.md

@@ -37,12 +37,6 @@ Thereby, `Target` is the current object; that is, the patch is applied to the cu
 
 Linear in the lengths of `apply_patch`.
 
-## Notes
-
-`apply_patch` may be `#!cpp *this` itself or refer to a value contained in `#!cpp *this` (for example, a subobject
-returned by `#!cpp (*this)[key]`); it is read as it was when `merge_patch()` was called, before any modification of
-`#!cpp *this`.
-
 ## Examples
 
 ??? example
@@ -67,5 +61,3 @@ returned by `#!cpp (*this)[key]`); it is read as it was when `merge_patch()` was
 ## Version history
 
 - Added in version 3.0.0.
-- Fixed use of freed or relocated memory when `apply_patch` is `#!cpp *this` or refers to a value contained in
-  `#!cpp *this`, in version 3.13.0.

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

@@ -90,7 +90,9 @@ The SAX event lister must follow the interface of [`json_sax`](../json_sax/index
 
 ## Return value
 
-return value of the last processed SAX event
+`#!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)).
 
 ## Exception safety
 
@@ -138,6 +140,7 @@ A UTF-8 byte order mark is silently ignored.
 - Ignoring comments via `ignore_comments` added in version 3.9.0.
 - Added `ignore_trailing_commas` 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/basic_json/update.md

@@ -59,12 +59,6 @@ Basic guarantee: if an exception is thrown during the operation, the JSON value
 1. O(N*log(size() + N)), where N is the number of elements to insert.
 2. O(N*log(size() + N)), where N is the number of elements to insert.
 
-## Notes
-
-The argument `j` (or, for overload (2), the range `[first, last)`) may be `#!cpp *this` itself or refer to a value
-contained in `#!cpp *this` (for example, a subobject returned by `#!cpp (*this)[key]`); it is read as it was when
-`update()` was called, before any modification of `#!cpp *this`.
-
 ## Examples
 
 ??? example
@@ -161,5 +155,3 @@ contained in `#!cpp *this` (for example, a subobject returned by `#!cpp (*this)[
 
 - Added in version 3.0.0.
 - Added `merge_objects` parameter in 3.10.5.
-- Fixed use of freed or relocated memory when the argument is `#!cpp *this` or refers to a value contained in
-  `#!cpp *this`, in version 3.13.0.

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

@@ -7,7 +7,8 @@ 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.
+processing the input; for [`parse_error`](parse_error.md), it decides whether to
+[recover from the error](../../features/parsing/error_recovery.md).
 
 ## Template parameters
 

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

@@ -21,7 +21,14 @@ A parse error occurred.
 
 ## Return value
 
-Whether parsing should proceed (**must return `#!cpp false`**).
+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`.
 
 ## Examples
 
@@ -39,6 +46,22 @@ Whether parsing should proceed (**must return `#!cpp false`**).
     --8<-- "examples/sax_parse.output"
     ```
 
+??? example
+
+    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"
+    ```
+
 ## 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/community/quality_assurance.md

@@ -90,7 +90,7 @@ Note: Some modern features (like C++20 ranges or filesystem support) may be disa
         | GNU 14.2.0                                   | x86_64       | Ubuntu 22.04.1 LTS                | GitHub    |
         | GNU 15.1.0                                   | x86_64       | Ubuntu 22.04.1 LTS                | GitHub    |
         | GNU 16.1.0                                   | x86_64       | Ubuntu 22.04.1 LTS                | GitHub    |
-        | GNU 16.1.0                                   | arm64        | Ubuntu 24.04                      | GitHub    |
+        | GNU 16.1.0                                   | arm64        | Linux 6.1.100                     | Cirrus CI |
         | icpc (ICC) 2021.10.0 20230609                | x86_64       | Ubuntu 22.04 LTS                  | GitHub    |
         | icpx (Intel oneAPI DPC++/C++) 2025.3.2       | x86_64       | Ubuntu 24.04 LTS                  | GitHub    |
         | nvc++ (NVIDIA HPC SDK) 25.5-0                | x86_64       | Ubuntu 22.04 LTS                  | GitHub    |
@@ -132,8 +132,7 @@ Note: Some modern features (like C++20 ranges or filesystem support) may be disa
   [libstdc++](https://gcc.gnu.org/onlinedocs/libstdc++/) to detect subtle differences or incompatibilities.
 - [x] The code checked with [Include What You Use (IWYU)](https://include-what-you-use.org) that all required standard
   headers are included.
-- [x] On Windows, the library is compiled with `<Windows.h>` being included to detect and avoid common bugs (see
+- [x] On Windows, the library is compiled with `<Windows.h>` being included to detect and avoid common bugs.
-  [`unit-windows_h.cpp`](https://github.com/nlohmann/json/blob/develop/tests/src/unit-windows_h.cpp)).
 - [x] The library is compiled with exceptions disabled to support alternative means of error handling.
 
 ## Stable public API

docs/mkdocs/docs/examples/sax_parse__error_recovery.cpp

@@ -0,0 +1,43 @@
+#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

@@ -0,0 +1,19 @@
+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

@@ -0,0 +1,121 @@
+# 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                                                                 | CBOR                                    | ignored                                                                 |
+| simple value other than `false`, `true`, and `null`, like undefined | CBOR                                    | `#!json null`                                                           |
+| negative integer below the range of `number_integer_t`              | CBOR                                    | the nearest floating-point number                                       |
+| string that is not valid UTF-8                                      | BJData, BSON, CBOR, MessagePack, UBJSON | each ill-formed sequence becomes U+FFFD                                 |
+| 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. Note that [`sax_parse`](../../api/basic_json/sax_parse.md) has no parameter for
+CBOR tags, so every tag is an error there; when recovering, tags are ignored like with
+[`cbor_tag_handler_t::ignore`](../../api/basic_json/cbor_tag_handler_t.md).
+
+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

@@ -65,7 +65,7 @@ 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.
+options. To get as much as possible out of malformed input, a SAX parser can [recover from errors](error_recovery.md).
 
 ## See also
 
@@ -76,3 +76,4 @@ options.
 - [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

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

@@ -64,7 +64,8 @@ bool parse_error(std::size_t position,
                  const json::exception& ex);
 ```
 
-The return value indicates whether the parsing should continue, so the function should usually return `#!cpp false`.
+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.
 
 ??? example
 

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

@@ -60,7 +60,8 @@ 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.
+The return value of each function determines whether parsing should proceed. For `parse_error`, returning
+`#!cpp true` [recovers from the error](error_recovery.md).
 
 To implement your own SAX handler, proceed as follows:
 
@@ -68,7 +69,7 @@ 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 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`.
+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`.
 
 ## See also
 

docs/mkdocs/mkdocs.yml

@@ -87,6 +87,7 @@ nav:
       - features/object_order.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/input/json_sax.hpp

@@ -131,7 +131,9 @@ 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 parsing should proceed (must return false)
+    @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
     */
     virtual bool parse_error(std::size_t position,
                              const std::string& last_token,
@@ -187,8 +189,11 @@ 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
 */
-template<typename BasicJsonType, typename InputAdapterType>
+template<typename BasicJsonType, typename InputAdapterType = string_input_adapter_type>
 class json_sax_dom_parser
 {
   public:
@@ -505,7 +510,7 @@ class json_sax_dom_parser
     lexer_t* m_lexer_ref = nullptr;
 };
 
-template<typename BasicJsonType, typename InputAdapterType>
+template<typename BasicJsonType, typename InputAdapterType = string_input_adapter_type>
 class json_sax_dom_callback_parser
 {
   public:

include/nlohmann/detail/input/lexer.hpp

@@ -10,6 +10,7 @@
 
 #include <array> // array
 #include <cstddef> // size_t
+#include <cstdint> // uint8_t
 #include <cstdio> // snprintf
 #include <initializer_list> // initializer_list
 #include <string> // char_traits, string
@@ -437,8 +438,16 @@ class lexer : public lexer_base<BasicJsonType>
                             if (0xD800 <= codepoint1 && codepoint1 <= 0xDBFF)
                             {
                                 // expect next \uxxxx entry
-                                if (JSON_HEDLEY_LIKELY(get() == '\\' && get() == 'u'))
+                                if (JSON_HEDLEY_LIKELY(get() == '\\'))
                                 {
+                                    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))
@@ -463,7 +472,11 @@ 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;
                                     }
                                 }
@@ -477,7 +490,9 @@ 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;
                                 }
                             }
@@ -2130,6 +2145,573 @@ scan_number_done:
         }
     }
 
+    /////////////////////
+    // 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 `\u` 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 `\u` 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));
+        }
+    }
+
   private:
     /// input adapter
     InputAdapterType ia;
@@ -2170,6 +2752,13 @@ 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

@@ -98,7 +98,7 @@ class parser
         if (callback)
         {
             json_sax_dom_callback_parser<BasicJsonType, InputAdapterType> sdp(result, callback, allow_exceptions, &m_lexer);
-            sax_parse_internal(&sdp);
+            sax_parse_internal<false>(&sdp);
 
             if (strict)
             {
@@ -135,7 +135,7 @@ class parser
         else
         {
             json_sax_dom_parser<BasicJsonType, InputAdapterType> sdp(result, allow_exceptions, &m_lexer);
-            sax_parse_internal(&sdp);
+            sax_parse_internal<false>(&sdp);
 
             if (strict)
             {
@@ -173,26 +173,59 @@ class parser
     bool accept(const bool strict = true)
     {
         json_sax_acceptor<BasicJsonType> sax_acceptor;
-        return sax_parse(&sax_acceptor, strict);
+        return sax_parse_impl<false>(&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(sax);
+        const bool result = sax_parse_internal<AllowRecovery>(sax);
 
         if (result)
         {
             if (strict)
             {
-                // strict mode: next byte must be EOF
+                // strict mode: next byte must be EOF; after recovering from an
-                if (get_token() != token_type::end_of_input)
+                // 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)
                 {
-                    return sax->parse_error(m_lexer.get_position(),
+                    // the value is complete, so there is nothing to recover
-                                            m_lexer.get_token_string(),
+                    static_cast<void>(report_error(sax, parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_of_input, "value"), nullptr),
-                                            parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_of_input, "value"), nullptr));
+                                                   std::integral_constant<bool, AllowRecovery> {}));
+                    return false;
                 }
             }
             else
@@ -203,14 +236,23 @@ class parser
             }
         }
 
-        return result;
+        return result && !error_reported;
     }
 
-  private:
+    /*!
-    template<typename SAX>
+    @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>
     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;
@@ -241,12 +283,18 @@ class parser
                             break;
                         }
 
-                        // parse key
+                        // 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)
                         if (JSON_HEDLEY_UNLIKELY(last_token != token_type::value_string))
                         {
-                            return sax->parse_error(m_lexer.get_position(),
+                            if (!continue_after(key_error(sax, allow_recovery, false), skip_to_state_evaluation))
-                                                    m_lexer.get_token_string(),
+                            {
-                                                    parse_error::create(101, m_lexer.get_position(), exception_message(token_type::value_string, "object key"), nullptr));
+                                return false;
+                            }
+                            continue;
                         }
                         if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string())))
                         {
@@ -256,13 +304,12 @@ class parser
                         // parse separator (:)
                         if (JSON_HEDLEY_UNLIKELY(get_token() != token_type::name_separator))
                         {
-                            return sax->parse_error(m_lexer.get_position(),
+                            if (!continue_after(key_error(sax, allow_recovery, true), skip_to_state_evaluation))
-                                                    m_lexer.get_token_string(),
+                            {
-                                                    parse_error::create(101, m_lexer.get_position(), exception_message(token_type::name_separator, "object separator"), nullptr));
+                                return false;
+                            }
+                            continue;
                         }
-
-                        // remember we are now inside an object
-                        states.push_back(false);
 
                         // parse values
                         get_token();
@@ -299,9 +346,11 @@ class parser
 
                         if (JSON_HEDLEY_UNLIKELY(!std::isfinite(res)))
                         {
-                            return sax->parse_error(m_lexer.get_position(),
+                            if (!overflow_error(sax, res, allow_recovery))
-                                                    m_lexer.get_token_string(),
+                            {
-                                                    out_of_range::create(406, concat("number overflow parsing '", m_lexer.get_token_string(), '\''), nullptr));
+                                return false;
+                            }
+                            break;
                         }
 
                         if (JSON_HEDLEY_UNLIKELY(!sax->number_float(res, m_lexer.get_string())))
@@ -369,23 +418,63 @@ class parser
                     case token_type::parse_error:
                     {
                         // using "uninitialized" to avoid an "expected" message
-                        return sax->parse_error(m_lexer.get_position(),
+                        if (!report_error(sax, parse_error::create(101, m_lexer.get_position(), exception_message(token_type::uninitialized, "value"), nullptr), allow_recovery))
-                                                m_lexer.get_token_string(),
+                        {
-                                                parse_error::create(101, m_lexer.get_position(), exception_message(token_type::uninitialized, "value"), nullptr));
+                            return false;
+                        }
+
+                        // recover: keep what can be read of the token
+                        recover_token();
+                        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())
+                            {
+                                return false;
+                            }
+                            continue;
+                        }
+                        // nothing could be read
+                        if (JSON_HEDLEY_UNLIKELY(!sax->null()))
+                        {
+                            return false;
+                        }
+                        break;
                     }
                     case token_type::end_of_input:
                     {
                         if (JSON_HEDLEY_UNLIKELY(m_lexer.get_position().chars_read_total == 1))
                         {
-                            return sax->parse_error(m_lexer.get_position(),
+                            // there is nothing to recover
-                                                    m_lexer.get_token_string(),
+                            static_cast<void>(report_error(sax, parse_error::create(101, m_lexer.get_position(),
-                                                    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));
-                                                            "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
+                            return false;
                         }
 
-                        return sax->parse_error(m_lexer.get_position(),
+                        if (!report_error(sax, parse_error::create(101, m_lexer.get_position(), exception_message(token_type::literal_or_value, "value"), nullptr), allow_recovery))
-                                                m_lexer.get_token_string(),
+                        {
-                                                parse_error::create(101, m_lexer.get_position(), exception_message(token_type::literal_or_value, "value"), nullptr));
+                            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))
+                        {
+                            return false;
+                        }
+                        // the state evaluation reads the token again
+                        m_lexer.unget_token();
+                        skip_to_state_evaluation = true;
+                        continue;
                     }
                     case token_type::uninitialized:
                     case token_type::end_array:
@@ -395,9 +484,35 @@ class parser
                     case token_type::literal_or_value:
                     default: // the last token was unexpected
                     {
-                        return sax->parse_error(m_lexer.get_position(),
+                        if (!report_error(sax, parse_error::create(101, m_lexer.get_position(), exception_message(token_type::literal_or_value, "value"), nullptr), allow_recovery))
-                                                m_lexer.get_token_string(),
+                        {
-                                                parse_error::create(101, m_lexer.get_position(), exception_message(token_type::literal_or_value, "value"), nullptr));
+                            return false;
+                        }
+
+                        // recover
+                        if (states.empty())
+                        {
+                            // look for the value after the garbage
+                            if (!skip_to_value())
+                            {
+                                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))
+                        {
+                            return false;
+                        }
+                        // the state evaluation reads the token again
+                        m_lexer.unget_token();
+                        skip_to_state_evaluation = true;
+                        continue;
                     }
                 }
             }
@@ -447,9 +562,30 @@ class parser
                     continue;
                 }
 
-                return sax->parse_error(m_lexer.get_position(),
+                if (!report_error(sax, parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_array, "array"), nullptr), allow_recovery))
-                                        m_lexer.get_token_string(),
+                {
-                                        parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_array, "array"), nullptr));
+                    return false;
+                }
+
+                // recover
+                if (last_token == token_type::end_of_input)
+                {
+                    // the input ends inside the array
+                    return close_containers(sax, states);
+                }
+                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;
             }
 
             // states.back() is false -> object
@@ -466,11 +602,12 @@ class parser
                     // parse key
                     if (JSON_HEDLEY_UNLIKELY(last_token != token_type::value_string))
                     {
-                        return sax->parse_error(m_lexer.get_position(),
+                        if (!continue_after(key_error(sax, allow_recovery, false), skip_to_state_evaluation))
-                                                m_lexer.get_token_string(),
+                        {
-                                                parse_error::create(101, m_lexer.get_position(), exception_message(token_type::value_string, "object key"), nullptr));
+                            return false;
+                        }
+                        continue;
                     }
-
                     if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string())))
                     {
                         return false;
@@ -479,9 +616,11 @@ class parser
                     // parse separator (:)
                     if (JSON_HEDLEY_UNLIKELY(get_token() != token_type::name_separator))
                     {
-                        return sax->parse_error(m_lexer.get_position(),
+                        if (!continue_after(key_error(sax, allow_recovery, true), skip_to_state_evaluation))
-                                                m_lexer.get_token_string(),
+                        {
-                                                parse_error::create(101, m_lexer.get_position(), exception_message(token_type::name_separator, "object separator"), nullptr));
+                            return false;
+                        }
+                        continue;
                     }
 
                     // parse values
@@ -508,10 +647,477 @@ class parser
                 continue;
             }
 
-            return sax->parse_error(m_lexer.get_position(),
+            if (!report_error(sax, parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_object, "object"), nullptr), allow_recovery))
-                                    m_lexer.get_token_string(),
+            {
-                                    parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_object, "object"), nullptr));
+                return false;
             }
+
+            // recover
+            if (last_token == token_type::end_of_input)
+            {
+                // the input ends inside the object
+                return close_containers(sax, states);
+            }
+            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;
+            }
+        }
+    }
+
+    /*!
+    @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
+    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, typename AllowRecovery>
+    bool overflow_error(SAX* sax, const number_float_t value, AllowRecovery 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());
+    }
+
+    /*!
+    @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>
+    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>
+    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;
+    }
+
+    /// pass the end events of all open containers
+    template<typename SAX>
+    bool close_containers(SAX* sax, std::vector<bool>& states)
+    {
+        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;
+    }
+
+    /*!
+    @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()
+    {
+        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)
+    {
+        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>
+    std::false_type recover_member(SAX* /*sax*/, std::false_type /*allow_recovery*/) const noexcept
+    {
+        return {};
     }
 
     /// get next token from lexer
@@ -560,6 +1166,12 @@ 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/string_utils.hpp

@@ -12,6 +12,7 @@
 #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>
@@ -133,5 +134,78 @@ inline bool is_valid_utf8(const StringType& s, const std::size_t first = 0) noex
     return state == UTF8_ACCEPT;
 }
 
+/*!
+@brief append U+FFFD REPLACEMENT CHARACTER, encoded in UTF-8
+@param[in,out] s  the string to append to
+*/
+template<typename StringType>
+inline void append_replacement_character(StringType& s)
+{
+    s.push_back(static_cast<typename StringType::value_type>(0xEFu));
+    s.push_back(static_cast<typename StringType::value_type>(0xBFu));
+    s.push_back(static_cast<typename StringType::value_type>(0xBDu));
+}
+
+/*!
+@brief replace ill-formed UTF-8 with U+FFFD REPLACEMENT CHARACTER
+
+Each maximal subpart of an ill-formed sequence becomes one U+FFFD, as the
+Unicode Standard recommends (Section 3.9, "U+FFFD Substitution of Maximal
+Subparts"), and as the parser for JSON text does when it recovers from errors.
+
+@param[in,out] s  the string to repair
+@param[in] first  index of the first byte to repair; the bytes before it are
+                  assumed to be valid UTF-8 that ends on a code point boundary
+*/
+template<typename StringType>
+inline void replace_invalid_utf8(StringType& s, const std::size_t first = 0)
+{
+    StringType result = s;
+    result.resize(first);
+
+    std::uint8_t state = UTF8_ACCEPT;
+    std::uint32_t codepoint = 0;
+    // the first byte of the sequence being decoded
+    std::size_t sequence_start = first;
+
+    std::size_t i = first;
+    while (i < s.size())
+    {
+        switch (decode(state, codepoint, static_cast<std::uint8_t>(s[i])))
+        {
+            case UTF8_ACCEPT:
+                for (++i; sequence_start < i; ++sequence_start)
+                {
+                    result.push_back(s[sequence_start]);
+                }
+                break;
+
+            case UTF8_REJECT:
+                append_replacement_character(result);
+                // the byte that made the sequence ill-formed begins the next
+                // one, unless it began this one
+                if (i == sequence_start)
+                {
+                    ++i;
+                }
+                state = UTF8_ACCEPT;
+                sequence_start = i;
+                break;
+
+            default: // in the middle of a sequence
+                ++i;
+                break;
+        }
+    }
+
+    // a sequence that the string ends in the middle of
+    if (state != UTF8_ACCEPT)
+    {
+        append_replacement_character(result);
+    }
+
+    s = std::move(result);
+}
+
 }  // namespace detail
 NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/json.hpp

@@ -29,9 +29,7 @@
 #endif
 
 #include <algorithm> // all_of, find, for_each, none_of
-#include <cmath> // isnan
 #include <cstddef> // nullptr_t, ptrdiff_t, size_t
-#include <cstdint> // uint8_t
 #include <functional> // hash, less
 #include <initializer_list> // initializer_list
 #ifndef JSON_NO_IO
@@ -40,28 +38,19 @@
 #include <iterator> // make_move_iterator, random_access_iterator_tag
 #include <limits> // numeric_limits
 #include <memory> // unique_ptr
-#include <set> // swap, operator!=
 #include <stdexcept> // length_error
 #include <string> // string, stoi, to_string
-#include <type_traits> // enable_if_t, is_same, is_scalar, ...
-#include <unordered_map> // swap (for the from_json(..., std::unordered_map&) overload)
 #include <utility> // declval, forward, move, pair, swap
 #include <vector> // vector
 
-// keep: json.hpp's own basic_json<> default template arguments need the complete definition of
+#include <nlohmann/adl_serializer.hpp>
-// each of these, not only the forward declarations from json_fwd.hpp, so IWYU's suggestion to
-// drop them (nothing in this file otherwise names the type) would break every downstream
-// translation unit that relies on basic_json<>'s defaults actually being usable.
-#include <nlohmann/adl_serializer.hpp> // IWYU pragma: keep
 #include <nlohmann/byte_container_with_subtype.hpp>
-#include <nlohmann/detail/abi_macros.hpp>
+#include <nlohmann/detail/conversions/from_json.hpp>
-#include <nlohmann/detail/conversions/from_json.hpp> // IWYU pragma: keep
+#include <nlohmann/detail/conversions/to_json.hpp>
-#include <nlohmann/detail/conversions/to_json.hpp> // IWYU pragma: keep
 #include <nlohmann/detail/exceptions.hpp>
 #include <nlohmann/detail/hash.hpp>
 #include <nlohmann/detail/input/binary_reader.hpp>
 #include <nlohmann/detail/input/input_adapters.hpp>
-#include <nlohmann/detail/input/json_sax.hpp>
 #include <nlohmann/detail/input/lexer.hpp>
 #include <nlohmann/detail/input/parser.hpp>
 #include <nlohmann/detail/iterators/internal_iterator.hpp>
@@ -73,7 +62,6 @@
 #include <nlohmann/detail/json_pointer.hpp>
 #include <nlohmann/detail/json_ref.hpp>
 #include <nlohmann/detail/macro_scope.hpp>
-#include <nlohmann/detail/meta/detected.hpp>
 #include <nlohmann/detail/string_concat.hpp>
 #include <nlohmann/detail/string_escape.hpp>
 #include <nlohmann/detail/string_utils.hpp>
@@ -85,8 +73,7 @@
 #include <nlohmann/detail/recursion_depth_limit.hpp>
 #include <nlohmann/detail/value_t.hpp>
 #include <nlohmann/json_fwd.hpp>
-#include <nlohmann/ordered_map.hpp> // IWYU pragma: keep
+#include <nlohmann/ordered_map.hpp>
-#include <nlohmann/thirdparty/hedley/hedley.hpp>
 
 #if defined(JSON_HAS_CPP_17)
     #if JSON_HAS_STATIC_RTTI
@@ -158,7 +145,7 @@ 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>
+    template<typename BasicJsonType, typename InputType, typename SAX, bool AllowRecovery>
     friend class ::nlohmann::detail::binary_reader;
     template<typename BasicJsonType, typename InputAdapterType>
     friend class ::nlohmann::detail::json_sax_dom_parser;
@@ -4415,26 +4402,25 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     /// @sa https://json.nlohmann.me/api/basic_json/update/
     void update(const_reference j, bool merge_objects = false)
     {
-        prepare_update();
+        update(j.begin(), j.end(), merge_objects);
-
-        // passed value must be an object (checked here so a type_error names
-        // j, not the copy made below)
-        if (JSON_HEDLEY_UNLIKELY(!j.is_object()))
-        {
-            JSON_THROW(type_error::create(312, detail::concat("cannot use update() with ", j.type_name()), &j));
-        }
-
-        // copy first: j may be *this or one of its descendants, and is
-        // iterated (and moved from) below to update *this
-        basic_json source = j;
-        update_from(source, merge_objects);
     }
 
     /// @brief updates a JSON object from another object, overwriting existing keys
     /// @sa https://json.nlohmann.me/api/basic_json/update/
     void update(const_iterator first, const_iterator last, bool merge_objects = false) // NOLINT(performance-unnecessary-value-param)
     {
-        prepare_update();
+        // implicitly convert a null value to an empty object
+        if (is_null())
+        {
+            m_data.m_type = value_t::object;
+            m_data.m_value.object = create<object_t>();
+            assert_invariant();
+        }
+
+        if (JSON_HEDLEY_UNLIKELY(!is_object()))
+        {
+            JSON_THROW(type_error::create(312, detail::concat("cannot use update() with ", type_name()), this));
+        }
 
         // check if range iterators belong to the same JSON object
         if (JSON_HEDLEY_UNLIKELY(first.m_object != last.m_object))
@@ -4448,11 +4434,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
             JSON_THROW(type_error::create(312, detail::concat("cannot use update() with ", first.m_object->type_name()), first.m_object));
         }
 
-        // copy first: the range may belong to *this or one of its
+        update_members(first, last, merge_objects, 0);
-        // descendants, and is iterated (and moved from) below to update
-        // *this
-        basic_json source(first, last);
-        update_from(source, merge_objects);
     }
 
   private:
@@ -4460,42 +4442,15 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     /// merge_patch_iteratively is merging into, and the members still to merge
     struct merge_frame
     {
-        merge_frame(basic_json* target_, iterator position_, iterator last_) noexcept
+        merge_frame(basic_json* target_, const_iterator position_, const_iterator last_) noexcept
             : target(target_), position(std::move(position_)), last(std::move(last_))
         {}
 
         basic_json* target;
-        iterator position;
+        const_iterator position;
-        iterator last;
+        const_iterator last;
     };
 
-    /// @brief converts a null value to an empty object and checks that this
-    /// value is an object; called first by both @ref update overloads
-    void prepare_update()
-    {
-        // implicitly convert a null value to an empty object; create the
-        // object before setting the type, so a throwing allocation leaves
-        // this value null
-        if (is_null())
-        {
-            m_data.m_value.object = create<object_t>();
-            m_data.m_type = value_t::object;
-            assert_invariant();
-        }
-
-        if (JSON_HEDLEY_UNLIKELY(!is_object()))
-        {
-            JSON_THROW(type_error::create(312, detail::concat("cannot use update() with ", type_name()), this));
-        }
-    }
-
-    /// @brief starts the @ref update_members loop over an already-copied @a
-    /// source; called by both @ref update overloads
-    void update_from(basic_json& source, const bool merge_objects)
-    {
-        update_members(source.begin(), source.end(), merge_objects, 0);
-    }
-
     /*!
     @brief the members loop of @ref update, for this object and range
 
@@ -4508,7 +4463,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     @param[in] depth  nesting level of this object, counted from the object
                       @ref update was called on
     */
-    void update_members(const iterator& first, const iterator& last, const bool merge_objects, const std::size_t depth)
+    void update_members(const const_iterator& first, const const_iterator& last, const bool merge_objects, const std::size_t depth)
     {
         if (JSON_HEDLEY_UNLIKELY(depth >= detail::recursion_depth_limit()))
         {
@@ -4526,13 +4481,13 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
                 // are overwritten as usual" behavior (see #5402).
                 if (it2 != m_data.m_value.object->end() && it2->second.is_object())
                 {
-                    it2->second.update_members(it.value().begin(), it.value().end(), true, depth + 1);
+                    it2->second.update_members(it.value().cbegin(), it.value().cend(), true, depth + 1);
                     continue;
                 }
             }
             // set_parent() also repairs the other members, which ordered_json
             // relocates when adding a key makes its vector grow
-            set_parent(m_data.m_value.object->operator[](it.key()) = std::move(it.value()));
+            set_parent(m_data.m_value.object->operator[](it.key()) = it.value());
         }
     }
 
@@ -4546,7 +4501,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     version. Only reached for values nested deeper than @ref
     detail::recursion_depth_limit.
     */
-    void update_members_iteratively(iterator first, iterator last)
+    void update_members_iteratively(const_iterator first, const_iterator last)
     {
         std::vector<merge_frame> stack;
 
@@ -4573,18 +4528,18 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
                 const auto it2 = target->m_data.m_value.object->find(first.key());
                 if (it2 != target->m_data.m_value.object->end() && it2->second.is_object())
                 {
-                    basic_json& source = first.value();
+                    const basic_json& source = first.value();
                     ++first;
                     stack.emplace_back(target, first, last);
                     target = &it2->second;
-                    first = source.begin();
+                    first = source.cbegin();
-                    last = source.end();
+                    last = source.cend();
                     continue;
                 }
             }
             // set_parent() also repairs the other members, which ordered_json
             // relocates when adding a key makes its vector grow
-            target->set_parent(target->m_data.m_value.object->operator[](first.key()) = std::move(first.value()));
+            target->set_parent(target->m_data.m_value.object->operator[](first.key()) = first.value());
             ++first;
         }
     }
@@ -5264,7 +5219,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         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>(std::move(ia), format).sax_parse(sax, strict);
+               : detail::binary_reader<basic_json, decltype(ia), SAX, true>(std::move(ia), format).sax_parse(sax, strict);
     }
 
     /// @brief generate SAX events (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -5281,7 +5236,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         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>(std::move(ia), format).sax_parse(sax, strict);
+               : detail::binary_reader<basic_json, decltype(ia), SAX, true>(std::move(ia), format).sax_parse(sax, strict);
     }
 
     /// @brief generate SAX events
@@ -5303,7 +5258,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
                // 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>(std::move(ia), format).sax_parse(sax, strict);
+               : detail::binary_reader<basic_json, decltype(ia), SAX, true>(std::move(ia), format).sax_parse(sax, strict);
     }
 #ifndef JSON_NO_IO
     /// @brief deserialize from stream
@@ -6593,10 +6548,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     /// @sa https://json.nlohmann.me/api/basic_json/merge_patch/
     void merge_patch(const basic_json& apply_patch)
     {
-        // copy first: apply_patch may be *this or one of its descendants,
+        apply_merge_patch(apply_patch, 0);
-        // and is iterated (and moved from) below to patch *this
-        basic_json patch = apply_patch;
-        apply_merge_patch(patch, 0);
     }
 
   private:
@@ -6609,7 +6561,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     detail::recursion_depth_limit levels have been entered, @ref
     merge_patch_iteratively applies what is left without the call stack.
     */
-    void apply_merge_patch(basic_json& apply_patch, const std::size_t depth)
+    void apply_merge_patch(const basic_json& apply_patch, const std::size_t depth)
     {
         if (apply_patch.is_object())
         {
@@ -6637,7 +6589,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         }
         else
         {
-            *this = std::move(apply_patch);
+            *this = apply_patch;
         }
     }
 
@@ -6650,12 +6602,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     recursive version. Only reached for patches nested deeper than @ref
     detail::recursion_depth_limit.
     */
-    void merge_patch_iteratively(basic_json& apply_patch)
+    void merge_patch_iteratively(const basic_json& apply_patch)
     {
         std::vector<merge_frame> stack;
 
         // patch `target` with `patch`, or start patching it member by member
-        const auto apply = [&stack](basic_json & target, basic_json & patch)
+        const auto apply = [&stack](basic_json & target, const basic_json & patch)
         {
             if (patch.is_object())
             {
@@ -6663,11 +6615,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
                 {
                     target = basic_json::object();
                 }
-                stack.emplace_back(&target, patch.begin(), patch.end());
+                stack.emplace_back(&target, patch.cbegin(), patch.cend());
             }
             else
             {
-                target = std::move(patch);
+                target = patch;
             }
         };
 
@@ -6683,7 +6635,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
                 continue;
             }
 
-            const iterator member = frame.position;
+            const const_iterator member = frame.position;
             ++stack.back().position;
             if (member.value().is_null())
             {
@@ -6850,10 +6802,7 @@ struct formatter<nlohmann::NLOHMANN_BASIC_JSON_TPL, char> // NOLINT(cert-dcl58-c
 
 }  // namespace std
 
-// keep: undoes the macros defined via detail/macro_scope.hpp at the top of this file; removing it
+#include <nlohmann/detail/macro_unscope.hpp>
-// (nothing in this file *uses* a symbol from it) would leak JSON_* macros into every translation
-// unit that includes this header.
-#include <nlohmann/detail/macro_unscope.hpp> // IWYU pragma: keep
 
 // End of GCC diagnostic pragmas for C++ modules support
 #if defined(__GNUC__) && !defined(__clang__) && __cplusplus >= 202002L

include/nlohmann/json_fwd.hpp

@@ -11,7 +11,8 @@
 
 #include <cstdint> // int64_t, uint64_t
 #include <map> // map
-#include <string> // allocator, string
+#include <memory> // allocator
+#include <string> // string
 #include <vector> // vector
 
 #include <nlohmann/detail/abi_macros.hpp>
@@ -31,7 +32,7 @@ This serializer ignores the template arguments and uses ADL
 for serialization.
 */
 template<typename T = void, typename SFINAE = void>
-struct adl_serializer; // IWYU pragma: keep
+struct adl_serializer;
 
 /// a class to store JSON values
 /// @sa https://json.nlohmann.me/api/basic_json/
@@ -47,12 +48,12 @@ template<template<typename U, typename V, typename... Args> class ObjectType =
          adl_serializer,
          class BinaryType = std::vector<std::uint8_t>, // cppcheck-suppress syntaxError
          class CustomBaseClass = void>
-class basic_json; // IWYU pragma: keep
+class basic_json;
 
 /// @brief JSON Pointer defines a string syntax for identifying a specific value within a JSON document
 /// @sa https://json.nlohmann.me/api/json_pointer/
 template<typename RefStringType>
-class json_pointer; // IWYU pragma: keep
+class json_pointer;
 
 /*!
 @brief default specialization
@@ -63,7 +64,7 @@ using json = basic_json<>;
 /// @brief a minimal map-like container that preserves insertion order
 /// @sa https://json.nlohmann.me/api/ordered_map/
 template<class Key, class T, class IgnoredLess, class Allocator>
-struct ordered_map; // IWYU pragma: keep
+struct ordered_map;
 
 /// @brief specialization that maintains the insertion order of object keys
 /// @sa https://json.nlohmann.me/api/ordered_json/

include/nlohmann/ordered_map.hpp

@@ -12,14 +12,13 @@
 #include <functional> // equal_to, less
 #include <initializer_list> // initializer_list
 #include <iterator> // input_iterator_tag, iterator_traits
-#include <new> // for operator new (placement new)
+#include <memory> // allocator
 #include <stdexcept> // for out_of_range
 #include <tuple> // forward_as_tuple
 #include <type_traits> // enable_if, integral_constant, is_convertible, is_nothrow_move_constructible
 #include <utility> // forward, move, pair, piecewise_construct
-#include <vector> // vector, allocator
+#include <vector> // vector
 
-#include <nlohmann/detail/abi_macros.hpp>
 #include <nlohmann/detail/macro_scope.hpp>
 #include <nlohmann/detail/meta/type_traits.hpp>
 

single_include/nlohmann/json_fwd.hpp

@@ -11,7 +11,8 @@
 
 #include <cstdint> // int64_t, uint64_t
 #include <map> // map
-#include <string> // allocator, string
+#include <memory> // allocator
+#include <string> // string
 #include <vector> // vector
 
 // #include <nlohmann/detail/abi_macros.hpp>
@@ -176,7 +177,7 @@ This serializer ignores the template arguments and uses ADL
 for serialization.
 */
 template<typename T = void, typename SFINAE = void>
-struct adl_serializer; // IWYU pragma: keep
+struct adl_serializer;
 
 /// a class to store JSON values
 /// @sa https://json.nlohmann.me/api/basic_json/
@@ -192,12 +193,12 @@ template<template<typename U, typename V, typename... Args> class ObjectType =
          adl_serializer,
          class BinaryType = std::vector<std::uint8_t>, // cppcheck-suppress syntaxError
          class CustomBaseClass = void>
-class basic_json; // IWYU pragma: keep
+class basic_json;
 
 /// @brief JSON Pointer defines a string syntax for identifying a specific value within a JSON document
 /// @sa https://json.nlohmann.me/api/json_pointer/
 template<typename RefStringType>
-class json_pointer; // IWYU pragma: keep
+class json_pointer;
 
 /*!
 @brief default specialization
@@ -208,7 +209,7 @@ using json = basic_json<>;
 /// @brief a minimal map-like container that preserves insertion order
 /// @sa https://json.nlohmann.me/api/ordered_map/
 template<class Key, class T, class IgnoredLess, class Allocator>
-struct ordered_map; // IWYU pragma: keep
+struct ordered_map;
 
 /// @brief specialization that maintains the insertion order of object keys
 /// @sa https://json.nlohmann.me/api/ordered_json/

src/modules/json.cppm

@@ -47,6 +47,7 @@ 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/src/fuzzer-parse_bjdata.cpp

@@ -45,6 +45,10 @@ 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.
 */
@@ -59,6 +63,8 @@ drivers.
     #error "the fuzzer drivers must be built without NDEBUG"
 #endif
 
+#include "fuzzer-recovering_checker.hpp"
+
 using json = nlohmann::json;
 
 // value-stable comparison for the round-trip checks below; see the note
@@ -71,11 +77,15 @@ 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)
 {
+    // step 0: 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;
+
     try
     {
         // step 1: parse input
         std::vector<uint8_t> const vec1(data, data + size);
         json const j1 = json::from_bjdata(vec1);
+        assert(recovered_without_errors);
 
         try
         {
@@ -109,6 +119,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::parse_error&)
     {
         // parse errors are ok, because input may be random bytes
+        assert(!recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -117,6 +128,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::out_of_range&)
     {
         // out of range errors may happen if provided sizes are excessive
+        assert(!recovered_without_errors);
     }
 
     // return 0 - non-zero return values are reserved for future use

tests/src/fuzzer-parse_bon8.cpp

@@ -19,6 +19,10 @@ 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.
 */
@@ -33,6 +37,8 @@ drivers.
     #error "the fuzzer drivers must be built without NDEBUG"
 #endif
 
+#include "fuzzer-recovering_checker.hpp"
+
 using json = nlohmann::json;
 
 namespace
@@ -56,6 +62,9 @@ std::string read_bon8(InputType&& input)
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
+    // step 0: 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));
@@ -67,6 +76,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
         // step 1: parse input
         std::vector<uint8_t> const vec1(data, data + size);
         json const j1 = json::from_bon8(vec1);
+        assert(recovered_without_errors);
 
         try
         {
@@ -88,6 +98,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::parse_error&)
     {
         // parse errors are ok, because input may be random bytes
+        assert(!recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -96,6 +107,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::out_of_range&)
     {
         // out of range errors may happen if provided sizes are excessive
+        assert(!recovered_without_errors);
     }
 
     // return 0 - non-zero return values are reserved for future use

tests/src/fuzzer-parse_bson.cpp

@@ -15,6 +15,10 @@ array data, it performs the following steps:
 - j2 = from_bson(vec)
 - assert(j1 == j2)
 
+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.
 */
@@ -29,16 +33,22 @@ drivers.
     #error "the fuzzer drivers must be built without NDEBUG"
 #endif
 
+#include "fuzzer-recovering_checker.hpp"
+
 using json = nlohmann::json;
 
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
+    // step 0: 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;
+
     try
     {
         // step 1: parse input
         std::vector<uint8_t> const vec1(data, data + size);
         json const j1 = json::from_bson(vec1);
+        assert(recovered_without_errors);
 
         if (j1.is_discarded())
         {
@@ -65,6 +75,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::parse_error&)
     {
         // parse errors are ok, because input may be random bytes
+        assert(!recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -73,6 +84,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::out_of_range&)
     {
         // out of range errors can occur during parsing, too
+        assert(!recovered_without_errors);
     }
 
     // return 0 - non-zero return values are reserved for future use

tests/src/fuzzer-parse_cbor.cpp

@@ -15,6 +15,10 @@ array data, it performs the following steps:
 - j2 = from_cbor(vec)
 - assert(j1 == j2)
 
+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.
 */
@@ -29,16 +33,22 @@ drivers.
     #error "the fuzzer drivers must be built without NDEBUG"
 #endif
 
+#include "fuzzer-recovering_checker.hpp"
+
 using json = nlohmann::json;
 
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
+    // step 0: 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;
+
     try
     {
         // step 1: parse input
         std::vector<uint8_t> const vec1(data, data + size);
         json const j1 = json::from_cbor(vec1);
+        assert(recovered_without_errors);
 
         try
         {
@@ -60,6 +70,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::parse_error&)
     {
         // parse errors are ok, because input may be random bytes
+        assert(!recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -68,6 +79,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::out_of_range&)
     {
         // out of range errors can occur during parsing, too
+        assert(!recovered_without_errors);
     }
 
     // return 0 - non-zero return values are reserved for future use

tests/src/fuzzer-parse_json.cpp

@@ -16,6 +16,10 @@ 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.
 */
@@ -23,6 +27,7 @@ drivers.
 #include <cassert>
 #include <iostream>
 #include <sstream>
+#include <string>
 #include <nlohmann/json.hpp>
 
 // the round-trip checks below are assertions; NDEBUG would compile them away
@@ -30,11 +35,20 @@ drivers.
     #error "the fuzzer drivers must be built without NDEBUG"
 #endif
 
+#include "fuzzer-recovering_checker.hpp"
+
 using json = nlohmann::json;
 
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
+    // step 0: 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));
+    }
+
     try
     {
         // step 1: parse input

tests/src/fuzzer-parse_msgpack.cpp

@@ -15,6 +15,10 @@ array data, it performs the following steps:
 - j2 = from_msgpack(vec)
 - assert(j1 == j2)
 
+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.
 */
@@ -29,16 +33,22 @@ drivers.
     #error "the fuzzer drivers must be built without NDEBUG"
 #endif
 
+#include "fuzzer-recovering_checker.hpp"
+
 using json = nlohmann::json;
 
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
+    // step 0: 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;
+
     try
     {
         // step 1: parse input
         std::vector<uint8_t> const vec1(data, data + size);
         json const j1 = json::from_msgpack(vec1);
+        assert(recovered_without_errors);
 
         try
         {
@@ -60,6 +70,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::parse_error&)
     {
         // parse errors are ok, because input may be random bytes
+        assert(!recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -68,6 +79,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::out_of_range&)
     {
         // out of range errors may happen if provided sizes are excessive
+        assert(!recovered_without_errors);
     }
 
     // return 0 - non-zero return values are reserved for future use

tests/src/fuzzer-parse_ubjson.cpp

@@ -24,6 +24,10 @@ 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.
 */
@@ -38,16 +42,22 @@ drivers.
     #error "the fuzzer drivers must be built without NDEBUG"
 #endif
 
+#include "fuzzer-recovering_checker.hpp"
+
 using json = nlohmann::json;
 
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
+    // step 0: 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;
+
     try
     {
         // step 1: parse input
         std::vector<uint8_t> const vec1(data, data + size);
         json const j1 = json::from_ubjson(vec1);
+        assert(recovered_without_errors);
 
         try
         {
@@ -79,6 +89,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::parse_error&)
     {
         // parse errors are ok, because input may be random bytes
+        assert(!recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -87,6 +98,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::out_of_range&)
     {
         // out of range errors may happen if provided sizes are excessive
+        assert(!recovered_without_errors);
     }
 
     // return 0 - non-zero return values are reserved for future use

tests/src/fuzzer-recovering_checker.hpp

@@ -0,0 +1,154 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  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-alt-string.cpp

@@ -419,6 +419,46 @@ 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("strict enum")
     {
         // regression test for #5667: NLOHMANN_JSON_SERIALIZE_ENUM_STRICT's from_json

tests/src/unit-class_parser.cpp

@@ -143,11 +143,13 @@ class SaxEventLogger
     {
         errored = true;
         events.push_back("parse_error(" + std::to_string(position) + ")");
-        return false;
+        return recover;
     }
 
     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
@@ -2937,3 +2939,583 @@ 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-diagnostics.cpp

@@ -236,31 +236,6 @@ TEST_CASE("Regression tests for extended diagnostics")
         }
     }
 
-    SECTION("Regression test for issue #5641 - parent pointers after update()/merge_patch() with an aliasing argument")
-    {
-        // update()'s and merge_patch()'s argument may be *this or one of its
-        // descendants; the values moved out of the (temporary) copy must end
-        // up with their parent pointing at their new location in *this
-        {
-            json j = {{"a", {{"a", 1}, {"b", 2}}}};
-            j.update(j["a"]);
-            CHECK(j == json({{"a", 1}, {"b", 2}}));
-
-            // Must call operator[] on const element, otherwise m_parent gets updated.
-            auto const& constJ = j;
-            CHECK_THROWS_WITH_AS(constJ["a"].at(0), "[json.exception.type_error.304] (/a) cannot use at() with number", json::type_error);
-        }
-
-        {
-            json j = {{"a", {{"a", nullptr}, {"b", 2}}}};
-            j.merge_patch(j["a"]);
-            CHECK(j == json({{"b", 2}}));
-
-            auto const& constJ = j;
-            CHECK_THROWS_WITH_AS(constJ["b"].at(0), "[json.exception.type_error.304] (/b) cannot use at() with number", json::type_error);
-        }
-    }
-
     SECTION("Regression test for issue #3032 - Yet another assertion failure when inserting into arrays with JSON_DIAGNOSTICS set")
     {
         // reference operator[](size_type idx)

tests/src/unit-merge_patch.cpp

@@ -374,52 +374,3 @@ TEST_CASE("JSON Merge Patch and update on ordered_json")
         CHECK(target == ordered_json::parse(R"({"a": 1, "e": {"y": 5}, "g": 6})"));
     }
 }
-
-TEST_CASE("merge_patch() with an argument that aliases *this (#5641)")
-{
-    SECTION("j.merge_patch(j): erasing a member destroys the node the loop's iterator points to")
-    {
-        // reproduces issue #5641, case 1
-        json j = {{"a", nullptr}, {"b", 1}};
-        j.merge_patch(j);
-        CHECK(j == json({{"b", 1}}));
-    }
-
-    SECTION("j.merge_patch(j[\"a\"]): removing \"a\" destroys the patch while it is iterated")
-    {
-        // reproduces issue #5641, case 2
-        json j = {{"a", {{"a", nullptr}, {"b", 2}}}};
-        j.merge_patch(j["a"]);
-        CHECK(j == json({{"b", 2}}));
-    }
-
-    SECTION("a patch nested past the iterative descent bound aliases *this")
-    {
-        // every depth on either side of where the iterative version takes
-        // over (detail::recursion_depth_limit(), 128); patching *this with
-        // itself is idempotent, aliased or not
-        for (const std::size_t depth :
-                {
-                    std::size_t{0}, std::size_t{127}, std::size_t{128}, std::size_t{300}
-                })
-        {
-            CAPTURE(depth);
-            json j = json::parse(nested_objects(depth, 0));
-            const json expected = j;
-            j.merge_patch(j);
-            CHECK(j == expected);
-        }
-    }
-
-    SECTION("ordered_json")
-    {
-        using nlohmann::ordered_json;
-
-        SECTION("merge_patch with a member of *this")
-        {
-            ordered_json j = {{"a", {{"a", nullptr}, {"b", 2}}}};
-            j.merge_patch(j["a"]);
-            CHECK(j == ordered_json({{"b", 2}}));
-        }
-    }
-}

tests/src/unit-modifiers.cpp

@@ -1116,72 +1116,3 @@ TEST_CASE("update() on deeply nested values")
         CHECK(p->at("y") == 2);
     }
 }
-
-TEST_CASE("update() with an argument that aliases *this (#5641)")
-{
-    SECTION("the target is checked before the argument, as before the copy")
-    {
-        json j = 1;
-        CHECK_THROWS_WITH_AS(j.update(json::array()), "[json.exception.type_error.312] cannot use update() with number", json::type_error&);
-        CHECK_THROWS_WITH_AS(j.update(j.cbegin(), j.cend()), "[json.exception.type_error.312] cannot use update() with number", json::type_error&);
-
-        json k;
-        CHECK_THROWS_WITH_AS(k.update(json::array()), "[json.exception.type_error.312] cannot use update() with array", json::type_error&);
-        CHECK(k == json::object());
-    }
-
-    SECTION("const reference")
-    {
-        SECTION("j.update(j[\"a\"]): assigning into the argument's parent destroys it mid-iteration")
-        {
-            // reproduces issue #5641, case 3
-            json j = {{"a", {{"a", 1}, {"b", 2}}}};
-            j.update(j["a"]);
-            CHECK(j == json({{"a", 1}, {"b", 2}}));
-        }
-
-        SECTION("merge_objects with an argument that is a member of *this")
-        {
-            json j = {{"defaults", {{"opts", {{"a", 1}}}}}, {"opts", {{"b", 2}}}};
-            j.update(j["defaults"], true);
-            CHECK(j == json({{"defaults", {{"opts", {{"a", 1}}}}}, {"opts", {{"a", 1}, {"b", 2}}}}));
-        }
-
-        SECTION("ordered_json: inserting a new key relocates the vector behind the argument")
-        {
-            // reproduces issue #5641, case 4
-            using nlohmann::ordered_json;
-            ordered_json j = {{"a", {{"x", 1}, {"y", 2}, {"z", 3}}}};
-            j.update(j["a"]);
-            CHECK(j == ordered_json({{"a", {{"x", 1}, {"y", 2}, {"z", 3}}}, {"x", 1}, {"y", 2}, {"z", 3}}));
-        }
-    }
-
-    SECTION("iterator range")
-    {
-        SECTION("range that is a member of *this")
-        {
-            json j = {{"a", {{"a", 1}, {"b", 2}}}};
-            j.update(j["a"].begin(), j["a"].end());
-            CHECK(j == json({{"a", 1}, {"b", 2}}));
-        }
-    }
-
-    SECTION("nested past the iterative descent bound aliases *this")
-    {
-        // every depth on either side of where the iterative version takes
-        // over (detail::recursion_depth_limit(), 128); merging *this into
-        // itself is idempotent, aliased or not
-        for (const std::size_t depth :
-                {
-                    std::size_t{0}, std::size_t{127}, std::size_t{128}, std::size_t{300}
-                })
-        {
-            CAPTURE(depth);
-            json j = json::parse(nested_objects(depth, 0));
-            const json expected = j;
-            j.update(j, true);
-            CHECK(j == expected);
-        }
-    }
-}

tests/src/unit-regression2.cpp

@@ -898,4 +898,585 @@ TEST_CASE("regression test - excessive binary container size honors allow_except
     CHECK(json::from_cbor(std::vector<std::uint8_t> {0x9b, 0, 0, 0, 0, 0, 0, 0, 0x02}, true, false).is_discarded());
 }
 
+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)
+class RecoveringParser
+{
+  public:
+    explicit RecoveringParser(json& j)
+        : dom(j, false)
+    {}
+
+    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)
+    {
+        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<json> 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;
+            }
+        }
+    }
+
+};
+
+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: ill-formed UTF-8 becomes U+FFFD, also in keys
+            {json::input_format_t::cbor, {0xA1, 0x61, 0xFF, 0x62, 0xC3, 0x28}, {{replacement_character(), replacement_character() + "("}}, 2},
+            // 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},
+            // MessagePack: ill-formed UTF-8 becomes U+FFFD
+            {json::input_format_t::msgpack, {0x92, 0xA2, 0xC3, 0x28, 0xA3, 0xE2, 0x82, 'x'}, {replacement_character() + "(", replacement_character() + "x"}, 2},
+            // 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},
+            // 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 negative integer below the range of number_integer_t
+        const auto cbor = parse_binary_recovering({0x3B, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF}, json::input_format_t::cbor);
+        CHECK(cbor.errors == 1);
+        CHECK(cbor.value.is_number_float());
+        CHECK(cbor.value.get<double>() == -18446744073709551616.0);
+
+        // 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}}));
+
+        // 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,]"));
+    }
+}
+
 DOCTEST_CLANG_SUPPRESS_WARNING_POP

tests/src/unit.cpp

@@ -7,22 +7,4 @@
 // SPDX-License-Identifier: MIT
 
 #define DOCTEST_CONFIG_IMPLEMENT_WITH_MAIN
-
-// libc++ annotates std::mutex for Clang's thread safety analysis, so -Weverything
-// reports -Wthread-safety-negative for the locks in doctest's reporters, which are
-// only compiled in this file. __has_warning keeps older Clang versions from
-// reporting an unknown warning group.
-#if defined(__clang__) && defined(__has_warning)
-    #if __has_warning("-Wthread-safety-negative")
-        #pragma clang diagnostic push
-        #pragma clang diagnostic ignored "-Wthread-safety-negative"
-    #endif
-#endif
-
 #include "doctest_compatibility.h"
-
-#if defined(__clang__) && defined(__has_warning)
-    #if __has_warning("-Wthread-safety-negative")
-        #pragma clang diagnostic pop
-    #endif
-#endif

tools/astyle/requirements.txt

@@ -1,4 +1 @@
-# astyle is deliberately pinned: newer versions reformat the code, and this version
-# defines the formatting that `make amalgamate` produces and check_amalgamation.yml enforces.
-# Dependabot is told to ignore it in .github/dependabot.yml.
 astyle==3.4.13