Address review: throw helpers take input_format_t, simpler type checks

- throw_on_discarded() and throw_integer_out_of_range() take an
  input_format_t and call input_format_name() themselves
- has_no_children(), set_parents() and max_size() check array, then
  object, instead of calling is_primitive() first
- parse_impl() chains like accept_impl(); sax_parse_impl() uses if/else
- std::array for the control character messages; negation<> in
  write_object_key(); clarify the is_primitive() comment

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

.github/CONTRIBUTING.md

@@ -108,16 +108,9 @@ The tests are located in [`tests/src/unit-*.cpp`](https://github.com/nlohmann/js
 are structured along the features of the library or the nature of the tests. Usually, it should be clear from the
 context which existing file needs to be extended, and only very few cases require creating new test files.
 
-When fixing a bug, edit `unit-regression3.cpp` and add a section referencing the fixed issue. Tests that need C++17 or
+When fixing a bug, edit `unit-regression3.cpp` and add a section referencing the fixed issue.
-C++20 go into `unit-regression3-cpp17.cpp` or `unit-regression3-cpp20.cpp` instead, so the large file is not rebuilt
+`unit-regression2.cpp` holds the older tests; the two files exist because a single one grew large enough for the
-for every C++ standard. `unit-regression2.cpp` holds the older tests; the two files exist because a single one grew
+MinGW linker to fail relocating it, so please keep adding to the smaller file rather than growing the larger one.
-large enough for the MinGW linker to fail relocating it, so please keep adding to the smaller file rather than growing
-the larger one.
-
-To keep compile times down, several test files are compiled together as one translation unit. This sets a few rules
-for test files, such as giving file-scope helpers file-specific names. See the README in the
-[`tests`](https://github.com/nlohmann/json/tree/develop/tests) folder for how the tests are built and what to keep in
-mind when adding them.
 
 #### Exceptions
 

.github/external_ci/appveyor.yml

@@ -18,7 +18,8 @@ environment:
   matrix:
     # The Visual Studio 2017 jobs compile everything with /std:c++17, so they
     # only build the C++17 variant of each test, split into two jobs each to
-    # stay below AppVeyor's 60-minute limit per job.
+    # stay below AppVeyor's 60-minute limit per job. The Visual Studio 2019
+    # job builds the tests for all standards and is split for the same reason.
     - APPVEYOR_BUILD_WORKER_IMAGE: Visual Studio 2015
       configuration: Debug
       platform: x86
@@ -50,7 +51,13 @@ environment:
       configuration: Release
       platform: x86
       CXX_FLAGS: "/W4 /WX"
-      CMAKE_OPTIONS: "-DJSON_ImplicitConversions=OFF"
+      CMAKE_OPTIONS: "-DJSON_ImplicitConversions=OFF -DJSON_TestShard=0/2"
+      GENERATOR: Visual Studio 16 2019
+    - APPVEYOR_BUILD_WORKER_IMAGE: Visual Studio 2019
+      configuration: Release
+      platform: x86
+      CXX_FLAGS: "/W4 /WX"
+      CMAKE_OPTIONS: "-DJSON_ImplicitConversions=OFF -DJSON_TestShard=1/2"
       GENERATOR: Visual Studio 16 2019
 
     - APPVEYOR_BUILD_WORKER_IMAGE: Visual Studio 2015

.github/labeler.yml

@@ -64,6 +64,7 @@ labels:
     - "tests/src/unit-json_view.*"
     - "tests/src/json_view_test_helpers\\.hpp"
     - "tests/src/fuzzer-(parse_json_view|json_view_image)\\.cpp"
+    - "tests/benchmarks/json_view/.*"
     - "tools/amalgamate/config_json_view\\.json"
     - "docs/mkdocs/docs/features/json_view\\.md"
     - "docs/mkdocs/docs/api/basic_json_(document|view)/.*"

.github/workflows/check_amalgamation.yml

@@ -154,6 +154,28 @@ jobs:
           # PR content in a job without credentials.
           python3 tools/generate_natvis/generate_natvis.py $MAIN_DIR
 
+      - name: Check the nlohmann_json.natvis generator options
+        run: |
+          cd $MAIN_DIR
+          # The options for configurations outside the checked-in file write
+          # to a temporary file, so they do not affect the diff below.
+          GENERATOR=tools/generate_natvis/generate_natvis.py
+          python3 $GENERATOR --list-tags
+          TAG_COUNT=$(python3 $GENERATOR --list-tags | wc -l)
+
+          python3 $GENERATOR --abi-tags diag,_dp,_vns --abi-tags _diag --output $RUNNER_TEMP/abi_tags.natvis
+          grep -q '<!-- Namespace nlohmann::json_abi_diag_dp_vns -->' $RUNNER_TEMP/abi_tags.natvis
+          grep -q '<!-- Namespace nlohmann::json_abi_diag_dp_vns_v[0-9_]* -->' $RUNNER_TEMP/abi_tags.natvis
+          test $(grep -c '<!-- Namespace ' $RUNNER_TEMP/abi_tags.natvis) -eq $(( $(grep -c '<!-- Namespace ' nlohmann_json.natvis) + 2 ))
+
+          python3 $GENERATOR --all --output $RUNNER_TEMP/all.natvis
+          test $(grep -c '<!-- Namespace ' $RUNNER_TEMP/all.natvis) -eq $(( (1 << TAG_COUNT) * 2 + 1 ))
+
+          if python3 $GENERATOR --abi-tags _unknown --output $RUNNER_TEMP/unknown.natvis; then
+            echo "generate_natvis.py accepted an unknown ABI tag"
+            exit 1
+          fi
+
       - name: Build patch and check for differences
         id: diff
         run: |

.github/workflows/codeql-analysis.yml

@@ -38,14 +38,14 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@24c54180a607b1449ed407dd24f251e4e9147c8d # v4.38.3
+      uses: github/codeql-action/init@6f2ac81f5cd81fe351a197ba0b00d91d03cd2aee # v4.39.0
       with:
         languages: c-cpp
 
     # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
-      uses: github/codeql-action/autobuild@24c54180a607b1449ed407dd24f251e4e9147c8d # v4.38.3
+      uses: github/codeql-action/autobuild@6f2ac81f5cd81fe351a197ba0b00d91d03cd2aee # v4.39.0
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@24c54180a607b1449ed407dd24f251e4e9147c8d # v4.38.3
+      uses: github/codeql-action/analyze@6f2ac81f5cd81fe351a197ba0b00d91d03cd2aee # v4.39.0

.github/workflows/comment_check_amalgamation.yml

@@ -37,6 +37,14 @@ jobs:
             var matchArtifact = artifacts.data.artifacts.filter((artifact) => {
               return artifact.name == "pr"
             })[0];
+            // a run that failed before its jobs started (e.g. a stale queued
+            // run cancelled long after its push) has no artifact to report on
+            if (!matchArtifact) {
+              core.notice('Run ${{ github.event.workflow_run.id }} has no "pr" artifact; nothing to comment on.');
+              core.setOutput('found', 'false');
+              return;
+            }
+            core.setOutput('found', 'true');
             var download = await github.rest.actions.downloadArtifact({
                owner: context.repo.owner,
                repo: context.repo.repo,
@@ -51,9 +59,11 @@ jobs:
       # Extract the untrusted PR artifact into a dedicated empty directory and
       # read only the two expected files by fixed path afterwards. This avoids a
       # malicious archive overwriting workspace files or escaping via ../ paths.
-      - run: unzip -o pr.zip -d ./pr_artifact
+      - if: steps.download.outputs.found == 'true'
+        run: unzip -o pr.zip -d ./pr_artifact
 
       - name: 'Comment on PR'
+        if: steps.download.outputs.found == 'true'
         uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/flawfinder.yml

@@ -47,6 +47,6 @@ jobs:
           output: 'flawfinder_results.sarif'
 
       - name: Upload analysis results to GitHub Security tab
-        uses: github/codeql-action/upload-sarif@24c54180a607b1449ed407dd24f251e4e9147c8d # v4.38.3
+        uses: github/codeql-action/upload-sarif@6f2ac81f5cd81fe351a197ba0b00d91d03cd2aee # v4.39.0
         with:
           sarif_file: ${{github.workspace}}/flawfinder_results.sarif

.github/workflows/json_view_benchmarks.yml

@@ -0,0 +1,84 @@
+name: "json_view benchmarks"
+
+# On demand only: runs the comparison of json_view with yyjson, simdjson, and
+# Boost.JSON (tests/benchmarks/json_view/compare.py) on GitHub-hosted runners,
+# for numbers from x86-64 and AArch64 Linux. It runs when started by hand, or
+# when a pull request gets the label "benchmark" (on both architectures, with
+# GCC and the default settings). Shared runners are noisy: the results show
+# where json_view stands, but published numbers need a quiet machine (see
+# tests/benchmarks/json_view/README.md).
+
+on:
+  pull_request:
+    types: [labeled]
+  workflow_dispatch:
+    inputs:
+      runner:
+        description: "Runner image"
+        type: choice
+        options:
+          - ubuntu-24.04
+          - ubuntu-24.04-arm
+        default: ubuntu-24.04
+      compiler:
+        description: "Compiler"
+        type: choice
+        options:
+          - g++
+          - clang++
+        default: g++
+      native:
+        description: "Compile for the runner's CPU (-march=native)"
+        type: boolean
+        default: false
+      rounds:
+        description: "Rounds of bench_view"
+        type: number
+        default: 30
+
+permissions:
+  contents: read
+
+concurrency:
+  # (the label is part of the group: adding an unrelated label must not cancel a running benchmark)
+  group: json-view-benchmarks-${{ github.workflow }}-${{ github.ref }}-${{ github.event.label.name }}
+  cancel-in-progress: true
+
+jobs:
+  compare:
+    if: github.event_name == 'workflow_dispatch' || github.event.label.name == 'benchmark'
+    strategy:
+      matrix:
+        runner: ${{ fromJSON(github.event_name == 'workflow_dispatch' && format('["{0}"]', inputs.runner) || '["ubuntu-24.04", "ubuntu-24.04-arm"]') }}
+    runs-on: ${{ matrix.runner }}
+    timeout-minutes: 60
+    steps:
+      - name: Harden Runner
+        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
+        with:
+          egress-policy: audit
+
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+
+      - name: Download test data
+        run: |
+          cmake -S . -B build -DJSON_BuildTests=On
+          cmake --build build --target download_test_data
+
+      - name: Run the comparison
+        env:
+          CXX: ${{ inputs.compiler || 'g++' }}
+          CC: ${{ inputs.compiler == 'clang++' && 'clang' || 'gcc' }}
+          ROUNDS: ${{ inputs.rounds || 30 }}
+          NATIVE: ${{ inputs.native && '--native' || '' }}
+        run: python3 tests/benchmarks/json_view/compare.py --data build/test_files --download --rounds "$ROUNDS" $NATIVE
+
+      - name: Summary
+        run: cat tests/benchmarks/json_view/results/*.md >> "$GITHUB_STEP_SUMMARY"
+
+      - uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7.0.2
+        with:
+          name: json_view-benchmarks-${{ matrix.runner }}-${{ inputs.compiler || 'g++' }}
+          path: tests/benchmarks/json_view/results/

.github/workflows/scorecards.yml

@@ -80,6 +80,6 @@ jobs:
 
       # Upload the results to GitHub's code scanning dashboard.
       - name: "Upload to code-scanning"
-        uses: github/codeql-action/upload-sarif@24c54180a607b1449ed407dd24f251e4e9147c8d # v4.38.3
+        uses: github/codeql-action/upload-sarif@6f2ac81f5cd81fe351a197ba0b00d91d03cd2aee # v4.39.0
         with:
           sarif_file: results.sarif

.github/workflows/semgrep.yml

@@ -65,7 +65,7 @@ jobs:
 
       # Upload SARIF file generated in previous step
       - name: Upload SARIF file
-        uses: github/codeql-action/upload-sarif@24c54180a607b1449ed407dd24f251e4e9147c8d # v4.38.3
+        uses: github/codeql-action/upload-sarif@6f2ac81f5cd81fe351a197ba0b00d91d03cd2aee # v4.39.0
         with:
           sarif_file: semgrep.sarif
         if: always()

BUILD.bazel

@@ -37,6 +37,7 @@ cc_library(
         "include/nlohmann/detail/input/parser.hpp",
         "include/nlohmann/detail/input/position_t.hpp",
         "include/nlohmann/detail/input/pow5_table.hpp",
+        "include/nlohmann/detail/input/simd_scan.hpp",
         "include/nlohmann/detail/input/string_scan.hpp",
         "include/nlohmann/detail/iterators/internal_iterator.hpp",
         "include/nlohmann/detail/iterators/iter_impl.hpp",

FILES.md

@@ -6,6 +6,7 @@ This file describes the source for supporting files; that is, files that are not
 - [GitHub](#github)
 - [REUSE](#reuse)
 - [Package Managers](#package-managers)
+- [Debugging](#debugging)
 
 ## Continuous Integration
 
@@ -289,3 +290,29 @@ The module definition for [Bazel](https://bazel.build)'s [Bzlmod](https://bazel.
 Further documentation:
 
 - [Bazel modules](https://bazel.build/external/module)
+
+## Debugging
+
+### `nlohmann_json.natvis`
+
+The [Natvis](https://learn.microsoft.com/en-us/visualstudio/debugger/create-custom-views-of-native-objects) file that
+gives `json` values a friendly view in the Visual Studio debugger. The file is generated by
+`tools/generate_natvis/generate_natvis.py` from the template `tools/generate_natvis/nlohmann_json.natvis.j2` and the ABI
+tags and version in `include/nlohmann/detail/abi_macros.hpp`; change the script or the template rather than editing
+the file by hand. The file can be updated by calling
+
+```shell
+make natvis
+```
+
+The "Check amalgamation" workflow fails if the file is out of date.
+
+The file covers the namespace variants with up to two ABI tags. A Natvis file for other configurations can be
+generated with the `--abi-tags` or `--all` options, for example
+`make natvis NATVIS_ARGS="--abi-tags _diag,_dp,_vns --output my_nlohmann_json.natvis"`; see
+[`tools/generate_natvis`](tools/generate_natvis/README.md). With MSVC, CMake adds the file to the `nlohmann_json`
+target and installs it.
+
+Further documentation:
+
+- [Create custom views of C++ objects in the debugger using the Natvis framework](https://learn.microsoft.com/en-us/visualstudio/debugger/create-custom-views-of-native-objects)

Makefile

@@ -46,7 +46,7 @@ all:
 	@echo "clean - remove built files"
 	@echo "(fuzzers) - see tests/fuzzing.md, or run 'make -C tests fuzzers' to build the AFL fuzzers"
 	@echo "macro_builder_check - check that macro_scope.hpp matches tools/macro_builder's output"
-	@echo "natvis - regenerate nlohmann_json.natvis from the current ABI tags and version"
+	@echo "natvis - regenerate nlohmann_json.natvis from the current ABI tags and version (pass generator options via NATVIS_ARGS, see tools/generate_natvis/README.md)"
 	@echo "pretty - beautify code with Artistic Style"
 	@echo "pvs_studio - run the PVS-Studio static analyzer and open the report"
 	@echo "release - create the release files (include.zip, json.tar.xz, single headers, signatures, hashes)"
@@ -120,13 +120,15 @@ $(AMALGAMATED_VIEW_FILE): $(SRCS)
 	tools/amalgamate/amalgamate.py -c tools/amalgamate/config_json_view.json -s . --verbose=yes
 
 NATVIS_VENV=tools/generate_natvis/venv
+# extra options for generate_natvis.py, e.g. NATVIS_ARGS="--abi-tags _diag,_dp,_vns --output my.natvis"
+NATVIS_ARGS=
 
 # regenerate nlohmann_json.natvis from the ABI tags and version in include/nlohmann/detail/abi_macros.hpp
 # (the dependencies are installed into a virtual environment first)
 natvis:
 	@test -d $(NATVIS_VENV) || python3 -mvenv $(NATVIS_VENV)
 	@$(NATVIS_VENV)/bin/python3 -c 'import jinja2' 2>/dev/null || $(NATVIS_VENV)/bin/pip3 install --quiet -r tools/generate_natvis/requirements.txt
-	$(NATVIS_VENV)/bin/python3 tools/generate_natvis/generate_natvis.py .
+	$(NATVIS_VENV)/bin/python3 tools/generate_natvis/generate_natvis.py $(NATVIS_ARGS) .
 
 # regenerate the two tools/macro_builder blocks of $(MACRO_SCOPE_HPP) (see its README.md) and diff against the
 # checked-in header; phony, because it never writes $(MACRO_SCOPE_HPP) itself

cmake/ci.cmake

@@ -890,11 +890,11 @@ add_custom_target(ci_icpx
 # The following tests are excluded as they trigger known nvc++ 25.5 defects (not
 # library bugs); see https://github.com/nlohmann/json for tracking. Only the
 # affected language-standard variants are excluded so coverage is otherwise kept:
-#   - test-comparison-cpp20_cpp20, test-comparison_legacy-cpp20_cpp20
+#   - test-comparison_cpp20, test-comparison_legacy_cpp20
 #         miscompiles cross-type/<=> comparison (e.g. `-17 <= null`)
 #   - test-constructor1_cpp11
 #         std::initializer_list lifetime bug -> SIGSEGV
-#   - test-deserialization-cpp20_cpp20
+#   - test-deserialization_cpp20
 #         mangles the UTF-8 u8"" string literal in the char8_t (C++20) section
 add_custom_target(ci_nvhpc
     COMMAND ${CMAKE_COMMAND}
@@ -906,7 +906,7 @@ add_custom_target(ci_nvhpc
     COMMAND ${CMAKE_COMMAND} --build ${PROJECT_BINARY_DIR}/build_nvhpc
     # the pipes are escaped so the surrounding shell passes them to ctest verbatim
     # instead of treating them as shell pipe operators
-    COMMAND cd ${PROJECT_BINARY_DIR}/build_nvhpc && ${CMAKE_CTEST_COMMAND} --parallel ${N} --exclude-regex "test-comparison-cpp20_cpp20\\|test-comparison_legacy-cpp20_cpp20\\|test-constructor1_cpp11\\|test-deserialization-cpp20_cpp20" --output-on-failure
+    COMMAND cd ${PROJECT_BINARY_DIR}/build_nvhpc && ${CMAKE_CTEST_COMMAND} --parallel ${N} --exclude-regex "test-comparison_cpp20\\|test-comparison_legacy_cpp20\\|test-constructor1_cpp11\\|test-deserialization_cpp20" --output-on-failure
     COMMENT "Compile and test with NVIDIA HPC SDK (nvc++)"
 )
 

cmake/test.cmake

@@ -109,55 +109,6 @@ function(_json_test_apply_test_properties test_target properties_target)
     endif()
 endfunction()
 
-# for internal use by _json_test_add_test() and _json_test_add_unity_batch():
-# registers the CTest test <test_name>_cpp<cxx_standard> (plus its Valgrind
-# variant), which runs the executable target <test_target> with the arguments
-# in ARGN, and applies the test properties of the test- and standard-specific
-# interface targets
-function(_json_test_register_test test_name test_target cxx_standard)
-    set(ctest_name ${test_name}_cpp${cxx_standard})
-
-    if (JSON_FastTests)
-        add_test(NAME ${ctest_name}
-            COMMAND ${test_target} ${DOCTEST_TEST_FILTER} ${ARGN}
-            WORKING_DIRECTORY ${CMAKE_SOURCE_DIR}
-        )
-    else()
-        add_test(NAME ${ctest_name}
-            COMMAND ${test_target} ${DOCTEST_TEST_FILTER} ${ARGN} --no-skip
-            WORKING_DIRECTORY ${CMAKE_SOURCE_DIR}
-        )
-    endif()
-    set_tests_properties(${ctest_name} PROPERTIES LABELS "all" FIXTURES_REQUIRED TEST_DATA)
-
-    # apply standard-specific test properties
-    if(TARGET _json_test_interface__cpp_${cxx_standard})
-        _json_test_apply_test_properties(${ctest_name} _json_test_interface__cpp_${cxx_standard})
-    endif()
-
-    # apply test-specific test properties
-    if(TARGET _json_test_interface_${test_name})
-        _json_test_apply_test_properties(${ctest_name} _json_test_interface_${test_name})
-    endif()
-
-    # apply test- and standard-specific test properties
-    if(TARGET _json_test_interface_${test_name}_cpp_${cxx_standard})
-        _json_test_apply_test_properties(${ctest_name}
-            _json_test_interface_${test_name}_cpp_${cxx_standard}
-        )
-    endif()
-
-    if(JSON_Valgrind)
-        add_test(NAME ${ctest_name}_valgrind
-            COMMAND ${memcheck_command} $<TARGET_FILE:${test_target}> ${DOCTEST_TEST_FILTER} ${ARGN}
-            WORKING_DIRECTORY ${CMAKE_SOURCE_DIR}
-        )
-        set_tests_properties(${ctest_name}_valgrind PROPERTIES
-            LABELS "valgrind" FIXTURES_REQUIRED TEST_DATA
-        )
-    endif()
-endfunction()
-
 # for internal use by json_test_add_test_for()
 function(_json_test_add_test test_name file main cxx_standard)
     set(test_target ${test_name}_cpp${cxx_standard})
@@ -192,7 +143,45 @@ function(_json_test_add_test test_name file main cxx_standard)
         )
     endif()
 
-    _json_test_register_test(${test_name} ${test_target} ${cxx_standard})
+    if (JSON_FastTests)
+        add_test(NAME ${test_target}
+            COMMAND ${test_target} ${DOCTEST_TEST_FILTER}
+            WORKING_DIRECTORY ${CMAKE_SOURCE_DIR}
+        )
+    else()
+        add_test(NAME ${test_target}
+            COMMAND ${test_target} ${DOCTEST_TEST_FILTER} --no-skip
+            WORKING_DIRECTORY ${CMAKE_SOURCE_DIR}
+        )
+    endif()
+    set_tests_properties(${test_target} PROPERTIES LABELS "all" FIXTURES_REQUIRED TEST_DATA)
+
+    # apply standard-specific test properties
+    if(TARGET _json_test_interface__cpp_${cxx_standard})
+        _json_test_apply_test_properties(${test_target} _json_test_interface__cpp_${cxx_standard})
+    endif()
+
+    # apply test-specific test properties
+    if(TARGET _json_test_interface_${test_name})
+        _json_test_apply_test_properties(${test_target} _json_test_interface_${test_name})
+    endif()
+
+    # apply test- and standard-specific test properties
+    if(TARGET _json_test_interface_${test_name}_cpp_${cxx_standard})
+        _json_test_apply_test_properties(${test_target}
+            _json_test_interface_${test_name}_cpp_${cxx_standard}
+        )
+    endif()
+
+    if(JSON_Valgrind)
+        add_test(NAME ${test_target}_valgrind
+            COMMAND ${memcheck_command} $<TARGET_FILE:${test_target}> ${DOCTEST_TEST_FILTER}
+            WORKING_DIRECTORY ${CMAKE_SOURCE_DIR}
+        )
+        set_tests_properties(${test_target}_valgrind PROPERTIES
+            LABELS "valgrind" FIXTURES_REQUIRED TEST_DATA
+        )
+    endif()
 endfunction()
 
 #############################################################################
@@ -211,14 +200,6 @@ endfunction()
 # Use NAME <name> to override the filename-derived test name.
 # Use FORCE to create the test regardless of the file containing
 # JSON_HAS_CPP_<version_number>.
-#
-# Tests that depend on the C++ standard (e.g., because they use the macros
-# JSON_HAS_FILESYSTEM, JSON_HAS_RANGES, or JSON_HAS_THREE_WAY_COMPARISON)
-# should not make the whole of a large unit-foo.cpp be rebuilt for every
-# standard. Put them into a separate file unit-foo-cpp<NN>.cpp (see, e.g.,
-# unit-items-cpp17.cpp) which wraps its content in #ifdef JSON_HAS_CPP_<NN>.
-# Then, unit-foo.cpp itself contains no JSON_HAS_CPP_<NN> and is only built for
-# C++11.
 # Test targets are linked against <main>.
 # CXX_STANDARDS defaults to "11".
 #############################################################################
@@ -262,314 +243,6 @@ function(json_test_add_test_for file)
     endforeach()
 endfunction()
 
-# for internal use by json_test_add_unity_tests(): sets <result> to whether the
-# (absolute) <file> is built for <cxx_standard>; same rule as in
-# json_test_add_test_for(): C++11 always, others only if the file contains
-# JSON_HAS_CPP_<cxx_standard> or <force> is set
-function(_json_test_unity_applies file cxx_standard force result)
-    set(${result} TRUE PARENT_SCOPE)
-    if(NOT ("${cxx_standard}" STREQUAL 11 OR force))
-        file(READ ${file} file_content)
-        string(FIND "${file_content}" JSON_HAS_CPP_${cxx_standard} has_cpp_found)
-        if(${has_cpp_found} EQUAL -1)
-            set(${result} FALSE PARENT_SCOPE)
-        endif()
-    endif()
-endfunction()
-
-# for internal use by json_test_add_unity_tests(): creates the executable
-# test-unity-<batch_name>_cpp<cxx_standard> from the (absolute) source files
-# in ARGN, which are #include-d by a generated source file, and registers one
-# CTest test per source file that runs only the test cases of that file; if
-# <private> is true, the generated file defines JSON_TESTS_PRIVATE first
-function(_json_test_add_unity_batch batch_name cxx_standard main private)
-    set(batch_target test-unity-${batch_name}_cpp${cxx_standard})
-    set(batch_source ${PROJECT_BINARY_DIR}/tests/unity/${batch_target}.cpp)
-
-    set(batch_content "// generated by cmake/test.cmake; do not edit\n")
-    if(private)
-        string(APPEND batch_content "// at least one file of this batch needs access to private members of the library\n")
-        string(APPEND batch_content "#define JSON_TESTS_PRIVATE\n")
-        # the files define the macro again; mark this definition as used, as
-        # -Wunused-macros reports an unused definition when it is redefined
-        string(APPEND batch_content "#ifdef JSON_TESTS_PRIVATE\n#endif\n")
-    endif()
-    foreach(file ${ARGN})
-        string(APPEND batch_content "#include \"${file}\" // NOLINT(bugprone-suspicious-include)\n")
-    endforeach()
-
-    # only touch the generated file if it changed to keep incremental builds incremental
-    set(old_content "")
-    if(EXISTS ${batch_source})
-        file(READ ${batch_source} old_content)
-    endif()
-    if(NOT "${old_content}" STREQUAL "${batch_content}")
-        file(WRITE ${batch_source} "${batch_content}")
-    endif()
-
-    add_executable(${batch_target} ${batch_source})
-    target_link_libraries(${batch_target} PRIVATE ${main})
-    set_target_properties(${batch_target} PROPERTIES
-        CXX_STANDARD ${cxx_standard}
-        CXX_STANDARD_REQUIRED ON
-    )
-    if(TARGET _json_test_interface__cpp_${cxx_standard})
-        target_link_libraries(${batch_target} PRIVATE _json_test_interface__cpp_${cxx_standard})
-    endif()
-
-    # rebuild the batch when one of its files changes, and show the files in IDEs;
-    # files that are also built standalone (VARIANT_FILES) are left out, as
-    # HEADER_FILE_ONLY is a per-file property and would also affect those targets
-    set_source_files_properties(${batch_source} PROPERTIES OBJECT_DEPENDS "${ARGN}")
-    foreach(file ${ARGN})
-        if(NOT file IN_LIST _json_test_unity_variant_files)
-            set_source_files_properties(${file} PROPERTIES HEADER_FILE_ONLY ON)
-            target_sources(${batch_target} PRIVATE ${file})
-        endif()
-    endforeach()
-
-    foreach(file ${ARGN})
-        get_filename_component(file_basename ${file} NAME_WE)
-        string(REGEX REPLACE "unit-(.+)" "test-\\1" test_name ${file_basename})
-
-        # run only the test cases defined in this file (and in the shared
-        # make_test_data_available.hpp if the file uses it)
-        file(READ ${file} file_content)
-        set(source_filter "--source-file=*${file_basename}.cpp")
-        string(FIND "${file_content}" make_test_data_available.hpp uses_test_data)
-        if(NOT ${uses_test_data} EQUAL -1)
-            string(APPEND source_filter ",*make_test_data_available.hpp")
-        endif()
-
-        _json_test_register_test(${test_name} ${batch_target} ${cxx_standard} "${source_filter}")
-    endforeach()
-endfunction()
-
-#############################################################################
-# json_test_add_unity_tests(
-#     FILES <files>...
-#     MAIN <main>
-#     [CXX_STANDARDS <version_number>...] [FORCE]
-#     [BATCH_SIZE <size>]
-#     [GROUPS <group>...]
-#     [VARIANT_FILES <files>...])
-#
-# Like calling json_test_add_test_for(<file> MAIN <main> ...) for each of the
-# <files>, but compiles several files together to speed up the build: for each
-# C++ standard, the files are split into batches of <size> files (default: 8)
-# and each batch is built as a single executable
-#
-#     test-unity-<pool><index>_cpp<version_number>
-#
-# whose generated source file #include-s the files of the batch (so they share
-# the template instantiations of the library). The tests are still named
-# test-foo_cpp<version_number>, one per file, but run the batch executable with
-# a doctest filter that selects the test cases of that file only.
-#
-# Files are only batched with files that agree on the macros defined before
-# the library is included: files that define at most JSON_TESTS_PRIVATE (or
-# macros derived from global compile definitions) form the pools "plain" and
-# "private". All other files are added with json_test_add_test_for() as usual,
-# as are files with test-specific build settings (see
-# json_test_set_test_options()) and the files listed in the explicit
-# exclusion list below.
-# Each <group> names a list variable json_test_unity_group_<group> of test file
-# stems (file names without "unit-" and ".cpp"). The batchable files of a group
-# are compiled together (regardless of BATCH_SIZE) as one executable
-#
-#     test-unity-<group>_cpp<version_number>
-#
-# so that related tests, which instantiate the same templates, share one
-# translation unit. A group may mix the pools "plain" and "private"; if any of
-# its files needs JSON_TESTS_PRIVATE, the whole group is built with it. Files
-# that cannot be batched stay standalone even if they are listed in a group.
-# Files in no group are batched by BATCH_SIZE as described above.
-# <files> in VARIANT_FILES are also built standalone with other settings, so
-# they are not marked as header-only sources of the batch.
-#############################################################################
-
-function(json_test_add_unity_tests)
-    cmake_parse_arguments(args "FORCE" "MAIN;BATCH_SIZE" "FILES;CXX_STANDARDS;VARIANT_FILES;GROUPS" ${ARGN})
-
-    if("${args_MAIN}" STREQUAL "")
-        message(FATAL_ERROR "Required argument MAIN <main> missing.")
-    endif()
-
-    if("${args_BATCH_SIZE}" STREQUAL "")
-        set(args_BATCH_SIZE 8)
-    endif()
-
-    if("${args_CXX_STANDARDS}" STREQUAL "")
-        set(args_CXX_STANDARDS 11)
-    endif()
-
-    if(args_FORCE)
-        set(force FORCE)
-    else()
-        set(force "")
-    endif()
-
-    set(_json_test_unity_variant_files "")
-    foreach(file ${args_VARIANT_FILES})
-        get_filename_component(file ${file} ABSOLUTE)
-        list(APPEND _json_test_unity_variant_files ${file})
-    endforeach()
-
-    # files that must not be merged into a batch: unit-32bit.cpp is only built
-    # for 32bit targets, and unit-no-macro-leak.cpp checks that including the
-    # library defines no unprefixed macro, which any other file would disturb
-    set(standalone_files unit-32bit.cpp unit-no-macro-leak.cpp)
-
-    set(harmless_macros "^(DOCTEST_.*|SKIP_TESTS_FOR_.*|JSON_TEST_DEPRECATED_FUNCTIONS_DELETED|JSON_TEST_STRICT_NUL_HANDLING_ENABLED|JSON_TEST_STRINGIZE)$")
-
-    # classify the files
-    set(plain_files "")
-    set(private_files "")
-    set(standalone_abs_files "")
-    foreach(file ${args_FILES})
-        get_filename_component(file_name ${file} NAME)
-        get_filename_component(file_basename ${file} NAME_WE)
-        string(REGEX REPLACE "unit-(.+)" "test-\\1" test_name ${file_basename})
-
-        set(batchable TRUE)
-        if(file_name IN_LIST standalone_files)
-            set(batchable FALSE)
-        endif()
-        if(TARGET _json_test_interface_${test_name})
-            set(batchable FALSE)
-        endif()
-        foreach(cxx_standard ${args_CXX_STANDARDS})
-            if(TARGET _json_test_interface_${test_name}_cpp_${cxx_standard})
-                set(batchable FALSE)
-            endif()
-        endforeach()
-
-        # files that suppress GCC's -Wnoexcept around their include of the
-        # library: the suppression has no effect once another file of the
-        # batch included the library first
-        if(batchable)
-            file(READ ${file} file_content)
-            string(FIND "${file_content}" "SUPPRESS_WARNING(\"-Wnoexcept\")" suppresses_noexcept)
-            if(NOT ${suppresses_noexcept} EQUAL -1)
-                set(batchable FALSE)
-            endif()
-        endif()
-
-        set(pool plain)
-        if(batchable)
-            # collect the macros (un)defined before the library is included
-            file(READ ${file} file_content)
-            string(FIND "${file_content}" "#include <nlohmann/" include_position)
-            if(NOT ${include_position} EQUAL -1)
-                string(SUBSTRING "${file_content}" 0 ${include_position} file_content)
-            endif()
-            string(REGEX MATCHALL "(^|\n)[ \t]*#[ \t]*(define|undef)[ \t]+[A-Za-z_0-9]+" directives "${file_content}")
-            foreach(directive ${directives})
-                string(REGEX REPLACE "^.*[ \t]([A-Za-z_0-9]+)$" "\\1" macro "${directive}")
-                if(macro MATCHES "${harmless_macros}")
-                    continue()
-                elseif("${macro}" STREQUAL JSON_TESTS_PRIVATE)
-                    set(pool private)
-                else()
-                    set(batchable FALSE)
-                endif()
-            endforeach()
-        endif()
-
-        get_filename_component(file_abs ${file} ABSOLUTE)
-        if(NOT batchable)
-            list(APPEND standalone_abs_files ${file_abs})
-            json_test_add_test_for(${file} MAIN ${args_MAIN} CXX_STANDARDS ${args_CXX_STANDARDS} ${force})
-            continue()
-        endif()
-        get_filename_component(file ${file} ABSOLUTE)
-        list(APPEND ${pool}_files ${file})
-    endforeach()
-
-    # resolve the explicit groups: group_<name>_files are the (absolute) files
-    # of the group, group_<name>_private tells whether one of them is private
-    set(grouped_files "")
-    foreach(group ${args_GROUPS})
-        if(NOT DEFINED json_test_unity_group_${group})
-            message(FATAL_ERROR "Unity test group '${group}' is not defined (json_test_unity_group_${group}).")
-        endif()
-        set(group_${group}_files "")
-        set(group_${group}_private FALSE)
-        foreach(stem ${json_test_unity_group_${group}})
-            # check against the source directory, because FILES may be filtered (JSON_TestShard)
-            get_filename_component(file ${CMAKE_CURRENT_SOURCE_DIR}/src/unit-${stem}.cpp ABSOLUTE)
-            if(NOT EXISTS ${file})
-                message(FATAL_ERROR "Unity test group '${group}' lists '${stem}', but ${file} does not exist.")
-            endif()
-            if(file IN_LIST grouped_files)
-                message(FATAL_ERROR "Unity test file unit-${stem}.cpp is listed in more than one group (second: '${group}').")
-            endif()
-            list(APPEND grouped_files ${file})
-
-            if(file IN_LIST standalone_abs_files)
-                message(STATUS "Unity test group '${group}': unit-${stem}.cpp cannot be batched and stays standalone")
-            elseif(file IN_LIST plain_files)
-                list(APPEND group_${group}_files ${file})
-                list(REMOVE_ITEM plain_files ${file})
-            elseif(file IN_LIST private_files)
-                list(APPEND group_${group}_files ${file})
-                list(REMOVE_ITEM private_files ${file})
-                set(group_${group}_private TRUE)
-            endif()
-        endforeach()
-    endforeach()
-
-    foreach(cxx_standard ${args_CXX_STANDARDS})
-        if(NOT compiler_supports_cpp_${cxx_standard})
-            continue()
-        endif()
-
-        # explicit groups: one batch per group
-        foreach(group ${args_GROUPS})
-            set(batch_files "")
-            foreach(file ${group_${group}_files})
-                _json_test_unity_applies(${file} ${cxx_standard} "${force}" applies)
-                if(applies)
-                    list(APPEND batch_files ${file})
-                endif()
-            endforeach()
-            if(batch_files)
-                _json_test_add_unity_batch(${group} ${cxx_standard} ${args_MAIN} ${group_${group}_private} ${batch_files})
-            endif()
-        endforeach()
-
-        # remaining files: batches of BATCH_SIZE files per pool
-        foreach(pool plain private)
-            set(is_private FALSE)
-            if(pool STREQUAL private)
-                set(is_private TRUE)
-            endif()
-
-            set(batch_files "")
-            set(batch_count 0)
-            set(batch_index 0)
-            foreach(file ${${pool}_files})
-                _json_test_unity_applies(${file} ${cxx_standard} "${force}" applies)
-                if(NOT applies)
-                    continue()
-                endif()
-
-                list(APPEND batch_files ${file})
-                math(EXPR batch_count "${batch_count} + 1")
-                if(batch_count EQUAL args_BATCH_SIZE)
-                    _json_test_add_unity_batch(${pool}${batch_index} ${cxx_standard} ${args_MAIN} ${is_private} ${batch_files})
-                    set(batch_files "")
-                    set(batch_count 0)
-                    math(EXPR batch_index "${batch_index} + 1")
-                endif()
-            endforeach()
-            if(batch_files)
-                _json_test_add_unity_batch(${pool}${batch_index} ${cxx_standard} ${args_MAIN} ${is_private} ${batch_files})
-            endif()
-        endforeach()
-    endforeach()
-endfunction()
-
 #############################################################################
 # json_test_should_build_32bit_test(
 #     <build_32bit_var> <build_32bit_only_var> <input>)

docs/docset/generate_docset.py

@@ -341,13 +341,14 @@ def download(url, docs) -> str:
         raise ValueError(f'not an http(s) URL: {url}')
     req = urllib.request.Request(u.geturl(), headers={'User-Agent': USER_AGENT})
     # (the scheme is checked above)
+    # nosemgrep: python.lang.security.audit.dynamic-urllib-use-detected.dynamic-urllib-use-detected
     with urllib.request.urlopen(req, timeout=20) as r:  # nosec B310
         data = r.read()
         ctype = r.headers.get_content_type()
     path = urllib.parse.unquote(u.path).lstrip('/')
     ext = os.path.splitext(path)[1]
     if u.query or not ext or path.endswith('/'):
-        digest = hashlib.sha1(url.encode(), usedforsecurity=False).hexdigest()[:12]
+        digest = hashlib.sha256(url.encode()).hexdigest()[:12]
         path = os.path.join(os.path.dirname(path), digest + CONTENT_TYPE_EXT.get(ctype, ext or '.bin'))
     rel = os.path.normpath(os.path.join('assets', 'external', u.hostname, path))
     out = os.path.join(docs, rel)

docs/mkdocs/docs/api/macros/index.md

@@ -38,6 +38,7 @@ header. See also the [macro overview page](../../features/macros.md).
 - [**JSON_HAS_THREE_WAY_COMPARISON**](json_has_three_way_comparison.md) - control 3-way comparison support
 - [**JSON_NO_AUTOMATIC_UDLS**](json_no_automatic_udls.md) - do not include the user-defined string literals (UDLs) automatically
 - [**JSON_NO_IO**](json_no_io.md) - switch off functions relying on certain C++ I/O headers
+- [**JSON_NO_SIMD**](json_no_simd.md) - use only portable code instead of vector instructions (SSE2, SSSE3, NEON)
 - [**JSON_NO_THREAD_LOCAL**](json_no_thread_local.md) - switch off the use of `thread_local` storage
 - [**JSON_SKIP_UNSUPPORTED_COMPILER_CHECK**](json_skip_unsupported_compiler_check.md) - do not warn about unsupported compilers
 - [**JSON_USE_GLOBAL_UDLS**](json_use_global_udls.md) - place user-defined string literals (UDLs) into the global namespace

docs/mkdocs/docs/api/macros/json_no_simd.md

@@ -0,0 +1,83 @@
+# JSON_NO_SIMD
+
+```cpp
+#define JSON_NO_SIMD
+```
+
+When defined, the library uses only portable C++ code where it would otherwise use vector instructions: when scanning
+strings during parsing, and when writing floating-point numbers during serialization.
+
+The macro is an escape hatch, for example for toolchains that cannot compile the vector code, for sanitizers or
+analyzers that do not understand it, or to compare the speed of both variants. It does not change any result: values,
+exceptions, and error positions are the same either way. Only the speed differs.
+
+## Default definition
+
+By default, `#!cpp JSON_NO_SIMD` is not defined, and vector instructions are used where the target has them.
+
+```cpp
+#undef JSON_NO_SIMD
+```
+
+## Notes
+
+!!! note "Which instructions are used"
+
+    - **x86-64:** SSE2, which every x86-64 CPU has, finds the end of runs of plain string characters 16 bytes at a time
+      and writes the digits of floating-point numbers. The UTF-8 check of non-ASCII text needs SSSE3, which is not part
+      of x86-64: it is compiled for SSSE3 with a function attribute and used when the CPU has SSSE3 (every x86-64 CPU
+      since about 2011), else the portable check. Code compiled for SSSE3 anyway (e.g., with `-mssse3` or `-march=native`)
+      skips this check of the CPU. 32-bit x86 uses SSE2 for strings when the compiler targets it.
+    - **AArch64:** NEON, which every 64-bit Arm CPU has, checks UTF-8 text and long runs of plain string characters 16
+      bytes at a time, and writes the digits of floating-point numbers. With MSVC, only the floating-point digits use
+      NEON.
+    - **Other targets:** portable code only.
+
+    Strings are only scanned this way for contiguous input and for the characters a `#!cpp std::istream` holds in its
+    stream buffer (see [`JSON_DISABLE_STREAM_BULK_SCAN`](json_disable_stream_bulk_scan.md)); other inputs are read one
+    character at a time.
+
+!!! note "Interaction with `JSON_USE_SIMDUTF`"
+
+    With [`JSON_USE_SIMDUTF`](json_use_simdutf.md), runs of string characters are first validated by simdutf; the code
+    described here is used for what simdutf does not accept, so that errors are reported at the same position.
+    `JSON_NO_SIMD` does not affect simdutf.
+
+!!! note "ABI compatibility"
+
+    The macro selects between two definitions of the library's internal scanning and formatting functions. Whether it
+    is defined is encoded in the [namespace](../../features/namespace.md) (tag `_ns`), resulting in distinct symbol
+    names. Translation units compiled with and without it can therefore be linked into the same program without One
+    Definition Rule (ODR) violations, but they cannot exchange instances of library types.
+
+## Examples
+
+??? example "Example: switching off vector instructions"
+
+    The program parses and serializes the same values with and without the macro:
+
+    ```cpp
+    #define JSON_NO_SIMD
+    #include <iostream>
+    #include <nlohmann/json.hpp>
+
+    using json = nlohmann::json;
+
+    int main()
+    {
+        const json j = json::parse(R"({"name": "日本語 text", "pi": 3.141592653589793})");
+        std::cout << j.dump() << '\n';  // {"name":"日本語 text","pi":3.141592653589793}
+    }
+    ```
+
+## See also
+
+- [**parse**](../basic_json/parse.md) - deserialize from a compatible input
+- [**dump**](../basic_json/dump.md) - serialization
+- [**JSON_USE_SIMDUTF**](json_use_simdutf.md) - use the simdutf library to accelerate UTF-8 validation
+- [**JSON_DISABLE_STREAM_BULK_SCAN**](json_disable_stream_bulk_scan.md) - read a `std::istream` one character at a time
+- [Parsing: input sources and performance](../../features/parsing/index.md#input-sources-and-performance)
+
+## Version history
+
+- Added in version 3.13.0.

docs/mkdocs/docs/api/macros/json_use_simdutf.md

@@ -6,8 +6,9 @@
 
 When defined, the parser validates the UTF-8 content of JSON strings that come from a **contiguous byte input**
 (`std::string`, `std::vector<char>`/`<std::uint8_t>`, string literals, `const char*` ranges, …) using the
-[simdutf](https://github.com/simdutf/simdutf) library instead of the built-in scalar validator. On text with many
+[simdutf](https://github.com/simdutf/simdutf) library instead of the built-in validator (which uses SSSE3 or NEON where
-non-ASCII characters (e.g. CJK or emoji) this can validate several times faster.
+available, see [`JSON_NO_SIMD`](json_no_simd.md)). On text with many non-ASCII characters (e.g. CJK or emoji) this can
+validate faster, depending on the CPU.
 
 This is an **opt-in external dependency**. The library itself remains header-only and its behavior is unchanged: the
 same input is accepted or rejected either way, and every parse error is reported at the same position with the same

docs/mkdocs/docs/api/macros/nlohmann_json_namespace.md

@@ -39,6 +39,6 @@ the library.
 ## Version history
 
 - Added in version 3.11.0. Changed inline namespace name in version 3.11.2. Added the ABI tag `_dp` in
-  version 3.12.0, and the ABI tags `_bics`, `_psp`, `_snul`, `_sbu8`, `_ekmo`, `_dsbs`, `_dufio`, `_vns`, and
+  version 3.12.0, and the ABI tags `_bics`, `_psp`, `_snul`, `_sbu8`, `_ekmo`, `_dsbs`, `_dufio`, `_ns`, `_vns`,
-  `_vssse3` in version 3.13.0; see
+  and `_vssse3` in version 3.13.0; see
   [`nlohmann` Namespace](../../features/namespace.md#structure).

docs/mkdocs/docs/features/macros.md

@@ -174,6 +174,13 @@ security reasons (e.g., Intel Software Guard Extensions (SGX)).
 
 See [full documentation of `JSON_NO_IO`](../api/macros/json_no_io.md).
 
+## `JSON_NO_SIMD`
+
+When defined, the library uses only portable code instead of vector instructions (SSE2, SSSE3, NEON) for scanning
+strings and writing floating-point numbers. Results are the same either way. It is not defined by default.
+
+See [full documentation of `JSON_NO_SIMD`](../api/macros/json_no_simd.md).
+
 ## `JSON_NO_THREAD_LOCAL`
 
 When defined, the library does not use `#!cpp thread_local` storage. Copying a value and comparing two values then

docs/mkdocs/docs/features/namespace.md

@@ -27,6 +27,7 @@ The complete default namespace name is derived as follows:
       `_dsbs`.
     - [`JSON_DISABLE_UNLOCKED_FILE_IO`](../api/macros/json_disable_unlocked_file_io.md) defined non-zero appends
       `_dufio`.
+    - [`JSON_NO_SIMD`](../api/macros/json_no_simd.md) defined appends `_ns`.
     - [`JSON_VIEW_NO_SIMD`](../api/macros/json_view_no_simd.md) defined appends `_vns`.
     - [`JSON_VIEW_USE_SSSE3`](../api/macros/json_view_use_ssse3.md) defined appends `_vssse3`.
 - The inline namespace ends with the suffix `_v` followed by the 3 components of the version number separated by
@@ -114,6 +115,7 @@ follows:
   ([`JSON_STRICT_BINARY_UTF8`](../api/macros/json_strict_binary_utf8.md)), `_ekmo`
   ([`JSON_USE_OBJECTS_FOR_ENUM_KEYED_MAPS`](../api/macros/json_use_objects_for_enum_keyed_maps.md)), `_dsbs`
   ([`JSON_DISABLE_STREAM_BULK_SCAN`](../api/macros/json_disable_stream_bulk_scan.md)), `_dufio`
-  ([`JSON_DISABLE_UNLOCKED_FILE_IO`](../api/macros/json_disable_unlocked_file_io.md)), `_vns`
+  ([`JSON_DISABLE_UNLOCKED_FILE_IO`](../api/macros/json_disable_unlocked_file_io.md)), `_ns`
+  ([`JSON_NO_SIMD`](../api/macros/json_no_simd.md)), `_vns`
   ([`JSON_VIEW_NO_SIMD`](../api/macros/json_view_no_simd.md)), and `_vssse3`
   ([`JSON_VIEW_USE_SSSE3`](../api/macros/json_view_use_ssse3.md)) in version 3.13.0.

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

@@ -79,6 +79,10 @@ follow the usual `std::streambuf` contract, and
 [`JSON_DISABLE_UNLOCKED_FILE_IO`](../../api/macros/json_disable_unlocked_file_io.md) for programs in which another
 thread must use the same `#!cpp FILE` object while it is parsed.
 
+Where the target has them, strings are scanned with vector instructions: SSE2 on x86-64 (and SSSE3 for UTF-8 text, when
+the CPU has it) and NEON on AArch64. [`JSON_NO_SIMD`](../../api/macros/json_no_simd.md) selects portable code instead,
+again without changing any result.
+
 ## SAX vs. DOM parsing
 
 The library offers two parsing models:

docs/mkdocs/docs/features/performance.md

@@ -20,32 +20,39 @@ below apply on every supported standard. This adapter exposes two optimizations
 
 - it can reconstruct already-consumed input on demand for error messages, instead of copying every character as it is
   read, and
-- the lexer can scan ordinary string characters directly out of the buffer, several bytes at a time, rather than one
+- the lexer can scan ordinary string characters, numbers, and indentation directly out of the buffer, several bytes at
-  character (and one function call) at a time.
+  a time, rather than one character (and one function call) at a time.
 
-A `#!cpp std::istream` (including `#!cpp std::ifstream`) or `#!cpp FILE*`, by contrast, is read through
+A `#!cpp std::istream` (including `#!cpp std::ifstream`) gets the same bulk scanning: `input_stream_adapter` scans the
-`input_stream_adapter` or `file_input_adapter`, which read one character (or one block, for binary formats) at a time
+characters its stream buffer already holds (the *get area*) and asks the stream buffer for more only when they are used
-and expose neither optimization -- the lexer falls back to the same byte-at-a-time path it uses for any
+up. Nothing is read ahead, so the stream is left exactly where it would be after reading one character at a time, and
-non-contiguous, general-purpose iterator range. An iterator pair over non-contiguous but random-access storage (e.g.
+[`operator>>`](../api/operator_gtgt.md) can still read several values from one stream. A stream buffer without a get
-`#!cpp std::deque<char>::iterator`) gets the first optimization but not the second, since the byte-scanning fast path
+area is read one character at a time. A `#!cpp FILE*` is still read one character at a time, but `file_input_adapter`
-additionally requires contiguous storage.
+locks the file once per parse instead of once per character. See
+[input sources and performance](parsing/index.md#input-sources-and-performance) for the full table. According to the
+description of [#5828](https://github.com/nlohmann/json/pull/5828), parsing from a stream is within about 10 to 20 % of
+parsing an equivalent `#!cpp std::string`.
 
-Practically: if the JSON text is already in memory, or small enough to read into memory, prefer passing a
+Inputs that are still read one character at a time: iterator ranges that are not contiguous (e.g.
-`#!cpp std::string`, a `#!cpp std::vector<char>`, or a pointer range to `parse` over a `#!cpp std::istream`. For a
+`#!cpp std::list<char>` or `#!cpp std::istreambuf_iterator<char>`), wide strings, and user-defined adapters. An
-file, that means reading it into a string first and then parsing the string, rather than passing a
+iterator pair over non-contiguous but random-access storage (e.g. `#!cpp std::deque<char>::iterator`) gets the first
-`#!cpp std::ifstream` directly to `parse` -- the latter never benefits from either optimization:
+optimization but not the second, since the byte-scanning fast path requires contiguous storage.
+
+Practically: a file can be passed directly to `parse`, which also avoids the memory for a copy of the file. Reading it
+into a string first is no longer necessary for speed:
 
 ```cpp
-// gets the contiguous fast paths
+// fast: the stream buffer's get area is scanned in bulk
 std::ifstream f("example.json");
-std::string contents((std::istreambuf_iterator<char>(f)), std::istreambuf_iterator<char>());
+json j = json::parse(f);
-json j = json::parse(contents);
-
-// does not: input_stream_adapter has no fast path
-std::ifstream f2("example.json");
-json j2 = json::parse(f2);
 ```
 
+Two macros switch the stream optimizations off without changing any result:
+[`JSON_DISABLE_STREAM_BULK_SCAN`](../api/macros/json_disable_stream_bulk_scan.md) for stream buffers that do not follow
+the usual `#!cpp std::streambuf` contract, and
+[`JSON_DISABLE_UNLOCKED_FILE_IO`](../api/macros/json_disable_unlocked_file_io.md) for programs in which another thread
+must use the same `#!cpp FILE` object while it is parsed.
+
 For contiguous input with many non-ASCII characters, [`JSON_USE_SIMDUTF`](../api/macros/json_use_simdutf.md) can
 additionally speed up UTF-8 validation by using the [simdutf](https://github.com/simdutf/simdutf) library instead of
 the built-in scalar validator; streaming inputs (files, `#!cpp std::istream`, wide strings, user-defined adapters)

docs/mkdocs/docs/home/architecture.md

@@ -64,7 +64,7 @@ below are relative to `include/nlohmann`.
 |-----------|----------|
 | Value type enumeration | [`detail/value_t.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/value_t.hpp) |
 | Input adapters | [`detail/input/input_adapters.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/input_adapters.hpp) |
-| Lexer | [`detail/input/lexer.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/lexer.hpp), [`detail/input/number_parse.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/number_parse.hpp), [`detail/input/string_scan.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/string_scan.hpp) |
+| Lexer | [`detail/input/lexer.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/lexer.hpp), [`detail/input/number_parse.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/number_parse.hpp), [`detail/input/string_scan.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/string_scan.hpp), [`detail/input/simd_scan.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/simd_scan.hpp) |
 | Parser | [`detail/input/parser.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/parser.hpp) |
 | SAX interface and DOM builders | [`detail/input/json_sax.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/json_sax.hpp) |
 | Binary format readers | [`detail/input/binary_reader.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/binary_reader.hpp) |
@@ -339,6 +339,11 @@ The `serializer` (used by [`dump`](../api/basic_json/dump.md) and [`operator<<`]
 - `output_stream_adapter` writes to a `std::ostream`.
 - `output_string_adapter` appends to a string.
 
+The `binary_writer` does not call an adapter for every byte. The `to_*` functions that return a `std::vector` write
+into the vector through a sink (`output_vector_sink`) that is not virtual. The functions that take an output adapter
+write through a sink (`output_adapter_sink`) that collects the output in a buffer of one kibibyte and passes it to the
+adapter in blocks, so that the adapter is called (and a stream locked) once per block instead of once per value.
+
 ## Value conversion
 
 Values are converted from and to other types with the `JSONSerializer` template parameter. The default,

docs/mkdocs/docs/home/debugging.md

@@ -10,6 +10,29 @@ at its root, a [Natvis](https://learn.microsoft.com/en-us/visualstudio/debugger/
 file that gives `json`/`ordered_json` values a friendly, key/value debugger view instead of showing raw internal
 fields, when debugging with the MSVC debug engine (`cppvsdbg`) in Visual Studio or VS Code.
 
+The checked-in visualizers cover namespace variants with zero, one, or two ABI tags. Configurations with three or more
+ABI tags are not covered and may show raw internal fields instead. To generate a Natvis file for such a configuration:
+
+1. Check out the release tag of the library version you use.
+2. List the ABI tags and the macros that enable them:
+
+    ```shell
+    make natvis NATVIS_ARGS="--list-tags"
+    ```
+
+3. Generate a Natvis file with the tags of your configuration, for example for `JSON_DIAGNOSTICS`,
+    `JSON_DIAGNOSTIC_POSITIONS`, and `JSON_VIEW_NO_SIMD`:
+
+    ```shell
+    make natvis NATVIS_ARGS="--abi-tags _diag,_dp,_vns --output my_nlohmann_json.natvis"
+    ```
+
+4. Use the generated file instead of `nlohmann_json.natvis`.
+
+`--abi-tags` can be repeated for several configurations, and `--all` generates every combination (about 60 MB for 12
+ABI tags, doubling with each further tag). See
+[`tools/generate_natvis`](https://github.com/nlohmann/json/tree/develop/tools/generate_natvis) for all options.
+
 Debug engines that wrap LLDB instead of the MSVC debug engine (for example, `codelldb` in VS Code) only have
 partial/experimental Natvis support, and commonly fall back to showing raw internal fields even with the
 `.natvis` file present. Switching to `cppvsdbg` where available, or checking your debug extension's own Natvis

docs/mkdocs/docs/integration/cmake.md

@@ -235,17 +235,6 @@ Build the unit tests against the [simdutf](https://github.com/simdutf/simdutf) U
 its version is set by the cache variable `JSON_SIMDUTF_VERSION`. This option is `OFF` by default. Depends on
 `JSON_BuildTests`.
 
-### `JSON_TestUnityBuild`
-
-Build the unit tests in batches of several test files per executable to speed up compilation: the files of a batch are
-compiled as one translation unit, so the template instantiations of the library are shared. Every test file still gets
-its own CTest test (e.g., `test-foo_cpp11`), which runs only the test cases of that file from the shared executable.
-This option is `ON` by default (and `OFF` with MinGW). Set it to `OFF` to get one executable per test file, e.g., when
-debugging a single file. The number of files per executable is set by the cache variable `JSON_TestUnityBatchSize`
-(default: `8`). Related test files (e.g., all binary formats) are grouped explicitly in `tests/CMakeLists.txt`; each
-group is compiled as one executable per C++ standard regardless of the batch size, and only the remaining files are
-batched by size. Depends on `JSON_BuildTests`.
-
 ### `JSON_Valgrind`
 
 Execute the test suite with [Valgrind](https://valgrind.org). This option is `OFF` by default. Depends on `JSON_BuildTests`.

docs/mkdocs/mkdocs.yml

@@ -383,6 +383,7 @@ nav:
           - 'JSON_NO_AUTOMATIC_UDLS': api/macros/json_no_automatic_udls.md
           - 'JSON_NOEXCEPTION': api/macros/json_noexception.md
           - 'JSON_NO_IO': api/macros/json_no_io.md
+          - 'JSON_NO_SIMD': api/macros/json_no_simd.md
           - 'JSON_NO_THREAD_LOCAL': api/macros/json_no_thread_local.md
           - 'JSON_PRECISE_STREAM_POSITION': api/macros/json_precise_stream_position.md
           - 'JSON_SKIP_LIBRARY_VERSION_CHECK': api/macros/json_skip_library_version_check.md

docs/mkdocs/scripts/mermaid/package-lock.json

@@ -6,7 +6,7 @@
     "": {
       "name": "check-mermaid",
       "dependencies": {
-        "jsdom": "30.1.2",
+        "jsdom": "30.1.3",
         "mermaid": "11.17.2"
       }
     },
@@ -40,9 +40,9 @@
       }
     },
     "node_modules/@asamuzakjp/dom-selector": {
-      "version": "9.2.4",
+      "version": "10.0.3",
-      "resolved": "https://registry.npmjs.org/@asamuzakjp/dom-selector/-/dom-selector-9.2.4.tgz",
+      "resolved": "https://registry.npmjs.org/@asamuzakjp/dom-selector/-/dom-selector-10.0.3.tgz",
-      "integrity": "sha512-YnVzxDxLaqL0t7Q4wfcgHZjg55Wm6y5EaO7Bhu3q9J7wq/8iw3PhsnWiOQhYekx4VexnbkgWpTT6n+QIV7kczw==",
+      "integrity": "sha512-3+777rEPsOOjoy5/sRmIzHnoRDaLpm3XWY2dmWn/N7f/XwDG0bcpnFaKL3X9FYJUbNwLmpcJC1bUYexJRxsFlw==",
       "license": "MIT",
       "dependencies": {
         "bidi-js": "^1.1.0",
@@ -1202,13 +1202,13 @@
       "license": "MIT"
     },
     "node_modules/jsdom": {
-      "version": "30.1.2",
+      "version": "30.1.3",
-      "resolved": "https://registry.npmjs.org/jsdom/-/jsdom-30.1.2.tgz",
+      "resolved": "https://registry.npmjs.org/jsdom/-/jsdom-30.1.3.tgz",
-      "integrity": "sha512-0FFE/jE1rppmVfUrJUgxqXjcwolZYIGtAgj1pTussMhNZxIxi7W/PvfWaMNroGi2B36X1IKHbexpZ9DhkoOPiQ==",
+      "integrity": "sha512-hQMUPvRgN7KxsfIytDQji7bimuJeRQa6Qo5+iuiZQk5CafeRxLIA10/cG5YCBFNpD9RO3oqIiN4CO1Y44kxqXg==",
       "license": "MIT",
       "dependencies": {
         "@asamuzakjp/css-color": "^7.1.3",
-        "@asamuzakjp/dom-selector": "^9.2.4",
+        "@asamuzakjp/dom-selector": "^10.0.3",
         "@bramus/specificity": "^2.4.2",
         "@csstools/css-syntax-patches-for-csstree": "^1.1.15",
         "@exodus/bytes": "^1.16.0",
@@ -1221,7 +1221,7 @@
         "parse5": "^8.0.1",
         "saxes": "^6.0.0",
         "tough-cookie": "^6.0.2",
-        "undici": "^8.11.2",
+        "undici": "^8.12.1",
         "w3c-xmlserializer": "^6.0.0",
         "webidl-conversions": "^8.0.1",
         "whatwg-mimetype": "^5.0.0",
@@ -1521,9 +1521,9 @@
       }
     },
     "node_modules/undici": {
-      "version": "8.11.2",
+      "version": "8.12.2",
-      "resolved": "https://registry.npmjs.org/undici/-/undici-8.11.2.tgz",
+      "resolved": "https://registry.npmjs.org/undici/-/undici-8.12.2.tgz",
-      "integrity": "sha512-u4UB2/IrKdU6lFxumHmmo1a3fCQO5tzQllRorfoRS63txhrB7xTpSn1PftwC4qEHkOaqP95fCWW4lJzwErwzhQ==",
+      "integrity": "sha512-XtuDWVdqTLr3NAxm2ly9/hU6kUsJOgGh1RASzMBbsw6aWCOaQzHdW+QQDfdERjfJ2V5vL5pRPa4RetO9UfivDg==",
       "license": "MIT",
       "engines": {
         "node": ">=22.19.0"

docs/mkdocs/scripts/mermaid/package.json

@@ -4,7 +4,7 @@
   "description": "Validate the Mermaid diagrams of the documentation (see check_mermaid.mjs)",
   "type": "module",
   "dependencies": {
-    "jsdom": "30.1.2",
+    "jsdom": "30.1.3",
     "mermaid": "11.17.2"
   }
 }

include/nlohmann/detail/abi_macros.hpp

@@ -122,6 +122,12 @@
     #define NLOHMANN_JSON_ABI_TAG_DISABLE_UNLOCKED_FILE_IO
 #endif
 
+#ifdef JSON_NO_SIMD
+    #define NLOHMANN_JSON_ABI_TAG_NO_SIMD _ns
+#else
+    #define NLOHMANN_JSON_ABI_TAG_NO_SIMD
+#endif
+
 #ifdef JSON_VIEW_NO_SIMD
     #define NLOHMANN_JSON_ABI_TAG_VIEW_NO_SIMD _vns
 #else
@@ -139,9 +145,9 @@
 #endif
 
 // Construct the namespace ABI tags component
-#define NLOHMANN_JSON_ABI_TAGS_CONCAT_EX(a, b, c, d, e, f, g, h, i, j, k, l) json_abi ## a ## b ## c ## d ## e ## f ## g ## h ## i ## j ## k ## l
+#define NLOHMANN_JSON_ABI_TAGS_CONCAT_EX(a, b, c, d, e, f, g, h, i, j, k, l, m) json_abi ## a ## b ## c ## d ## e ## f ## g ## h ## i ## j ## k ## l ## m
-#define NLOHMANN_JSON_ABI_TAGS_CONCAT(a, b, c, d, e, f, g, h, i, j, k, l) \
+#define NLOHMANN_JSON_ABI_TAGS_CONCAT(a, b, c, d, e, f, g, h, i, j, k, l, m) \
-    NLOHMANN_JSON_ABI_TAGS_CONCAT_EX(a, b, c, d, e, f, g, h, i, j, k, l)
+    NLOHMANN_JSON_ABI_TAGS_CONCAT_EX(a, b, c, d, e, f, g, h, i, j, k, l, m)
 
 #define NLOHMANN_JSON_ABI_TAGS                                       \
     NLOHMANN_JSON_ABI_TAGS_CONCAT(                                   \
@@ -155,6 +161,7 @@
             NLOHMANN_JSON_ABI_TAG_OBJECTS_FOR_ENUM_KEYED_MAPS,       \
             NLOHMANN_JSON_ABI_TAG_DISABLE_STREAM_BULK_SCAN,          \
             NLOHMANN_JSON_ABI_TAG_DISABLE_UNLOCKED_FILE_IO,          \
+            NLOHMANN_JSON_ABI_TAG_NO_SIMD,                           \
             NLOHMANN_JSON_ABI_TAG_VIEW_NO_SIMD,                      \
             NLOHMANN_JSON_ABI_TAG_VIEW_USE_SSSE3)
 

include/nlohmann/detail/bit_ops.hpp

@@ -14,11 +14,24 @@
     #include <intrin0.h> // __umulh, _umul128, _BitScanForward64, _BitScanReverse64
 #endif
 
+#ifdef _MSC_VER
+    #include <cstdlib> // _byteswap_ushort, _byteswap_ulong, _byteswap_uint64
+#endif
+#if defined(_MSC_VER) && !defined(__clang__) && (defined(_M_IX86) || defined(_M_ARM))
+    #include <intrin.h> // _BitScanForward, _BitScanReverse
+#endif
+
 #include <nlohmann/detail/macro_scope.hpp> // JSON_HEDLEY_ALWAYS_INLINE, NLOHMANN_JSON_NAMESPACE_BEGIN
 
+#if defined(__cpp_lib_bit_cast) || defined(__cpp_lib_bitops) || defined(__cpp_lib_byteswap)
+    #include <bit> // bit_cast, byteswap, countl_zero, countr_zero
+#endif
+
 // Portable bit-level helpers for the number and string scanners. They use
-// compiler builtins or platform-specific intrinsics where available and plain
+// compiler builtins or platform-specific intrinsics where available, the
-// C++ otherwise, so they work regardless of byte order.
+// C++20 <bit> functions next, and plain C++ otherwise, so they work regardless
+// of byte order. (The builtins and intrinsics come first: MSVC's
+// std::countl_zero checks for LZCNT at run time unless AVX2 is enabled.)
 
 NLOHMANN_JSON_NAMESPACE_BEGIN
 namespace detail
@@ -33,6 +46,16 @@ inline int count_leading_zeros(std::uint64_t x) noexcept
     unsigned long index = 0; // NOLINT(runtime/int): the type _BitScan*64 takes
     _BitScanReverse64(&index, x);
     return 63 - static_cast<int>(index);
+#elif defined(_MSC_VER) && (defined(_M_IX86) || defined(_M_ARM))
+    unsigned long index = 0; // NOLINT(runtime/int): the type _BitScan* takes
+    if (_BitScanReverse(&index, static_cast<unsigned long>(x >> 32u))) // NOLINT(runtime/int)
+    {
+        return 31 - static_cast<int>(index);
+    }
+    _BitScanReverse(&index, static_cast<unsigned long>(x)); // NOLINT(runtime/int)
+    return 63 - static_cast<int>(index);
+#elif defined(__cpp_lib_bitops)
+    return std::countl_zero(x);
 #else
     int n = 0;
     for (int shift = 32; shift != 0; shift >>= 1)
@@ -56,6 +79,16 @@ inline int count_trailing_zeros(std::uint64_t x) noexcept
     unsigned long index = 0; // NOLINT(runtime/int): the type _BitScan*64 takes
     _BitScanForward64(&index, x);
     return static_cast<int>(index);
+#elif defined(_MSC_VER) && (defined(_M_IX86) || defined(_M_ARM))
+    unsigned long index = 0; // NOLINT(runtime/int): the type _BitScan* takes
+    if (_BitScanForward(&index, static_cast<unsigned long>(x))) // NOLINT(runtime/int)
+    {
+        return static_cast<int>(index);
+    }
+    _BitScanForward(&index, static_cast<unsigned long>(x >> 32u)); // NOLINT(runtime/int)
+    return 32 + static_cast<int>(index);
+#elif defined(__cpp_lib_bitops)
+    return std::countr_zero(x);
 #else
     int n = 0;
     for (int shift = 32; shift != 0; shift >>= 1)
@@ -70,6 +103,67 @@ inline int count_trailing_zeros(std::uint64_t x) noexcept
 #endif
 }
 
+/// the object representation of @a from as a @a To (std::bit_cast in C++20)
+template<typename To, typename From>
+JSON_HEDLEY_ALWAYS_INLINE To bit_cast(const From& from) noexcept
+{
+    static_assert(sizeof(To) == sizeof(From), "bit_cast needs types of the same size");
+#if defined(__cpp_lib_bit_cast)
+    return std::bit_cast<To>(from);
+#else
+    To to {};
+    std::memcpy(&to, &from, sizeof(To));
+    return to;
+#endif
+}
+
+/// x with its bytes in reverse order (std::byteswap in C++23); compilers lower
+/// it to a single bswap/rev/movbe
+inline std::uint16_t byteswap(std::uint16_t x) noexcept
+{
+#if defined(__GNUC__) || defined(__clang__)
+    return __builtin_bswap16(x);
+#elif defined(_MSC_VER)
+    return _byteswap_ushort(x);
+#elif defined(__cpp_lib_byteswap)
+    return std::byteswap(x);
+#else
+    return static_cast<std::uint16_t>((x >> 8u) | (x << 8u));
+#endif
+}
+
+/// x with its bytes in reverse order (std::byteswap in C++23)
+inline std::uint32_t byteswap(std::uint32_t x) noexcept
+{
+#if defined(__GNUC__) || defined(__clang__)
+    return __builtin_bswap32(x);
+#elif defined(_MSC_VER)
+    return _byteswap_ulong(x);
+#elif defined(__cpp_lib_byteswap)
+    return std::byteswap(x);
+#else
+    return ((x & 0x000000FFu) << 24u) | ((x & 0x0000FF00u) << 8u)
+           | ((x & 0x00FF0000u) >> 8u) | ((x & 0xFF000000u) >> 24u);
+#endif
+}
+
+/// x with its bytes in reverse order (std::byteswap in C++23)
+inline std::uint64_t byteswap(std::uint64_t x) noexcept
+{
+#if defined(__GNUC__) || defined(__clang__)
+    return __builtin_bswap64(x);
+#elif defined(_MSC_VER)
+    return _byteswap_uint64(x);
+#elif defined(__cpp_lib_byteswap)
+    return std::byteswap(x);
+#else
+    x = ((x & 0x00000000FFFFFFFFull) << 32u) | ((x & 0xFFFFFFFF00000000ull) >> 32u);
+    x = ((x & 0x0000FFFF0000FFFFull) << 16u) | ((x & 0xFFFF0000FFFF0000ull) >> 16u);
+    x = ((x & 0x00FF00FF00FF00FFull) << 8u) | ((x & 0xFF00FF00FF00FF00ull) >> 8u);
+    return x;
+#endif
+}
+
 /// the 128-bit product of two 64-bit numbers
 struct uint128_parts
 {
@@ -107,8 +201,8 @@ inline uint128_parts full_multiplication(std::uint64_t a, std::uint64_t b) noexc
 /// targets; always inlined, as GCC otherwise calls it in the number loops)
 JSON_HEDLEY_ALWAYS_INLINE std::uint64_t read_eight_bytes(const unsigned char* b) noexcept
 {
-#if defined(_MSC_VER) || defined(__x86_64__) || defined(__i386__) || (defined(__BYTE_ORDER__) && defined(__ORDER_LITTLE_ENDIAN__) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__)
+#if JSON_LITTLE_ENDIAN_TARGET
-    // the byte order already matches (all MSVC targets are little-endian)
+    // the byte order already matches
     std::uint64_t result = 0;
     std::memcpy(&result, b, sizeof(result));
     return result;

include/nlohmann/detail/conversions/from_json.hpp

@@ -69,12 +69,10 @@ void from_json(const BasicJsonType& j, std::optional<T>& opt)
 }
 #endif // JSON_HAS_CPP_17
 
-// overloads for basic_json template parameters
+// read a number value of any of the three number types into val;
-template < typename BasicJsonType, typename ArithmeticType,
+// returns false (leaving val untouched) if j is not a number
-           enable_if_t < std::is_arithmetic<ArithmeticType>::value&&
+template<typename BasicJsonType, typename ArithmeticType>
-                         !std::is_same<ArithmeticType, typename BasicJsonType::boolean_t>::value,
+bool get_number_value(const BasicJsonType& j, ArithmeticType& val)
-                         int > = 0 >
-void get_arithmetic_value(const BasicJsonType& j, ArithmeticType& val)
 {
     switch (static_cast<value_t>(j))
     {
@@ -85,17 +83,17 @@ void get_arithmetic_value(const BasicJsonType& j, ArithmeticType& val)
             const auto* ptr = j.template get_ptr<const typename BasicJsonType::number_unsigned_t*>();
             JSON_ASSERT(ptr != nullptr);
             val = static_cast<ArithmeticType>(*ptr);
-            break;
+            return true;
         }
         case value_t::number_integer:
         {
             val = static_cast<ArithmeticType>(*j.template get_ptr<const typename BasicJsonType::number_integer_t*>());
-            break;
+            return true;
         }
         case value_t::number_float:
         {
             val = static_cast<ArithmeticType>(*j.template get_ptr<const typename BasicJsonType::number_float_t*>());
-            break;
+            return true;
         }
 
         case value_t::null:
@@ -106,7 +104,20 @@ void get_arithmetic_value(const BasicJsonType& j, ArithmeticType& val)
         case value_t::binary:
         case value_t::discarded:
         default:
-            throw_type_must_be("number", j);
+            return false;
+    }
+}
+
+// overloads for basic_json template parameters
+template < typename BasicJsonType, typename ArithmeticType,
+           enable_if_t < std::is_arithmetic<ArithmeticType>::value&&
+                         !std::is_same<ArithmeticType, typename BasicJsonType::boolean_t>::value,
+                         int > = 0 >
+void get_arithmetic_value(const BasicJsonType& j, ArithmeticType& val)
+{
+    if (JSON_HEDLEY_UNLIKELY(!get_number_value(j, val)))
+    {
+        throw_type_must_be("number", j);
     }
 }
 
@@ -256,18 +267,18 @@ auto from_json_array_impl(const BasicJsonType& j, std::array<T, N>& arr,
     }
 }
 
-// reserve() is called through this pair (modeled on from_json_object_reserve)
+// reserve() is called through this pair (used for arrays and objects alike)
-// so from_json_array_impl below has a single body for both ConstructibleArrayType
+// so from_json_array_impl and the object from_json have a single body for both
-// that support reserve() and those that don't.
+// containers that support reserve() and those that don't.
-template<typename ConstructibleArrayType>
+template<typename ConstructibleContainerType>
-auto from_json_array_reserve(ConstructibleArrayType& arr, typename ConstructibleArrayType::size_type size, priority_tag<1> /*unused*/)
+auto reserve_if_possible(ConstructibleContainerType& c, typename ConstructibleContainerType::size_type size, priority_tag<1> /*unused*/)
--> decltype(arr.reserve(size), void())
+-> decltype(c.reserve(size), void())
 {
-    arr.reserve(size);
+    c.reserve(size);
 }
 
-template<typename ConstructibleArrayType>
+template<typename ConstructibleContainerType>
-void from_json_array_reserve(ConstructibleArrayType& /*arr*/, std::size_t /*size*/, priority_tag<0> /*unused*/)
+void reserve_if_possible(ConstructibleContainerType& /*c*/, std::size_t /*size*/, priority_tag<0> /*unused*/)
 {}
 
 // append through push_back() where available; containers without it (such as
@@ -297,7 +308,7 @@ auto from_json_array_impl(const BasicJsonType& j, ConstructibleArrayType& arr, p
 {
     ConstructibleArrayType ret;
     const auto* inner_array = j.template get_ptr<const typename BasicJsonType::array_t*>();
-    from_json_array_reserve(ret, inner_array->size(), priority_tag<1> {});
+    reserve_if_possible(ret, inner_array->size(), priority_tag<1> {});
     for (const auto& elem : *inner_array)
     {
         // get<BasicJsonType>() returns *this, this won't call a from_json
@@ -378,17 +389,6 @@ inline void from_json(const BasicJsonType& j, CompatibleArrayType& bin)
     }
 }
 
-template<typename ConstructibleObjectType>
-auto from_json_object_reserve(ConstructibleObjectType& obj, typename ConstructibleObjectType::size_type size, priority_tag<1> /*unused*/)
--> decltype(obj.reserve(size), void())
-{
-    obj.reserve(size);
-}
-
-template<typename ConstructibleObjectType>
-inline void from_json_object_reserve(ConstructibleObjectType& /*obj*/, std::size_t /*size*/, priority_tag<0> /*unused*/)
-{}
-
 // the keys of the source are sorted for the usual object types, so hinting the
 // end makes every insertion constant-time (for containers that order their keys
 // the same way); containers without emplace_hint() (such as ordered_map) fall
@@ -417,7 +417,7 @@ inline void from_json(const BasicJsonType& j, ConstructibleObjectType& obj)
 
     ConstructibleObjectType ret;
     const auto* inner_object = j.template get_ptr<const typename BasicJsonType::object_t*>();
-    from_json_object_reserve(ret, inner_object->size(), priority_tag<1> {});
+    reserve_if_possible(ret, inner_object->size(), priority_tag<1> {});
     for (const auto& p : *inner_object)
     {
         from_json_object_emplace(ret, p.first, p.second.template get<typename ConstructibleObjectType::mapped_type>(), priority_tag<1> {});
@@ -437,6 +437,10 @@ template < typename BasicJsonType, typename ArithmeticType,
                int > = 0 >
 inline void from_json(const BasicJsonType& j, ArithmeticType& val)
 {
+    // the number cases repeat get_number_value() on purpose: calling it here
+    // changes the inlining of get<T>() in the std::array conversion, which then
+    // runs 2.4x slower (GetArray benchmark, #5891); unlike get_arithmetic_value(),
+    // a boolean is accepted
     switch (static_cast<value_t>(j))
     {
         case value_t::number_unsigned:

include/nlohmann/detail/conversions/to_chars.hpp

@@ -18,17 +18,14 @@
 #include <limits> // numeric_limits
 #include <type_traits> // conditional
 
-#ifdef _MSC_VER
-    #include <cstdlib> // _byteswap_uint64
-#endif
 
 // SSE2 (every x86-64 CPU) and NEON (every 64-bit Arm CPU) convert the 16
-// digits of a double at once
+// digits of a double at once (unless JSON_NO_SIMD selects the portable code)
-#if defined(__x86_64__) || (defined(_M_X64) && !defined(_M_ARM64EC))
+#if !defined(JSON_NO_SIMD) && (defined(__x86_64__) || (defined(_M_X64) && !defined(_M_ARM64EC)))
     #include <emmintrin.h>
     #define JSON_DTOA_SSE2 1
     #define JSON_DTOA_NEON 0
-#elif (defined(__aarch64__) || defined(_M_ARM64)) && !defined(_M_ARM64EC) && !defined(__ARM_BIG_ENDIAN)
+#elif !defined(JSON_NO_SIMD) && (defined(__aarch64__) || defined(_M_ARM64)) && !defined(_M_ARM64EC) && !defined(__ARM_BIG_ENDIAN)
     #include <arm_neon.h>
     #define JSON_DTOA_SSE2 0
     #define JSON_DTOA_NEON 1
@@ -37,6 +34,7 @@
     #define JSON_DTOA_NEON 0
 #endif
 
+#include <nlohmann/detail/bit_ops.hpp>
 #include <nlohmann/detail/conversions/zmij.hpp>
 #include <nlohmann/detail/macro_scope.hpp>
 
@@ -66,16 +64,6 @@ For a detailed description of the algorithm see:
 namespace dtoa_impl
 {
 
-template<typename Target, typename Source>
-Target reinterpret_bits(const Source source)
-{
-    static_assert(sizeof(Target) == sizeof(Source), "size mismatch");
-
-    Target target;
-    std::memcpy(&target, &source, sizeof(Source));
-    return target;
-}
-
 struct diyfp // f * 2^e
 {
     static constexpr int kPrecision = 64; // = q
@@ -230,7 +218,7 @@ boundaries compute_boundaries(FloatType value)
 
     using bits_type = typename std::conditional<kPrecision == 24, std::uint32_t, std::uint64_t >::type;
 
-    const auto bits = static_cast<std::uint64_t>(reinterpret_bits<bits_type>(value));
+    const auto bits = static_cast<std::uint64_t>(bit_cast<bits_type>(value));
     const std::uint64_t E = bits >> (kPrecision - 1);
     const std::uint64_t F = bits & (kHiddenBit - 1);
 
@@ -1084,13 +1072,10 @@ inline std::uint64_t eight_digit_bytes(std::uint64_t abcdefgh) noexcept
 /// the byte stores once this is inlined)
 inline void store_msb_first(char* p, std::uint64_t v) noexcept
 {
-#if defined(__BYTE_ORDER__) && defined(__ORDER_LITTLE_ENDIAN__) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+#if JSON_LITTLE_ENDIAN_TARGET
-    v = __builtin_bswap64(v);
+    v = byteswap(v);
     std::memcpy(p, &v, sizeof(v));
-#elif defined(__BYTE_ORDER__) && defined(__ORDER_BIG_ENDIAN__) && __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+#elif JSON_BIG_ENDIAN_TARGET
-    std::memcpy(p, &v, sizeof(v));
-#elif defined(_MSC_VER) // (little-endian on all its targets)
-    v = _byteswap_uint64(v);
     std::memcpy(p, &v, sizeof(v));
 #else
     for (unsigned i = 0; i < 8; ++i)
@@ -1462,8 +1447,7 @@ char* write_positive_zmij(char* first, const char* last, FloatType value)
 {
     static_assert(is_binary64<FloatType>::value,
                   "internal error: the conversion of Zmij needs IEEE 754 binary64 numbers");
-    std::uint64_t bits = 0;
+    const auto bits = bit_cast<std::uint64_t>(value);
-    std::memcpy(&bits, &value, sizeof(bits));
     const zmij::shortest_decimal d = zmij::to_shortest(bits);
     if (JSON_HEDLEY_LIKELY(last - first >= 41))
     {

include/nlohmann/detail/exceptions.hpp

@@ -66,6 +66,7 @@ enum class exception_id : int
     invalid_string_or_size = 113, ///< a binary input contains an invalid string or size specification
     bson_unsupported_type = 114, ///< a BSON record type is not supported
     invalid_high_precision_number = 115, ///< a UBJSON/BJData high-precision number cannot be parsed
+    invalid_document_image = 116, ///< json_document::load() rejects an image
     // invalid_iterator
     iterators_incompatible = 201, ///< the iterators of a range belong to different values
     iterator_from_other_value = 202, ///< an iterator does not belong to the value it is used with
@@ -100,6 +101,8 @@ enum class exception_id : int
     invalid_utf8 = 316, ///< dump() finds a string that is not valid UTF-8
     type_not_serializable = 317, ///< a value cannot be serialized to the requested binary format
     enum_key_duplicate = 318, ///< an enum-keyed map has two keys that serialize to the same string
+    document_binary_value = 319, ///< a binary value is stored in a json_document
+    document_image_unsupported = 320, ///< a json_document image cannot be saved or loaded (discarded document, big-endian target)
     discarded_value_used = 321, ///< a discarded value is used
     // out_of_range
     array_index_out_of_range = 401, ///< an array index is out of range
@@ -117,6 +120,7 @@ enum class exception_id : int
     patch_remove_parent_not_container = 413, ///< the parent of a JSON Patch 'remove' target is not a container
     patch_move_into_child = 414, ///< a JSON Patch 'move' moves a value into one of its children
     subtype_out_of_range = 415, ///< a binary subtype does not fit into one byte
+    document_too_large = 416, ///< a json_document input, its edit storage, or an image reaches the 32-bit (4 GiB) limit
     // other_error
     internal_error = 500, ///< unreachable code was reached
     patch_test_failed = 501, ///< a JSON Patch 'test' operation failed
@@ -146,6 +150,13 @@ class exception : public std::exception
         return concat("[json.exception.", ename, '.', std::to_string(id_), "] ");
     }
 
+    /// build the message "[json.exception.<ename>.<id>] <diagnostics><what_arg>"
+    template<typename BasicJsonContext>
+    static std::string what_impl(const std::string& ename, int id_, const std::string& what_arg, BasicJsonContext context)
+    {
+        return concat(name(ename, id_), diagnostics(context), what_arg);
+    }
+
     static std::string diagnostics(std::nullptr_t /*leaf_element*/)
     {
         return "";
@@ -158,48 +169,33 @@ class exception : public std::exception
         std::vector<std::string> tokens;
         for (const auto* current = leaf_element; current != nullptr && current->m_parent != nullptr; current = current->m_parent)
         {
-            switch (current->m_parent->type())
+            const auto* parent = current->m_parent;
+            if (parent->is_array())
             {
-                case value_t::array:
+                for (std::size_t i = 0; i < parent->m_data.m_value.array->size(); ++i)
                 {
-                    for (std::size_t i = 0; i < current->m_parent->m_data.m_value.array->size(); ++i)
+                    if (&parent->m_data.m_value.array->operator[](i) == current)
                     {
-                        if (&current->m_parent->m_data.m_value.array->operator[](i) == current)
+                        tokens.emplace_back(std::to_string(i));
-                        {
+                        break;
-                            tokens.emplace_back(std::to_string(i));
-                            break;
-                        }
                     }
-                    break;
                 }
-
-                case value_t::object:
-                {
-                    for (const auto& element : *current->m_parent->m_data.m_value.object)
-                    {
-                        if (&element.second == current)
-                        {
-                            // data() is null-terminated, so a key containing
-                            // a null byte is cut short here rather than
-                            // truncating the whole message at what()
-                            tokens.emplace_back(element.first.data());
-                            break;
-                        }
-                    }
-                    break;
-                }
-
-                case value_t::null: // LCOV_EXCL_LINE
-                case value_t::string: // LCOV_EXCL_LINE
-                case value_t::boolean: // LCOV_EXCL_LINE
-                case value_t::number_integer: // LCOV_EXCL_LINE
-                case value_t::number_unsigned: // LCOV_EXCL_LINE
-                case value_t::number_float: // LCOV_EXCL_LINE
-                case value_t::binary: // LCOV_EXCL_LINE
-                case value_t::discarded: // LCOV_EXCL_LINE
-                default:   // LCOV_EXCL_LINE
-                    break; // LCOV_EXCL_LINE
             }
+            else if (parent->is_object())
+            {
+                for (const auto& element : *parent->m_data.m_value.object)
+                {
+                    if (&element.second == current)
+                    {
+                        // data() is null-terminated, so a key containing
+                        // a null byte is cut short here rather than
+                        // truncating the whole message at what()
+                        tokens.emplace_back(element.first.data());
+                        break;
+                    }
+                }
+            }
+            // all other parent types (primitives) contribute no token
         }
 
         if (tokens.empty())
@@ -315,7 +311,7 @@ class invalid_iterator : public exception
     template<typename BasicJsonContext, enable_if_t<is_basic_json_context<BasicJsonContext>::value, int> = 0>
     static invalid_iterator create(int id_, const std::string& what_arg, BasicJsonContext context)
     {
-        const std::string w = concat(exception::name("invalid_iterator", id_), exception::diagnostics(context), what_arg);
+        const std::string w = exception::what_impl("invalid_iterator", id_, what_arg, context);
         return {id_, w.c_str()};
     }
 
@@ -339,7 +335,7 @@ class type_error : public exception
     template<typename BasicJsonContext, enable_if_t<is_basic_json_context<BasicJsonContext>::value, int> = 0>
     static type_error create(int id_, const std::string& what_arg, BasicJsonContext context)
     {
-        const std::string w = concat(exception::name("type_error", id_), exception::diagnostics(context), what_arg);
+        const std::string w = exception::what_impl("type_error", id_, what_arg, context);
         return {id_, w.c_str()};
     }
 
@@ -362,7 +358,7 @@ class out_of_range : public exception
     template<typename BasicJsonContext, enable_if_t<is_basic_json_context<BasicJsonContext>::value, int> = 0>
     static out_of_range create(int id_, const std::string& what_arg, BasicJsonContext context)
     {
-        const std::string w = concat(exception::name("out_of_range", id_), exception::diagnostics(context), what_arg);
+        const std::string w = exception::what_impl("out_of_range", id_, what_arg, context);
         return {id_, w.c_str()};
     }
 
@@ -385,7 +381,7 @@ class other_error : public exception
     template<typename BasicJsonContext, enable_if_t<is_basic_json_context<BasicJsonContext>::value, int> = 0>
     static other_error create(int id_, const std::string& what_arg, BasicJsonContext context)
     {
-        const std::string w = concat(exception::name("other_error", id_), exception::diagnostics(context), what_arg);
+        const std::string w = exception::what_impl("other_error", id_, what_arg, context);
         return {id_, w.c_str()};
     }
 

include/nlohmann/detail/input/binary_reader.hpp

@@ -293,6 +293,40 @@ class binary_reader
         return is_object ? sax->end_object() : sax->end_array();
     }
 
+    /*!
+    @brief close the innermost open container and report whether that
+           completed the value being read
+
+    The value begun by the driver is complete once its container is not
+    inside another one.
+
+    @param[out] value_complete  whether no container is left open
+    @return whether the SAX parser accepted the end event
+    */
+    bool leave_container_and_check(bool& value_complete)
+    {
+        if (JSON_HEDLEY_UNLIKELY(!leave_container()))
+        {
+            return false;
+        }
+        value_complete = container_stack.empty();
+        return true;
+    }
+
+    /*!
+    @brief read an object key and pass it to the SAX parser
+
+    @tparam GetKey  member function that reads the key into a string
+    @param[in,out] key  string the key is read into; cleared first
+    @return whether reading the key and the SAX event succeeded
+    */
+    template<bool (binary_reader::*GetKey)(string_t&)>
+    bool read_object_key(string_t& key)
+    {
+        key.clear();
+        return (this->*GetKey)(key) && sax->key(key);
+    }
+
     //////////
     // BSON //
     //////////
@@ -1064,6 +1098,34 @@ class binary_reader
         return last_byte_error(exception_id::invalid_string_or_size, concat("indefinite-length ", type_name, " is not allowed inside indefinite-length ", type_name, "; last byte: 0x", get_token_string()), context);
     }
 
+    /*!
+    @brief report an object key that is not a string
+
+    @param[in] found  description of what was found instead of a string key
+    @return false
+    */
+    bool unsupported_key_type(const char* found) const
+    {
+        return last_byte_error(exception_id::invalid_string_or_size, "only string keys are supported, but found ", "object key", found);
+    }
+
+    /*!
+    @brief read the length of a CBOR string or byte array and then its bytes
+
+    @tparam NumberType    the type of the length field
+    @tparam ContainerType the destination container (string_t or binary_t)
+    @param[in] context  further context information (for diagnostics)
+    @param[out] result  container the bytes are appended to
+
+    @return whether reading completed
+    */
+    template<typename NumberType, typename ContainerType>
+    bool get_cbor_sized_bytes(const char* context, ContainerType& result)
+    {
+        NumberType len{};
+        return get_number(len) && get_bytes(len, context, result);
+    }
+
     /*!
     @brief reads a definite-length CBOR string
 
@@ -1114,26 +1176,22 @@ class binary_reader
 
             case 0x78: // UTF-8 string (one-byte uint8_t for n follows)
             {
-                std::uint8_t len{};
+                return get_cbor_sized_bytes<std::uint8_t>("string", result);
-                return get_number(len) && get_string(len, result);
             }
 
             case 0x79: // UTF-8 string (two-byte uint16_t for n follow)
             {
-                std::uint16_t len{};
+                return get_cbor_sized_bytes<std::uint16_t>("string", result);
-                return get_number(len) && get_string(len, result);
             }
 
             case 0x7A: // UTF-8 string (four-byte uint32_t for n follow)
             {
-                std::uint32_t len{};
+                return get_cbor_sized_bytes<std::uint32_t>("string", result);
-                return get_number(len) && get_string(len, result);
             }
 
             case 0x7B: // UTF-8 string (eight-byte uint64_t for n follow)
             {
-                std::uint64_t len{};
+                return get_cbor_sized_bytes<std::uint64_t>("string", result);
-                return get_number(len) && get_string(len, result);
             }
 
             default:
@@ -1268,7 +1326,7 @@ class binary_reader
                 break;
         }
 
-        return last_byte_error(exception_id::invalid_string_or_size, "only string keys are supported, but found ", "object key", found);
+        return unsupported_key_type(found);
     }
 
     /*!
@@ -1321,30 +1379,22 @@ class binary_reader
 
             case 0x58: // Binary data (one-byte uint8_t for n follows)
             {
-                std::uint8_t len{};
+                return get_cbor_sized_bytes<std::uint8_t>("binary", result);
-                return get_number(len) &&
-                       get_binary(len, result);
             }
 
             case 0x59: // Binary data (two-byte uint16_t for n follow)
             {
-                std::uint16_t len{};
+                return get_cbor_sized_bytes<std::uint16_t>("binary", result);
-                return get_number(len) &&
-                       get_binary(len, result);
             }
 
             case 0x5A: // Binary data (four-byte uint32_t for n follow)
             {
-                std::uint32_t len{};
+                return get_cbor_sized_bytes<std::uint32_t>("binary", result);
-                return get_number(len) &&
-                       get_binary(len, result);
             }
 
             case 0x5B: // Binary data (eight-byte uint64_t for n follow)
             {
-                std::uint64_t len{};
+                return get_cbor_sized_bytes<std::uint64_t>("binary", result);
-                return get_number(len) &&
-                       get_binary(len, result);
             }
 
             default:
@@ -1559,12 +1609,12 @@ class binary_reader
 
                 if (at_end)
                 {
-                    if (JSON_HEDLEY_UNLIKELY(!leave_container()))
+                    bool value_complete = false;
+                    if (JSON_HEDLEY_UNLIKELY(!leave_container_and_check(value_complete)))
                     {
                         return false;
                     }
-                    // the value begun here is complete once its container is
+                    if (value_complete)
-                    if (container_stack.empty())
                     {
                         return true;
                     }
@@ -1573,8 +1623,7 @@ class binary_reader
 
                 if (top.is_object)
                 {
-                    key.clear();
+                    if (JSON_HEDLEY_UNLIKELY(!read_object_key<&binary_reader::get_cbor_object_key>(key)))
-                    if (JSON_HEDLEY_UNLIKELY(!get_cbor_object_key(key) || !sax->key(key)))
                     {
                         return false;
                     }
@@ -2045,20 +2094,17 @@ class binary_reader
 
             case 0xD9: // str 8
             {
-                std::uint8_t len{};
+                return get_string_with_length<std::uint8_t>(result, context);
-                return get_number(len) && get_string(len, result) && check_string_utf8(result, context);
             }
 
             case 0xDA: // str 16
             {
-                std::uint16_t len{};
+                return get_string_with_length<std::uint16_t>(result, context);
-                return get_number(len) && get_string(len, result) && check_string_utf8(result, context);
             }
 
             case 0xDB: // str 32
             {
-                std::uint32_t len{};
+                return get_string_with_length<std::uint32_t>(result, context);
-                return get_number(len) && get_string(len, result) && check_string_utf8(result, context);
             }
 
             default:
@@ -2155,7 +2201,7 @@ class binary_reader
                 break;
         }
 
-        return last_byte_error(exception_id::invalid_string_or_size, "only string keys are supported, but found ", "object key", found);
+        return unsupported_key_type(found);
     }
 
     /*!
@@ -2300,12 +2346,12 @@ class binary_reader
 
                 if (container_stack.back().remaining == 0)
                 {
-                    if (JSON_HEDLEY_UNLIKELY(!leave_container()))
+                    bool value_complete = false;
+                    if (JSON_HEDLEY_UNLIKELY(!leave_container_and_check(value_complete)))
                     {
                         return false;
                     }
-                    // the value begun here is complete once its container is
+                    if (value_complete)
-                    if (container_stack.empty())
                     {
                         return true;
                     }
@@ -2318,8 +2364,7 @@ class binary_reader
                 if (is_object)
                 {
                     get();
-                    key.clear();
+                    if (JSON_HEDLEY_UNLIKELY(!read_object_key<&binary_reader::get_msgpack_object_key>(key)))
-                    if (JSON_HEDLEY_UNLIKELY(!get_msgpack_object_key(key) || !sax->key(key)))
                     {
                         return false;
                     }
@@ -2503,8 +2548,7 @@ class binary_reader
         {
             case 'U':
             {
-                std::uint8_t len{};
+                return get_string_with_length<std::uint8_t>(result, context);
-                return get_number(len) && get_string(len, result) && check_string_utf8(result, context);
             }
 
             case 'i':
@@ -2537,8 +2581,7 @@ class binary_reader
                 {
                     break;
                 }
-                std::uint16_t len{};
+                return get_string_with_length<std::uint16_t>(result, context);
-                return get_number(len) && get_string(len, result) && check_string_utf8(result, context);
             }
 
             case 'm':
@@ -2547,8 +2590,7 @@ class binary_reader
                 {
                     break;
                 }
-                std::uint32_t len{};
+                return get_string_with_length<std::uint32_t>(result, context);
-                return get_number(len) && get_string(len, result) && check_string_utf8(result, context);
             }
 
             case 'M':
@@ -2557,8 +2599,7 @@ class binary_reader
                 {
                     break;
                 }
-                std::uint64_t len{};
+                return get_string_with_length<std::uint64_t>(result, context);
-                return get_number(len) && get_string(len, result) && check_string_utf8(result, context);
             }
 
             default:
@@ -3374,12 +3415,12 @@ class binary_reader
 
                 if (at_end)
                 {
-                    if (JSON_HEDLEY_UNLIKELY(!leave_container()))
+                    bool value_complete = false;
+                    if (JSON_HEDLEY_UNLIKELY(!leave_container_and_check(value_complete)))
                     {
                         return false;
                     }
-                    // the value begun here is complete once its container is
+                    if (value_complete)
-                    if (container_stack.empty())
                     {
                         return true;
                     }
@@ -3388,8 +3429,7 @@ class binary_reader
 
                 if (top.is_object)
                 {
-                    key.clear();
+                    if (JSON_HEDLEY_UNLIKELY(!read_object_key<&binary_reader::get_bon8_key>(key)))
-                    if (JSON_HEDLEY_UNLIKELY(!get_bon8_key(key) || !sax->key(key)))
                     {
                         return false;
                     }
@@ -4129,6 +4169,22 @@ class binary_reader
         return true;
     }
 
+    /*!
+    @brief read a length of type @a NumberType, then a string of that many bytes
+
+    @tparam NumberType  the type of the length field
+    @param[out] result  string the bytes are appended to
+    @param[in] context  further context information (for diagnostics)
+
+    @return whether reading and validating the string succeeded
+    */
+    template<typename NumberType>
+    bool get_string_with_length(string_t& result, const char* context)
+    {
+        NumberType len{};
+        return get_number(len) && get_string(len, result) && check_string_utf8(result, context);
+    }
+
     /*!
     @brief create a byte array by reading bytes from the input
 
@@ -4338,37 +4394,7 @@ class binary_reader
                                   const std::string& context) const
     {
         std::string error_msg = "syntax error while parsing ";
-
+        error_msg += input_format_name(input_format);
-        switch (input_format)
-        {
-            case input_format_t::cbor:
-                error_msg += "CBOR";
-                break;
-
-            case input_format_t::msgpack:
-                error_msg += "MessagePack";
-                break;
-
-            case input_format_t::ubjson:
-                error_msg += "UBJSON";
-                break;
-
-            case input_format_t::bson:
-                error_msg += "BSON";
-                break;
-
-            case input_format_t::bjdata:
-                error_msg += "BJData";
-                break;
-
-            case input_format_t::bon8:
-                error_msg += "BON8";
-                break;
-
-            case input_format_t::json: // LCOV_EXCL_LINE
-            default:            // LCOV_EXCL_LINE
-                JSON_ASSERT(false); // NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert) LCOV_EXCL_LINE
-        }
 
         return concat(error_msg, ' ', context, ": ", detail);
     }

include/nlohmann/detail/input/input_adapters.hpp

@@ -8,17 +8,18 @@
 
 #pragma once
 
-#include <algorithm> // count, find, min
+#include <algorithm> // count, find, max, min
 #include <array> // array
 #include <cstddef> // size_t
 #include <cstdint> // uint32_t
 #include <cstring> // strlen
 #include <iterator> // begin, end, iterator_traits, random_access_iterator_tag, distance, next, reverse_iterator
 #include <limits> // numeric_limits
+#include <memory> // unique_ptr
 #include <streambuf> // streambuf
 #include <string> // string, char_traits
 #include <type_traits> // enable_if, is_base_of, is_pointer, is_integral, remove_pointer
-#include <utility> // pair, declval
+#include <utility> // declval, move, pair
 #include <vector> // vector
 
 #ifndef JSON_NO_IO
@@ -66,12 +67,118 @@ namespace detail
 /// the supported input formats
 enum class input_format_t { json, cbor, msgpack, ubjson, bson, bjdata, bon8 };
 
+/// @return the name of a binary input format, as used in exception messages
+inline const char* input_format_name(const input_format_t format) noexcept
+{
+    switch (format)
+    {
+        case input_format_t::cbor:
+            return "CBOR";
+        case input_format_t::msgpack:
+            return "MessagePack";
+        case input_format_t::ubjson:
+            return "UBJSON";
+        case input_format_t::bson:
+            return "BSON";
+        case input_format_t::bjdata:
+            return "BJData";
+        case input_format_t::bon8:
+            return "BON8";
+        case input_format_t::json: // LCOV_EXCL_LINE
+        default:            // LCOV_EXCL_LINE
+            JSON_ASSERT(false); // NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert) LCOV_EXCL_LINE
+            return ""; // LCOV_EXCL_LINE
+    }
+}
+
+/// @return the message of the parse_error thrown or reported for an empty input
+inline const char* empty_input_message() noexcept
+{
+    return "attempting to parse an empty input; check that your input string or stream contains the expected JSON";
+}
+
 ////////////////////
 // input adapters //
 ////////////////////
 
 #ifndef JSON_NO_IO
 /*!
+A growable array of characters for the part of a token that an input adapter
+copied out of its window: unlike std::vector<char>::push_back(), appending a
+character takes no reference to a local, and is a few instructions when there
+is room.
+*/
+class token_carry_buffer
+{
+  public:
+    token_carry_buffer() = default;
+    token_carry_buffer(const token_carry_buffer&) = delete;
+    token_carry_buffer& operator=(const token_carry_buffer&) = delete;
+    token_carry_buffer(token_carry_buffer&& rhs) noexcept
+        : m_data(std::move(rhs.m_data)), m_end(rhs.m_end), m_capacity_end(rhs.m_capacity_end)
+    {
+        rhs.m_end = rhs.m_capacity_end = nullptr;
+    }
+    token_carry_buffer& operator=(token_carry_buffer&&) = delete;
+    ~token_carry_buffer() = default;
+
+    void clear() noexcept
+    {
+        m_end = m_data.get();
+    }
+
+    void push_back(char c)
+    {
+        if (JSON_HEDLEY_UNLIKELY(m_end == m_capacity_end))
+        {
+            grow(1);
+        }
+        *m_end++ = c;
+    }
+
+    void append(const char* first, const char* last)
+    {
+        const auto n = static_cast<std::size_t>(last - first);
+        const auto room = static_cast<std::size_t>(m_capacity_end - m_end);
+        if (n > room)
+        {
+            grow(n);
+        }
+        if (n != 0)
+        {
+            std::memcpy(m_end, first, n);
+        }
+        m_end += n;
+    }
+
+    /// replace the contents of @a out
+    void copy_to(std::vector<char>& out) const
+    {
+        out.assign(m_data.get(), m_end);
+    }
+
+  private:
+    /// make room for @a extra more characters
+    JSON_HEDLEY_NEVER_INLINE void grow(std::size_t extra)
+    {
+        const auto size = static_cast<std::size_t>(m_end - m_data.get());
+        const auto capacity = static_cast<std::size_t>(m_capacity_end - m_data.get());
+        const std::size_t new_capacity = (std::max)(capacity < 32 ? static_cast<std::size_t>(32) : 2 * capacity, size + extra);
+        std::unique_ptr<char[]> data(new char[new_capacity]); // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+        if (size != 0)
+        {
+            std::memcpy(data.get(), m_data.get(), size);
+        }
+        m_data = std::move(data);
+        m_end = m_data.get() + size;
+        m_capacity_end = m_data.get() + new_capacity;
+    }
+
+    std::unique_ptr<char[]> m_data{}; // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays,readability-redundant-member-init)
+    char* m_end = nullptr;
+    char* m_capacity_end = nullptr;
+};
+/*!
 Input adapter for stdio file access. This adapter read only 1 byte and do not use any
  buffer. This adapter is a very low level adapter.
 */
@@ -209,6 +316,7 @@ class input_stream_adapter
         , token_segment(rhs.token_segment)
         , current_in_get_area(rhs.current_in_get_area)
         , tracking_token(rhs.tracking_token)
+        , no_get_area(rhs.no_get_area)
 #endif
     {
         rhs.is = nullptr;
@@ -295,37 +403,20 @@ class input_stream_adapter
     std::char_traits<char>::int_type get_character()
     {
 #if !JSON_DISABLE_STREAM_BULK_SCAN
-        // sbumpc() refills the get area if it is exhausted
+        // the character is in the get area: step over it, as sbumpc() does
-        const bool refill = streambuf_access::get_ptr(sb) == streambuf_access::get_end(sb);
+        const char* const next = streambuf_access::get_ptr(sb);
-        if (JSON_HEDLEY_UNLIKELY(refill))
+        if (JSON_HEDLEY_LIKELY(next != streambuf_access::get_end(sb)))
-        {
-            save_token_segment();
-        }
-#endif
-
-        auto res = sb->sbumpc();
-        // set eof manually, as we don't use the istream interface.
-        if (JSON_HEDLEY_UNLIKELY(res == std::char_traits<char>::eof()))
-        {
-#if !JSON_DISABLE_STREAM_BULK_SCAN
-            current_in_get_area = false;
-#endif
-            is->clear(is->rdstate() | std::ios::eofbit);
-        }
-#if !JSON_DISABLE_STREAM_BULK_SCAN
-        else if (JSON_HEDLEY_UNLIKELY(refill))
-        {
-            // the consumed character is at gptr() - 1, unless the streambuf
-            // has no get area and returned it from uflow()
-            const char* const next = streambuf_access::get_ptr(sb);
-            after_refill(res, next != nullptr && next != streambuf_access::get_begin(sb));
-        }
-        else
         {
             current_in_get_area = true;
+            streambuf_access::bump(sb, 1);
+            return std::char_traits<char>::to_int_type(*next);
+        }
+        if (no_get_area)
+        {
+            return get_character_no_get_area();
         }
 #endif
-        return res;
+        return get_character_slow();
     }
 #endif
 
@@ -334,6 +425,18 @@ class input_stream_adapter
     {
 #if JSON_PRECISE_STREAM_POSITION
         commit_lookahead();
+#endif
+#if !JSON_DISABLE_STREAM_BULK_SCAN
+        // the elements are in the get area: copy them, as sgetn() does, but
+        // without the virtual call
+        const char* const first = streambuf_access::get_ptr(sb);
+        const auto available = static_cast<std::size_t>(streambuf_access::get_end(sb) - first);
+        if (JSON_HEDLEY_LIKELY(count * sizeof(T) <= available && count * sizeof(T) <= static_cast<std::size_t>((std::numeric_limits<int>::max)())))
+        {
+            std::memcpy(dest, first, count * sizeof(T));
+            streambuf_access::bump(sb, static_cast<int>(count * sizeof(T)));
+            return count * sizeof(T);
+        }
 #endif
         auto res = static_cast<std::size_t>(sb->sgetn(reinterpret_cast<char*>(dest), static_cast<std::streamsize>(count * sizeof(T))));
         if (JSON_HEDLEY_UNLIKELY(res < count * sizeof(T)))
@@ -421,7 +524,7 @@ class input_stream_adapter
     // last one if @a drop_last.
     void copy_token(std::vector<char>& out, bool drop_last) const
     {
-        out = token_carry;
+        token_carry.copy_to(out);
         if (token_segment != nullptr)
         {
             out.insert(out.end(), token_segment, current_end());
@@ -434,6 +537,47 @@ class input_stream_adapter
 #endif
 
   private:
+#if !JSON_PRECISE_STREAM_POSITION
+    // the get area is exhausted, or there is none
+#if !JSON_DISABLE_STREAM_BULK_SCAN
+    JSON_HEDLEY_NEVER_INLINE
+#endif
+    std::char_traits<char>::int_type get_character_slow()
+    {
+#if !JSON_DISABLE_STREAM_BULK_SCAN
+        // sbumpc() refills the get area if it is exhausted
+        const bool refill = streambuf_access::get_ptr(sb) == streambuf_access::get_end(sb);
+        if (JSON_HEDLEY_UNLIKELY(refill))
+        {
+            save_token_segment();
+        }
+#endif
+
+        auto res = sb->sbumpc();
+        // set eof manually, as we don't use the istream interface.
+        if (JSON_HEDLEY_UNLIKELY(res == std::char_traits<char>::eof()))
+        {
+#if !JSON_DISABLE_STREAM_BULK_SCAN
+            current_in_get_area = false;
+#endif
+            is->clear(is->rdstate() | std::ios::eofbit);
+        }
+#if !JSON_DISABLE_STREAM_BULK_SCAN
+        else if (JSON_HEDLEY_UNLIKELY(refill))
+        {
+            // the consumed character is at gptr() - 1, unless the streambuf
+            // has no get area and returned it from uflow()
+            const char* const next = streambuf_access::get_ptr(sb);
+            after_refill(res, next != nullptr && next != streambuf_access::get_begin(sb));
+        }
+        else
+        {
+            current_in_get_area = true;
+        }
+#endif
+        return res;
+    }
+#endif
 #if !JSON_DISABLE_STREAM_BULK_SCAN
     // Reads the protected get-area pointers of any std::streambuf. Naming the
     // members through a derived class makes forming the member pointers
@@ -457,6 +601,11 @@ class input_stream_adapter
         {
             (s->*(&streambuf_access::gbump))(n);
         }
+        // sbumpc() for an exhausted get area
+        static std::streambuf::int_type next_character(std::streambuf* s)
+        {
+            return (s->*(&streambuf_access::uflow))();
+        }
     };
 
     // one past the character last returned by get_character(), if that is in
@@ -477,16 +626,53 @@ class input_stream_adapter
     {
         if (token_segment != nullptr)
         {
-            token_carry.insert(token_carry.end(), token_segment, streambuf_access::get_end(sb));
+            token_carry.append(token_segment, streambuf_access::get_end(sb));
             token_segment = nullptr;
         }
     }
 
+#if !JSON_PRECISE_STREAM_POSITION
+    // The streambuf has no get area (e.g., std::cin synchronized with stdio):
+    // every character comes from uflow(), and the token is kept by value.
+    JSON_HEDLEY_NEVER_INLINE std::char_traits<char>::int_type get_character_no_get_area()
+    {
+        // the get area is exhausted, so this is what sbumpc() does
+        const auto res = streambuf_access::next_character(sb);
+        if (JSON_HEDLEY_UNLIKELY(res == std::char_traits<char>::eof() || streambuf_access::get_end(sb) != nullptr))
+        {
+            return get_character_no_get_area_other(res);
+        }
+        // current_in_get_area is false: only the first character of a get
+        // area, or the end of the input, is read here
+        if (tracking_token)
+        {
+            token_carry.push_back(std::char_traits<char>::to_char_type(res));
+        }
+        return res;
+    }
+
+    // @a res came from uflow() of a streambuf without a get area: it is the
+    // end of the input, or the streambuf has a get area now
+    JSON_HEDLEY_NEVER_INLINE std::char_traits<char>::int_type get_character_no_get_area_other(std::char_traits<char>::int_type res)
+    {
+        if (res == std::char_traits<char>::eof())
+        {
+            current_in_get_area = false;
+            is->clear(is->rdstate() | std::ios::eofbit);
+            return res;
+        }
+        // the consumed character is at gptr() - 1
+        after_refill(res, streambuf_access::get_ptr(sb) != streambuf_access::get_begin(sb));
+        return res;
+    }
+#endif
+
     // character @a c was just read into a new get area (@a in_get_area) or
     // returned without one
     void after_refill(std::char_traits<char>::int_type c, bool in_get_area)
     {
         current_in_get_area = in_get_area;
+        no_get_area = !in_get_area;
         if (!tracking_token)
         {
             return;
@@ -525,13 +711,16 @@ class input_stream_adapter
 #endif
 #if !JSON_DISABLE_STREAM_BULK_SCAN
     /// the part of the current token that was in earlier get areas
-    std::vector<char> token_carry{}; // NOLINT(readability-redundant-member-init)
+    token_carry_buffer token_carry{}; // NOLINT(readability-redundant-member-init)
     /// start of the current token's part in the get area, or nullptr
     const char* token_segment = nullptr;
     /// whether the character last returned by get_character() is in the get area
     bool current_in_get_area = false;
     /// whether a token is tracked at all; the binary readers never start one
     bool tracking_token = false;
+    /// whether the streambuf had no get area when it was last asked for a
+    /// character
+    bool no_get_area = false;
 #endif
 };
 #endif  // JSON_NO_IO
@@ -1109,7 +1298,7 @@ inline file_input_adapter input_adapter(std::FILE* file)
 {
     if (file == nullptr)
     {
-        JSON_THROW(parse_error::create(exception_id::syntax_error, 0, "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
+        JSON_THROW(parse_error::create(exception_id::syntax_error, 0, empty_input_message(), nullptr));
     }
     return file_input_adapter(file);
 }
@@ -1118,7 +1307,7 @@ inline input_stream_adapter input_adapter(std::istream& stream)
 {
     if (stream.rdbuf() == nullptr)
     {
-        JSON_THROW(parse_error::create(exception_id::syntax_error, 0, "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
+        JSON_THROW(parse_error::create(exception_id::syntax_error, 0, empty_input_message(), nullptr));
     }
     return input_stream_adapter(stream);
 }
@@ -1143,7 +1332,7 @@ contiguous_bytes_input_adapter input_adapter(CharT b)
 {
     if (b == nullptr)
     {
-        JSON_THROW(parse_error::create(exception_id::syntax_error, 0, "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
+        JSON_THROW(parse_error::create(exception_id::syntax_error, 0, empty_input_message(), nullptr));
     }
     auto length = std::strlen(reinterpret_cast<const char*>(b));
     const auto* ptr = reinterpret_cast<const char*>(b);

include/nlohmann/detail/input/json_sax.hpp

@@ -315,6 +315,52 @@ struct diagnostic_positions
 };
 #endif
 
+/*!
+@brief error state shared by the DOM-building SAX parsers
+
+Holds whether a parse error occurred and whether errors are thrown, and
+implements the parse_error() and is_errored() members of the SAX interface for
+json_sax_dom_parser and json_sax_dom_callback_parser.
+*/
+class json_sax_dom_error_state
+{
+  public:
+    explicit json_sax_dom_error_state(const bool allow_exceptions_) noexcept
+        : allow_exceptions(allow_exceptions_)
+    {}
+
+    // make class move-only
+    json_sax_dom_error_state(const json_sax_dom_error_state&) = delete;
+    json_sax_dom_error_state(json_sax_dom_error_state&&) = default; // NOLINT(hicpp-noexcept-move,performance-noexcept-move-constructor)
+    json_sax_dom_error_state& operator=(const json_sax_dom_error_state&) = delete;
+    json_sax_dom_error_state& operator=(json_sax_dom_error_state&&) = delete; // the const member prevents assignment
+    ~json_sax_dom_error_state() = default;
+
+    template<class Exception>
+    bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/,
+                     const Exception& ex)
+    {
+        errored = true;
+        static_cast<void>(ex);
+        if (allow_exceptions)
+        {
+            JSON_THROW(ex);
+        }
+        return false;
+    }
+
+    bool is_errored() const
+    {
+        return errored;
+    }
+
+  private:
+    /// whether a syntax error occurred
+    bool errored = false;
+    /// whether to throw exceptions in case of errors
+    const bool allow_exceptions = true;
+};
+
 /*!
 @brief SAX implementation to create a JSON value from SAX events
 
@@ -329,7 +375,7 @@ constructor contains the parsed value.
 @tparam BasicJsonType  the JSON type
 */
 template<typename BasicJsonType, typename InputAdapterType>
-class json_sax_dom_parser
+class json_sax_dom_parser : public json_sax_dom_error_state
 {
   public:
     using number_integer_t = typename BasicJsonType::number_integer_t;
@@ -345,7 +391,7 @@ class json_sax_dom_parser
     @param[in] allow_exceptions_  whether parse errors yield exceptions
     */
     explicit json_sax_dom_parser(BasicJsonType& r, const bool allow_exceptions_ = true, lexer_t* lexer_ = nullptr)
-        : root(r), allow_exceptions(allow_exceptions_), m_lexer_ref(lexer_)
+        : json_sax_dom_error_state(allow_exceptions_), root(r), m_lexer_ref(lexer_)
     {}
 
     // make class move-only
@@ -418,8 +464,9 @@ class json_sax_dom_parser
         JSON_ASSERT(!ref_stack.empty());
         JSON_ASSERT(ref_stack.back()->is_object());
 
-        // add null at the given key and store the reference for later
+        // add null at the given key and store the reference for later; the
-        object_element = &(ref_stack.back()->m_data.m_value.object->operator[](val));
+        // key is moved, as the lexer starts the next token with reset()
+        object_element = &(ref_stack.back()->m_data.m_value.object->operator[](std::move(val)));
         return true;
     }
 
@@ -473,24 +520,6 @@ class json_sax_dom_parser
         return true;
     }
 
-    template<class Exception>
-    bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/,
-                     const Exception& ex)
-    {
-        errored = true;
-        static_cast<void>(ex);
-        if (allow_exceptions)
-        {
-            JSON_THROW(ex);
-        }
-        return false;
-    }
-
-    constexpr bool is_errored() const
-    {
-        return errored;
-    }
-
   private:
 
     /*!
@@ -544,16 +573,12 @@ class json_sax_dom_parser
     std::vector<BasicJsonType*> ref_stack {};
     /// helper to hold the reference for the next object element
     BasicJsonType* object_element = nullptr;
-    /// whether a syntax error occurred
-    bool errored = false;
-    /// whether to throw exceptions in case of errors
-    const bool allow_exceptions = true;
     /// the lexer reference to obtain the current position
     lexer_t* m_lexer_ref = nullptr;
 };
 
 template<typename BasicJsonType, typename InputAdapterType>
-class json_sax_dom_callback_parser
+class json_sax_dom_callback_parser : public json_sax_dom_error_state
 {
   public:
     using number_integer_t = typename BasicJsonType::number_integer_t;
@@ -569,7 +594,7 @@ class json_sax_dom_callback_parser
                                  parser_callback_t cb,
                                  const bool allow_exceptions_ = true,
                                  lexer_t* lexer_ = nullptr)
-        : root(r), callback(std::move(cb)), allow_exceptions(allow_exceptions_), m_lexer_ref(lexer_)
+        : json_sax_dom_error_state(allow_exceptions_), root(r), callback(std::move(cb)), m_lexer_ref(lexer_)
     {
         keep_stack.push_back(true);
     }
@@ -836,24 +861,6 @@ class json_sax_dom_callback_parser
         return true;
     }
 
-    template<class Exception>
-    bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/,
-                     const Exception& ex)
-    {
-        errored = true;
-        static_cast<void>(ex);
-        if (allow_exceptions)
-        {
-            JSON_THROW(ex);
-        }
-        return false;
-    }
-
-    constexpr bool is_errored() const
-    {
-        return errored;
-    }
-
   private:
 
     /// if there is a pending duplicate-key stash entry for this exact slot,
@@ -1095,12 +1102,8 @@ class json_sax_dom_callback_parser
     /// value is later rejected by the callback, instead of erasing the
     /// member entirely
     std::vector<std::pair<BasicJsonType*, BasicJsonType>> duplicate_key_stash {};
-    /// whether a syntax error occurred
-    bool errored = false;
     /// callback function
     const parser_callback_t callback = nullptr;
-    /// whether to throw exceptions in case of errors
-    const bool allow_exceptions = true;
     /// a discarded value for the callback
     BasicJsonType discarded = BasicJsonType::value_t::discarded;
     /// the lexer reference to obtain the current position

include/nlohmann/detail/input/lexer.hpp

@@ -12,6 +12,7 @@
 #include <cstddef> // size_t
 #include <cstdint> // uint32_t
 #include <cstdio> // snprintf
+#include <cstring> // memcmp
 #include <initializer_list> // initializer_list
 #include <string> // char_traits, string
 #include <utility> // move
@@ -417,30 +418,43 @@ class lexer : public lexer_base<BasicJsonType>
     }
 
     /// contiguous input: bulk-append the run of ordinary characters and complete
-    /// well-formed UTF-8 sequences starting at the current read position, leaving
+    /// well-formed UTF-8 sequences starting at the current read position, then
-    /// the first byte that needs individual handling (the closing quote, an
+    /// read the first byte that needs individual handling (the closing quote, an
-    /// escape, a control character, or an ill-formed UTF-8 byte) for get()
+    /// escape, a control character, or an ill-formed UTF-8 byte) like get().
-    void scan_string_bulk(std::true_type /*bulk*/)
+    /// That byte is taken from the buffer that was just scanned. Through get(),
+    /// Apple Clang merged this read with the other get() calls of the scan
+    /// function, which load the read position again right after it was stored
+    /// (3% of json::accept() on jeopardy.json on Apple M1).
+    char_int_type get_after_string_run(std::true_type /*bulk*/)
     {
         // a pending unget must be consumed through the normal path first
         if (next_unget)
         {
-            return;
+            return get();
         }
         const std::size_t remaining = ia.bulk_remaining();
         if (remaining == 0)
         {
-            return;
+            return get();
         }
-        const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
+        const auto* const raw = ia.bulk_data();
+        const auto* const data = reinterpret_cast<const unsigned char*>(raw);
 
-        const std::size_t pos = string_bulk_run(data, remaining);
+        const std::size_t pos = lexer_string_bulk_run(data, remaining);
-        if (pos == 0)
+        if (pos != 0)
         {
-            return;
+            token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), pos);
+            bulk_consume(reinterpret_cast<const char*>(data), pos);
         }
-        token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), pos);
+        if (pos == remaining)
-        bulk_consume(reinterpret_cast<const char*>(data), pos);
+        {
+            return get(); // end of the contiguous input
+        }
+        // what get() does, with the byte at hand
+        advance_position();
+        ia.bulk_skip(1);
+        current = char_traits<char_type>::to_int_type(raw[pos]);
+        return track_after_read();
     }
 
     /// consume @a n characters at @a data (the adapter's bulk_data()) and do
@@ -473,7 +487,10 @@ class lexer : public lexer_base<BasicJsonType>
     }
 
     /// streaming input: no bulk fast path
-    void scan_string_bulk(std::false_type /*bulk*/) const noexcept {}
+    char_int_type get_after_string_run(std::false_type /*bulk*/)
+    {
+        return get();
+    }
 
     /*!
     @brief scan a string literal
@@ -501,11 +518,8 @@ class lexer : public lexer_base<BasicJsonType>
         while (true)
         {
             // bulk-consume ordinary characters from contiguous input, then
-            // handle the next special byte through the switch below
+            // get the next character, the one that ends the run
-            scan_string_bulk(std::integral_constant<bool, bulk_scan> {});
+            switch (get_after_string_run(std::integral_constant<bool, bulk_scan>()))
-
-            // get the next character
-            switch (get())
             {
                 // end of file while parsing the string
                 case char_traits<char_type>::eof():
@@ -642,194 +656,74 @@ class lexer : public lexer_base<BasicJsonType>
 
                 // invalid control characters
                 case 0x00:
-                {
-                    error_message = "invalid string: control character U+0000 (NUL) must be escaped to \\u0000";
-                    return token_type::parse_error;
-                }
-
                 case 0x01:
-                {
-                    error_message = "invalid string: control character U+0001 (SOH) must be escaped to \\u0001";
-                    return token_type::parse_error;
-                }
-
                 case 0x02:
-                {
-                    error_message = "invalid string: control character U+0002 (STX) must be escaped to \\u0002";
-                    return token_type::parse_error;
-                }
-
                 case 0x03:
-                {
-                    error_message = "invalid string: control character U+0003 (ETX) must be escaped to \\u0003";
-                    return token_type::parse_error;
-                }
-
                 case 0x04:
-                {
-                    error_message = "invalid string: control character U+0004 (EOT) must be escaped to \\u0004";
-                    return token_type::parse_error;
-                }
-
                 case 0x05:
-                {
-                    error_message = "invalid string: control character U+0005 (ENQ) must be escaped to \\u0005";
-                    return token_type::parse_error;
-                }
-
                 case 0x06:
-                {
-                    error_message = "invalid string: control character U+0006 (ACK) must be escaped to \\u0006";
-                    return token_type::parse_error;
-                }
-
                 case 0x07:
-                {
-                    error_message = "invalid string: control character U+0007 (BEL) must be escaped to \\u0007";
-                    return token_type::parse_error;
-                }
-
                 case 0x08:
-                {
-                    error_message = "invalid string: control character U+0008 (BS) must be escaped to \\u0008 or \\b";
-                    return token_type::parse_error;
-                }
-
                 case 0x09:
-                {
-                    error_message = "invalid string: control character U+0009 (HT) must be escaped to \\u0009 or \\t";
-                    return token_type::parse_error;
-                }
-
                 case 0x0A:
-                {
-                    error_message = "invalid string: control character U+000A (LF) must be escaped to \\u000A or \\n";
-                    return token_type::parse_error;
-                }
-
                 case 0x0B:
-                {
-                    error_message = "invalid string: control character U+000B (VT) must be escaped to \\u000B";
-                    return token_type::parse_error;
-                }
-
                 case 0x0C:
-                {
-                    error_message = "invalid string: control character U+000C (FF) must be escaped to \\u000C or \\f";
-                    return token_type::parse_error;
-                }
-
                 case 0x0D:
-                {
-                    error_message = "invalid string: control character U+000D (CR) must be escaped to \\u000D or \\r";
-                    return token_type::parse_error;
-                }
-
                 case 0x0E:
-                {
-                    error_message = "invalid string: control character U+000E (SO) must be escaped to \\u000E";
-                    return token_type::parse_error;
-                }
-
                 case 0x0F:
-                {
-                    error_message = "invalid string: control character U+000F (SI) must be escaped to \\u000F";
-                    return token_type::parse_error;
-                }
-
                 case 0x10:
-                {
-                    error_message = "invalid string: control character U+0010 (DLE) must be escaped to \\u0010";
-                    return token_type::parse_error;
-                }
-
                 case 0x11:
-                {
-                    error_message = "invalid string: control character U+0011 (DC1) must be escaped to \\u0011";
-                    return token_type::parse_error;
-                }
-
                 case 0x12:
-                {
-                    error_message = "invalid string: control character U+0012 (DC2) must be escaped to \\u0012";
-                    return token_type::parse_error;
-                }
-
                 case 0x13:
-                {
-                    error_message = "invalid string: control character U+0013 (DC3) must be escaped to \\u0013";
-                    return token_type::parse_error;
-                }
-
                 case 0x14:
-                {
-                    error_message = "invalid string: control character U+0014 (DC4) must be escaped to \\u0014";
-                    return token_type::parse_error;
-                }
-
                 case 0x15:
-                {
-                    error_message = "invalid string: control character U+0015 (NAK) must be escaped to \\u0015";
-                    return token_type::parse_error;
-                }
-
                 case 0x16:
-                {
-                    error_message = "invalid string: control character U+0016 (SYN) must be escaped to \\u0016";
-                    return token_type::parse_error;
-                }
-
                 case 0x17:
-                {
-                    error_message = "invalid string: control character U+0017 (ETB) must be escaped to \\u0017";
-                    return token_type::parse_error;
-                }
-
                 case 0x18:
-                {
-                    error_message = "invalid string: control character U+0018 (CAN) must be escaped to \\u0018";
-                    return token_type::parse_error;
-                }
-
                 case 0x19:
-                {
-                    error_message = "invalid string: control character U+0019 (EM) must be escaped to \\u0019";
-                    return token_type::parse_error;
-                }
-
                 case 0x1A:
-                {
-                    error_message = "invalid string: control character U+001A (SUB) must be escaped to \\u001A";
-                    return token_type::parse_error;
-                }
-
                 case 0x1B:
-                {
-                    error_message = "invalid string: control character U+001B (ESC) must be escaped to \\u001B";
-                    return token_type::parse_error;
-                }
-
                 case 0x1C:
-                {
-                    error_message = "invalid string: control character U+001C (FS) must be escaped to \\u001C";
-                    return token_type::parse_error;
-                }
-
                 case 0x1D:
-                {
-                    error_message = "invalid string: control character U+001D (GS) must be escaped to \\u001D";
-                    return token_type::parse_error;
-                }
-
                 case 0x1E:
-                {
-                    error_message = "invalid string: control character U+001E (RS) must be escaped to \\u001E";
-                    return token_type::parse_error;
-                }
-
                 case 0x1F:
                 {
-                    error_message = "invalid string: control character U+001F (US) must be escaped to \\u001F";
+                    static const std::array<const char*, 32> control_character_messages = {{
+                            "invalid string: control character U+0000 (NUL) must be escaped to \\u0000",
+                            "invalid string: control character U+0001 (SOH) must be escaped to \\u0001",
+                            "invalid string: control character U+0002 (STX) must be escaped to \\u0002",
+                            "invalid string: control character U+0003 (ETX) must be escaped to \\u0003",
+                            "invalid string: control character U+0004 (EOT) must be escaped to \\u0004",
+                            "invalid string: control character U+0005 (ENQ) must be escaped to \\u0005",
+                            "invalid string: control character U+0006 (ACK) must be escaped to \\u0006",
+                            "invalid string: control character U+0007 (BEL) must be escaped to \\u0007",
+                            "invalid string: control character U+0008 (BS) must be escaped to \\u0008 or \\b",
+                            "invalid string: control character U+0009 (HT) must be escaped to \\u0009 or \\t",
+                            "invalid string: control character U+000A (LF) must be escaped to \\u000A or \\n",
+                            "invalid string: control character U+000B (VT) must be escaped to \\u000B",
+                            "invalid string: control character U+000C (FF) must be escaped to \\u000C or \\f",
+                            "invalid string: control character U+000D (CR) must be escaped to \\u000D or \\r",
+                            "invalid string: control character U+000E (SO) must be escaped to \\u000E",
+                            "invalid string: control character U+000F (SI) must be escaped to \\u000F",
+                            "invalid string: control character U+0010 (DLE) must be escaped to \\u0010",
+                            "invalid string: control character U+0011 (DC1) must be escaped to \\u0011",
+                            "invalid string: control character U+0012 (DC2) must be escaped to \\u0012",
+                            "invalid string: control character U+0013 (DC3) must be escaped to \\u0013",
+                            "invalid string: control character U+0014 (DC4) must be escaped to \\u0014",
+                            "invalid string: control character U+0015 (NAK) must be escaped to \\u0015",
+                            "invalid string: control character U+0016 (SYN) must be escaped to \\u0016",
+                            "invalid string: control character U+0017 (ETB) must be escaped to \\u0017",
+                            "invalid string: control character U+0018 (CAN) must be escaped to \\u0018",
+                            "invalid string: control character U+0019 (EM) must be escaped to \\u0019",
+                            "invalid string: control character U+001A (SUB) must be escaped to \\u001A",
+                            "invalid string: control character U+001B (ESC) must be escaped to \\u001B",
+                            "invalid string: control character U+001C (FS) must be escaped to \\u001C",
+                            "invalid string: control character U+001D (GS) must be escaped to \\u001D",
+                            "invalid string: control character U+001E (RS) must be escaped to \\u001E",
+                            "invalid string: control character U+001F (US) must be escaped to \\u001F"
+                        }
+                    };
+                    error_message = control_character_messages[static_cast<std::size_t>(current)];
                     return token_type::parse_error;
                 }
 
@@ -1625,9 +1519,12 @@ scan_number_done:
         const std::size_t avail = rem + 1;
 
         // validate + classify the number extent (mirrors scan_number()'s grammar)
+        // and accumulate the mantissa digits on the way, so that tokens with up
+        // to 19 digits need no second pass for their value
         std::size_t i = 0;
         std::size_t dot_index = std::string::npos;
         token_type number_type = token_type::value_unsigned;
+        std::uint64_t w = 0;
         if (data[0] == '-')
         {
             number_type = token_type::value_integer;
@@ -1637,22 +1534,21 @@ scan_number_done:
                 return token_type::uninitialized;
             }
         }
+        const std::size_t integer_begin = i;
         if (data[i] == '0')
         {
             ++i;
         }
         else if (data[i] >= '1' && data[i] <= '9')
         {
-            ++i;
+            i = accumulate_digits(data, i, avail, w);
-            while (i < avail && data[i] >= '0' && data[i] <= '9')
-            {
-                ++i;
-            }
         }
         else
         {
             return token_type::uninitialized;
         }
+        std::size_t digit_count = i - integer_begin;
+        std::size_t fraction_digits = 0;
         if (i < avail && data[i] == '.')
         {
             number_type = token_type::value_float;
@@ -1662,29 +1558,39 @@ scan_number_done:
             {
                 return token_type::uninitialized;
             }
-            while (i < avail && data[i] >= '0' && data[i] <= '9')
+            const std::size_t fraction_begin = i;
-            {
+            i = accumulate_digits(data, i, avail, w);
-                ++i;
+            fraction_digits = i - fraction_begin;
-            }
+            digit_count += fraction_digits;
         }
         // the mantissa ends here, whether or not an exponent part follows
         const std::size_t mantissa_end = i;
+        std::int64_t exponent = 0;
         if (i < avail && (data[i] == 'e' || data[i] == 'E'))
         {
             number_type = token_type::value_float;
             ++i;
+            bool negative_exponent = false;
             if (i < avail && (data[i] == '+' || data[i] == '-'))
             {
+                negative_exponent = data[i] == '-';
                 ++i;
             }
             if (i >= avail || !(data[i] >= '0' && data[i] <= '9'))
             {
                 return token_type::uninitialized;
             }
+            // saturated far beyond every range, see parse_float_exponent()
+            constexpr std::int64_t saturation = 100000000000000000; // 10^17
             while (i < avail && data[i] >= '0' && data[i] <= '9')
             {
+                if (exponent < saturation)
+                {
+                    exponent = (exponent * 10) + (data[i] - '0');
+                }
                 ++i;
             }
+            exponent = negative_exponent ? -exponent : exponent;
         }
         const std::size_t len = i;
         if (number_may_continue(len == avail, std::integral_constant<bool, bulk_window> {}))
@@ -1705,7 +1611,10 @@ scan_number_done:
 #if !JSON_DIAGNOSTIC_POSITIONS
         if (number_type != token_type::value_float)
         {
-            const token_type integer_result = convert_integer(number_type, data, data + len);
+            // up to 18 digits always fit into std::uint64_t and std::int64_t
+            const token_type integer_result = (digit_count <= 18)
+                                              ? store_integer(number_type, w)
+                                              : convert_integer(number_type, data, data + len);
             if (JSON_HEDLEY_LIKELY(integer_result != token_type::uninitialized))
             {
                 bulk_consume(data + 1, len - 1);
@@ -1719,15 +1628,42 @@ scan_number_done:
         }
 #endif
 
-        // materialize the token exactly as scan_number() would. reset() already
-        // cleared token_buffer, so append() fills it (assign() is avoided
-        // because custom string_t types need not provide it)
-        token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), len);
         decimal_point_position = dot_index;
 
         bulk_consume(data + 1, len - 1);
         read_number_terminator(std::integral_constant<bool, bulk_window> {});
 
+        // a float whose digits all fit into w converts from the accumulated
+        // value; longer ones (and other float formats) take the general path
+        if (number_type == token_type::value_float && digit_count <= 19)
+        {
+            float_significand s;
+            s.w = w;
+            s.exponent = exponent - static_cast<std::int64_t>(fraction_digits);
+            s.negative = data[0] == '-';
+            if (convert_accumulated_float(s, std::integral_constant<bool, has_native_float_format<number_float_t>::value> {}))
+            {
+                // the token text is only copied into token_buffer when
+                // get_string() asks for it; the library's own SAX handlers
+                // ignore it. A window into a stream may be refilled by the
+                // next read, so there the text is copied right away.
+                if (bulk_window)
+                {
+                    token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), len);
+                }
+                else
+                {
+                    pending_number_text = data;
+                    pending_number_length = len;
+                }
+                return token_type::value_float;
+            }
+        }
+
+        // materialize the token exactly as scan_number() would. reset() already
+        // cleared token_buffer, so append() fills it (assign() is avoided
+        // because custom string_t types need not provide it)
+        token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), len);
         return convert_number(number_type, mantissa_end);
     }
 
@@ -1756,6 +1692,35 @@ scan_number_done:
     /// the input is not handed back, so the terminator can stay unread
     void read_number_terminator(std::false_type /*window*/) const noexcept {}
 
+    /// binary32/binary64: the value of a float token from its accumulated
+    /// significand (see scan_number_bulk_contiguous())
+    bool convert_accumulated_float(const float_significand& s, std::true_type /*native*/) noexcept
+    {
+        value_float = decimal_to_float<number_float_t>(s);
+        return true;
+    }
+
+    /// other formats (e.g. x87 long double): not instantiated for them, as
+    /// decimal_to_float() only supports binary32/binary64
+    static bool convert_accumulated_float(const float_significand& /*s*/, std::false_type /*native*/) noexcept
+    {
+        return false;
+    }
+
+    /// the value of an integer token with at most 18 digits, accumulated in @a w
+    token_type store_integer(token_type number_type, std::uint64_t w) noexcept
+    {
+        if (number_type == token_type::value_unsigned)
+        {
+            value_unsigned = static_cast<number_unsigned_t>(w);
+            // reject values that do not round-trip into a narrower type
+            return (static_cast<std::uint64_t>(value_unsigned) == w) ? token_type::value_unsigned : token_type::uninitialized;
+        }
+        const std::int64_t x = -static_cast<std::int64_t>(w);
+        value_integer = static_cast<number_integer_t>(x);
+        return (static_cast<std::int64_t>(value_integer) == x) ? token_type::value_integer : token_type::uninitialized;
+    }
+
     /// contiguous input: try the number fast path, else the byte-path scanner
     token_type scan_number_dispatch(std::true_type /*bulk*/)
     {
@@ -1770,18 +1735,23 @@ scan_number_done:
     }
 
     /*!
-    @param[in] literal_text  the literal text to expect
+    @param[in] rest         the literal text after its first character, which
-    @param[in] length        the length of the passed literal text
+                            is current (its length is a template parameter, so
-    @param[in] return_type   the token type to return on success
+                            that the comparison of the contiguous fast path is
+                            a fixed-size load, not a call of memcmp)
+    @param[in] return_type  the token type to return on success
     */
-    JSON_HEDLEY_NON_NULL(2)
+    template<std::size_t N>
-    token_type scan_literal(const char_type* literal_text, const std::size_t length,
+    JSON_HEDLEY_NEVER_INLINE token_type scan_literal(const char (&rest)[N], token_type return_type) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
-                            token_type return_type)
     {
-        JSON_ASSERT(char_traits<char_type>::to_char_type(current) == literal_text[0]);
+        constexpr std::size_t length = N - 1;
-        for (std::size_t i = 1; i < length; ++i)
+        if (scan_literal_bulk(rest, length, std::integral_constant<bool, bulk_scan> {}))
         {
-            if (JSON_HEDLEY_UNLIKELY(char_traits<char_type>::to_char_type(get()) != literal_text[i]))
+            return return_type;
+        }
+        for (std::size_t i = 0; i < length; ++i)
+        {
+            if (JSON_HEDLEY_UNLIKELY(char_traits<char_type>::to_char_type(get()) != static_cast<char_type>(rest[i])))
             {
                 error_message = "invalid literal";
                 return token_type::parse_error;
@@ -1790,6 +1760,27 @@ scan_number_done:
         return return_type;
     }
 
+    /// contiguous input: compare the rest of a literal at once; false (and
+    /// nothing consumed) if it does not match, so that the byte path reports
+    /// the error at the right character
+    JSON_HEDLEY_ALWAYS_INLINE bool scan_literal_bulk(const char* rest, const std::size_t length, std::true_type /*bulk*/)
+    {
+        if (next_unget || ia.bulk_remaining() < length
+                || std::memcmp(ia.bulk_data(), rest, length) != 0)
+        {
+            return false;
+        }
+        bulk_consume(reinterpret_cast<const char*>(ia.bulk_data()), length);
+        current = static_cast<char_int_type>(static_cast<unsigned char>(rest[length - 1]));
+        return true;
+    }
+
+    /// streaming input: no bulk fast path
+    bool scan_literal_bulk(const char* /*rest*/, const std::size_t /*length*/, std::false_type /*bulk*/) const noexcept
+    {
+        return false;
+    }
+
     /////////////////////
     // input management
     /////////////////////
@@ -1798,6 +1789,7 @@ scan_number_done:
     void reset() noexcept
     {
         token_buffer.clear();
+        pending_number_text = nullptr;
         decimal_point_position = std::string::npos;
 
 #if JSON_DIAGNOSTIC_POSITIONS
@@ -2057,10 +2049,30 @@ scan_number_done:
     /// return current string value
     string_t& get_string()
     {
+        if (pending_number_text != nullptr)
+        {
+            token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(pending_number_text), pending_number_length);
+            pending_number_text = nullptr;
+        }
         // a number token holds '.' regardless of the locale (#4084)
         return token_buffer;
     }
 
+    /// the value of a string token (key or string), which never has pending
+    /// number text, so get_string()'s check is not needed
+    string_t& get_string_token() noexcept
+    {
+        JSON_ASSERT(pending_number_text == nullptr);
+        return token_buffer;
+    }
+
+    /// the text of a float token for a SAX handler that ignores it (the
+    /// library's own handlers): empty, without copying the token
+    const string_t& get_ignored_number_text() const noexcept
+    {
+        return token_buffer;
+    }
+
     /////////////////////
     // diagnostics
     /////////////////////
@@ -2394,21 +2406,14 @@ scan_number_done:
                 return token_type::value_separator;
 
             // literals
+            // (the text after the first character; no local arrays, which
+            // would give this function a stack canary on every token)
             case 't':
-            {
+                return scan_literal("rue", token_type::literal_true);
-                std::array<char_type, 4> true_literal = {{static_cast<char_type>('t'), static_cast<char_type>('r'), static_cast<char_type>('u'), static_cast<char_type>('e')}};
-                return scan_literal(true_literal.data(), true_literal.size(), token_type::literal_true);
-            }
             case 'f':
-            {
+                return scan_literal("alse", token_type::literal_false);
-                std::array<char_type, 5> false_literal = {{static_cast<char_type>('f'), static_cast<char_type>('a'), static_cast<char_type>('l'), static_cast<char_type>('s'), static_cast<char_type>('e')}};
-                return scan_literal(false_literal.data(), false_literal.size(), token_type::literal_false);
-            }
             case 'n':
-            {
+                return scan_literal("ull", token_type::literal_null);
-                std::array<char_type, 4> null_literal = {{static_cast<char_type>('n'), static_cast<char_type>('u'), static_cast<char_type>('l'), static_cast<char_type>('l')}};
-                return scan_literal(null_literal.data(), null_literal.size(), token_type::literal_null);
-            }
 
             // string
             case '\"':
@@ -2456,6 +2461,11 @@ scan_number_done:
     /// whether the next get() call should just return current
     bool next_unget = false;
 
+    /// the text of the current float token in the input, not yet copied into
+    /// token_buffer (see get_string()), or nullptr
+    const char* pending_number_text = nullptr;
+    std::size_t pending_number_length = 0;
+
     /// the start position of the current token
     position_t position {};
 

include/nlohmann/detail/input/number_parse.hpp

@@ -16,7 +16,6 @@
 #include <cstddef> // size_t
 #include <cstdint> // int64_t, uint64_t
 #include <cstdlib> // strtof, strtod, strtold
-#include <cstring> // memcpy
 #include <limits> // numeric_limits
 #include <string> // string
 #include <type_traits> // conditional, integral_constant, is_signed, true_type, false_type
@@ -275,13 +274,77 @@ JSON_HEDLEY_ALWAYS_INLINE std::uint32_t parse_eight_digits(std::uint64_t v) noex
     return static_cast<std::uint32_t>(((v & 0x0000FFFF0000FFFFu) * 42949672960001u) >> 32u);
 }
 
-/// whether [first, last) contains a digit other than '0'
+/// whether the eight bytes in @a v (see read_eight_bytes()) are all ASCII
-inline bool has_nonzero_digit(const char* first, const char* last) noexcept
+/// digits (after fast_float)
+JSON_HEDLEY_ALWAYS_INLINE bool is_eight_digits(std::uint64_t v) noexcept
 {
-    return std::any_of(first, last, [](char c) noexcept
+    return ((v & 0xF0F0F0F0F0F0F0F0u) | (((v + 0x0606060606060606u) & 0xF0F0F0F0F0F0F0F0u) >> 4u)) == 0x3333333333333333u;
+}
+
+/*!
+@brief skip the ASCII digits starting at data[i] and accumulate their value
+
+Eight digits are taken at a time while at least eight bytes remain. @a w wraps
+around after 19 digits; the caller only uses it for shorter digit runs.
+
+@return the index of the first byte at or after @a i that is not a digit
+*/
+JSON_HEDLEY_ALWAYS_INLINE std::size_t accumulate_digits(const char* data, std::size_t i, std::size_t avail, std::uint64_t& w) noexcept
+{
+    while (avail - i >= 8)
     {
-        return c != '0';
+        const std::uint64_t v = read_eight_bytes(data + i);
-    });
+        if (!is_eight_digits(v))
+        {
+            break;
+        }
+        w = (w * 100000000u) + parse_eight_digits(v);
+        i += 8;
+    }
+    while (i < avail && data[i] >= '0' && data[i] <= '9')
+    {
+        w = (w * 10u) + static_cast<std::uint64_t>(data[i] - '0');
+        ++i;
+    }
+    return i;
+}
+
+/// whether [first, last) contains a digit other than '0'; a plain loop, as
+/// GCC calls std::any_of out of line even for the usual empty range
+JSON_HEDLEY_ALWAYS_INLINE bool has_nonzero_digit(const char* first, const char* last) noexcept
+{
+    for (; first != last; ++first)
+    {
+        if (*first != '0')
+        {
+            return true;
+        }
+    }
+    return false;
+}
+
+/*!
+@brief accumulate the validated digits [p, last) into @a w, as long as
+       @a remaining digits still fit into it
+
+Eight digits are taken at a time while at least eight remain, and @a remaining
+is decreased by the number of digits taken.
+
+@return a pointer past the last digit taken
+*/
+JSON_HEDLEY_ALWAYS_INLINE const char* accumulate_significant_digits(const char* p, const char* last, int& remaining, std::uint64_t& w) noexcept
+{
+    while (remaining >= 8 && last - p >= 8)
+    {
+        w = (w * 100000000u) + parse_eight_digits(read_eight_bytes(p));
+        p += 8;
+        remaining -= 8;
+    }
+    for (; remaining > 0 && p != last; ++p, --remaining)
+    {
+        w = (w * 10u) + static_cast<std::uint64_t>(*p - '0');
+    }
+    return p;
 }
 
 /// the value of the validated exponent digits [+-]?[0-9]+ in [first, last),
@@ -327,7 +390,7 @@ truncated is set.
                                    std::string::npos if there is none
 @param[in] mantissa_end            index of the 'e'/'E', or the token length
 */
-inline float_significand parse_float_significand(const char* first, const char* last,
+JSON_HEDLEY_ALWAYS_INLINE float_significand parse_float_significand(const char* first, const char* last,
         std::size_t decimal_point_position, std::size_t mantissa_end) noexcept
 {
     float_significand s;
@@ -342,16 +405,7 @@ inline float_significand parse_float_significand(const char* first, const char*
     int remaining = 19; // digits that still fit into w
     if (*p != '0') // the integer part is "0" or [1-9][0-9]*
     {
-        while (remaining >= 8 && integer_last - p >= 8)
+        p = accumulate_significant_digits(p, integer_last, remaining, w);
-        {
-            w = (w * 100000000u) + parse_eight_digits(read_eight_bytes(p));
-            p += 8;
-            remaining -= 8;
-        }
-        for (; remaining > 0 && p != integer_last; ++p, --remaining)
-        {
-            w = (w * 10u) + static_cast<std::uint64_t>(*p - '0');
-        }
         s.exponent = integer_last - p;
         s.truncated = has_nonzero_digit(p, integer_last);
     }
@@ -370,16 +424,7 @@ inline float_significand parse_float_significand(const char* first, const char*
             s.exponent -= p - zeros;
         }
         const char* const digits = p;
-        while (remaining >= 8 && mantissa_last - p >= 8)
+        p = accumulate_significant_digits(p, mantissa_last, remaining, w);
-        {
-            w = (w * 100000000u) + parse_eight_digits(read_eight_bytes(p));
-            p += 8;
-            remaining -= 8;
-        }
-        for (; remaining > 0 && p != mantissa_last; ++p, --remaining)
-        {
-            w = (w * 10u) + static_cast<std::uint64_t>(*p - '0');
-        }
         s.exponent -= p - digits;
         s.truncated = s.truncated || has_nonzero_digit(p, mantissa_last);
     }
@@ -712,15 +757,14 @@ std::uint64_t digit_comparison(const char* first, const char* last, std::uint64_
 inline void float_from_bits(std::uint64_t bits, double& value) noexcept
 {
     static_assert(sizeof(double) == sizeof(std::uint64_t), "double must have 64 bits");
-    std::memcpy(&value, &bits, sizeof(value));
+    value = bit_cast<double>(bits);
 }
 
 /// the float with the IEEE-754 bits @a bits (the lower 32)
 inline void float_from_bits(std::uint64_t bits, float& value) noexcept
 {
     static_assert(sizeof(float) == sizeof(std::uint32_t), "float must have 32 bits");
-    const auto bits32 = static_cast<std::uint32_t>(bits);
+    value = bit_cast<float>(static_cast<std::uint32_t>(bits));
-    std::memcpy(&value, &bits32, sizeof(bits32));
 }
 
 /// the powers of ten that are exact in binary64 (up to 10^22)

include/nlohmann/detail/input/parser.hpp

@@ -51,6 +51,20 @@ template<typename BasicJsonType>
 using parser_callback_t =
     std::function<bool(int /*depth*/, parse_event_t /*event*/, BasicJsonType& /*parsed*/)>;
 
+/// whether a SAX handler ignores the text of float tokens (the library's own
+/// handlers do), so that the parser need not materialize it
+template<typename SAX>
+struct sax_ignores_number_text : std::false_type {};
+
+template<typename BasicJsonType, typename InputAdapterType>
+struct sax_ignores_number_text<json_sax_dom_parser<BasicJsonType, InputAdapterType>> : std::true_type {};
+
+template<typename BasicJsonType, typename InputAdapterType>
+struct sax_ignores_number_text<json_sax_dom_callback_parser<BasicJsonType, InputAdapterType>> : std::true_type {};
+
+template<typename BasicJsonType>
+struct sax_ignores_number_text<json_sax_acceptor<BasicJsonType>> : std::true_type {};
+
 /*!
 @brief syntax analysis
 
@@ -151,26 +165,63 @@ class parser
 
         if (result)
         {
-            if (strict)
+            return finish_input(*sax, strict);
-            {
-                // strict mode: next byte must be EOF
-                if (get_token() != token_type::end_of_input)
-                {
-                    return syntax_error(*sax, exception_message(token_type::end_of_input, "value"));
-                }
-            }
-            else
-            {
-                // the caller keeps using the input: position it right after
-                // the value by leaving the character that terminated it
-                m_lexer.release_lookahead();
-            }
         }
 
-        return result;
+        return false;
     }
 
   private:
+    /// the text of the current float token for @a sax (see sax_ignores_number_text)
+    template<typename SAX>
+    const string_t& number_float_text(SAX* /*sax*/)
+    {
+        return number_float_text(std::integral_constant<bool, sax_ignores_number_text<SAX>::value> {});
+    }
+
+    const string_t& number_float_text(std::true_type /*ignored*/) const noexcept
+    {
+        return m_lexer.get_ignored_number_text();
+    }
+
+    string_t& number_float_text(std::false_type /*ignored*/)
+    {
+        return m_lexer.get_string();
+    }
+
+    /*!
+    @brief apply the end-of-input handling after a value was parsed
+
+    In strict mode, the next token must be the end of the input; otherwise
+    parse_error.101 is reported through @a sax. In non-strict mode, the
+    lookahead is released so the caller can keep reading the input right after
+    the parsed value.
+
+    @param[in,out] sax  the SAX parser to report an error to
+    @param[in] strict   whether to expect the last token to be EOF
+    @return true, or what @a sax returned for the error
+    */
+    template<typename SAX>
+    bool finish_input(SAX& sax, const bool strict)
+    {
+        if (strict)
+        {
+            // strict mode: next byte must be EOF
+            if (get_token() != token_type::end_of_input)
+            {
+                return syntax_error(sax, exception_message(token_type::end_of_input, "value"));
+            }
+        }
+        else
+        {
+            // the caller keeps using the input: position it right after
+            // the value by leaving the character that terminated it
+            m_lexer.release_lookahead();
+        }
+
+        return true;
+    }
+
     /*!
     @brief run a DOM SAX parser to completion and position the lexer
 
@@ -190,20 +241,7 @@ class parser
     {
         sax_parse_internal(&sdp);
 
-        if (strict)
+        static_cast<void>(finish_input(sdp, strict));
-        {
-            // in strict mode, input must be completely read
-            if (get_token() != token_type::end_of_input)
-            {
-                syntax_error(sdp, exception_message(token_type::end_of_input, "value"));
-            }
-        }
-        else
-        {
-            // the caller keeps using the input: position it right after
-            // the value by leaving the character that terminated it
-            m_lexer.release_lookahead();
-        }
 
         return !sdp.is_errored();
     }
@@ -213,8 +251,9 @@ class parser
     bool sax_parse_internal(SAX* sax)
     {
         // stack to remember the hierarchy of structured values we are parsing
-        // true = array; false = object
+        // true = array; false = object (bytes, not std::vector<bool>, whose
-        std::vector<bool> states;
+        // push_back() is a call with GCC)
+        std::vector<std::uint8_t> states;
         // value to avoid a goto (see comment where set to true)
         bool skip_to_state_evaluation = false;
 
@@ -247,7 +286,7 @@ class parser
                         {
                             return syntax_error(*sax, exception_message(token_type::value_string, "object key"));
                         }
-                        if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string())))
+                        if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string_token())))
                         {
                             return false;
                         }
@@ -259,7 +298,7 @@ class parser
                         }
 
                         // remember we are now inside an object
-                        states.push_back(false);
+                        states.push_back(0);
 
                         // parse values
                         get_token();
@@ -284,7 +323,7 @@ class parser
                         }
 
                         // remember we are now inside an array
-                        states.push_back(true);
+                        states.push_back(1);
 
                         // parse values (no need to call get_token)
                         continue;
@@ -301,7 +340,7 @@ class parser
                                                     out_of_range::create(exception_id::number_overflow, concat("number overflow parsing '", m_lexer.get_token_string(), '\''), nullptr));
                         }
 
-                        if (JSON_HEDLEY_UNLIKELY(!sax->number_float(res, m_lexer.get_string())))
+                        if (JSON_HEDLEY_UNLIKELY(!sax->number_float(res, number_float_text(sax))))
                         {
                             return false;
                         }
@@ -347,7 +386,7 @@ class parser
 
                     case token_type::value_string:
                     {
-                        if (JSON_HEDLEY_UNLIKELY(!sax->string(m_lexer.get_string())))
+                        if (JSON_HEDLEY_UNLIKELY(!sax->string(m_lexer.get_string_token())))
                         {
                             return false;
                         }
@@ -372,7 +411,7 @@ class parser
                     {
                         if (JSON_HEDLEY_UNLIKELY(m_lexer.get_chars_read_total() == 1))
                         {
-                            return syntax_error(*sax, "attempting to parse an empty input; check that your input string or stream contains the expected JSON");
+                            return syntax_error(*sax, empty_input_message());
                         }
 
                         return syntax_error(*sax, exception_message(token_type::literal_or_value, "value"));
@@ -401,7 +440,7 @@ class parser
                 return true;
             }
 
-            if (states.back())  // array
+            if (states.back() != 0)  // array
             {
                 // comma -> next value
                 // or end of array (ignore_trailing_commas = true)
@@ -456,7 +495,7 @@ class parser
                         return syntax_error(*sax, exception_message(token_type::value_string, "object key"));
                     }
 
-                    if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string())))
+                    if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string_token())))
                     {
                         return false;
                     }

include/nlohmann/detail/input/simd_scan.hpp

@@ -0,0 +1,321 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  JSON for Modern C++
+// |  |  |__   |  |  | | | |  version 3.12.0
+// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
+//
+// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
+// SPDX-FileCopyrightText: 2018-2025 The simdjson authors <https://github.com/simdjson/simdjson>
+// SPDX-License-Identifier: MIT
+
+#pragma once
+
+#include <array> // array
+#include <atomic> // atomic
+#include <cstddef> // size_t
+#include <cstdint> // uint8_t, uint64_t
+
+#include <nlohmann/detail/bit_ops.hpp>
+#include <nlohmann/detail/macro_scope.hpp>
+
+// Vector code for runs of string bytes, used by the lexer for contiguous input
+// (see string_bulk_run()). NEON (AArch64) and SSE2 (x86-64) belong to the
+// baseline instruction sets and are used by default. The vector UTF-8 check
+// needs NEON or SSSE3. SSSE3 is not part of x86-64, and the code must not
+// depend on the flags of a translation unit (two translation units with
+// different flags would have different definitions of the same inline
+// functions): the check is compiled for SSSE3 with a function attribute and
+// used where the CPU has SSSE3 (all x86-64 CPUs since about 2011), else the
+// portable check. Code compiled for SSSE3 anyway (-mssse3 or more) skips the
+// CPU check. JSON_NO_SIMD selects the portable code everywhere.
+// NLOHMANN_JSON_NO_TARGET_ATTRIBUTE (for compilers that ignore the target
+// attribute and then reject the SSSE3 intrinsics) keeps the check portable
+// without disabling the SSE2 code.
+#if !defined(JSON_NO_SIMD) && defined(__aarch64__) && (defined(__GNUC__) || defined(__clang__)) && defined(__BYTE_ORDER__) && defined(__ORDER_LITTLE_ENDIAN__) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+    #include <arm_neon.h>
+    #define JSON_SCAN_NEON 1
+#else
+    #define JSON_SCAN_NEON 0
+#endif
+// (x86 only: other targets can define __SSE2__ as well, e.g., WebAssembly with -msse2, but have no <cpuid.h>)
+#if !defined(JSON_NO_SIMD) && !JSON_SCAN_NEON && (defined(__x86_64__) || defined(__i386__) || defined(_M_X64) || defined(_M_IX86)) && !defined(_M_ARM64EC) && (defined(__SSE2__) || defined(_M_X64) || (defined(_M_IX86_FP) && _M_IX86_FP >= 2))
+    #include <emmintrin.h>
+    #define JSON_SCAN_SSE2 1
+#else
+    #define JSON_SCAN_SSE2 0
+#endif
+#if JSON_SCAN_SSE2 && defined(__SSSE3__)
+    #include <tmmintrin.h>
+    #define JSON_SCAN_SSSE3 1 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
+#else
+    #define JSON_SCAN_SSSE3 0 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
+#endif
+#if JSON_SCAN_SSE2 && !JSON_SCAN_SSSE3 && !defined(NLOHMANN_JSON_NO_TARGET_ATTRIBUTE) && ((defined(__clang__) && __clang_major__ >= 4) || (defined(__GNUC__) && !defined(__clang__) && (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 9)) && !defined(__cpp_modules)))
+    // (GCC before 4.9 has no SSSE3 intrinsics without -mssse3; GCC with C++20
+    // modules drops the target attribute from functions it reads from a module
+    // interface and then rejects the intrinsics: "needs isa option -mssse3")
+    // <cpuid.h> of GCC before 11 has no include guard, and json.hpp and
+    // json_view.hpp both include it
+    #ifndef NLOHMANN_JSON_CPUID_INCLUDED
+        #define NLOHMANN_JSON_CPUID_INCLUDED
+        #include <cpuid.h>
+    #endif
+    #include <tmmintrin.h>
+    #define JSON_SCAN_SSSE3_DISPATCH 1 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
+    #define JSON_SCAN_SSSE3_TARGET __attribute__((target("ssse3")))
+#elif JSON_SCAN_SSE2 && !JSON_SCAN_SSSE3 && defined(_MSC_VER)
+    // (MSVC compiles intrinsics of any instruction set)
+    #include <intrin.h>
+    #include <tmmintrin.h>
+    #define JSON_SCAN_SSSE3_DISPATCH 1 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
+    #define JSON_SCAN_SSSE3_TARGET
+#else
+    #define JSON_SCAN_SSSE3_DISPATCH 0 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
+    #define JSON_SCAN_SSSE3_TARGET
+#endif
+#define JSON_SCAN_VECTOR (JSON_SCAN_NEON || JSON_SCAN_SSE2)
+#define JSON_SCAN_VECTOR_UTF8 (JSON_SCAN_NEON || JSON_SCAN_SSSE3 || JSON_SCAN_SSSE3_DISPATCH)
+
+NLOHMANN_JSON_NAMESPACE_BEGIN
+namespace detail
+{
+
+#if JSON_SCAN_VECTOR
+/*!
+@brief the first byte of a string run that is a quote, a backslash, a control
+character, or not ASCII, 16 bytes per step
+
+Stops at such a byte, or where fewer than 16 bytes are left (the caller tells
+the two apart). A signed compare with 0x20 finds control characters and
+non-ASCII bytes at once.
+*/
+JSON_HEDLEY_ALWAYS_INLINE const unsigned char* vector_plain_run(const unsigned char* p, const unsigned char* e) noexcept
+{
+    while (e - p >= 16)
+    {
+#if JSON_SCAN_NEON
+        const uint8x16_t in = vld1q_u8(p);
+        const uint8x16_t special = vorrq_u8(vorrq_u8(vceqq_u8(in, vdupq_n_u8('"')), vceqq_u8(in, vdupq_n_u8('\\'))),
+                                            vcltq_s8(vreinterpretq_s8_u8(in), vdupq_n_s8(0x20)));
+        // one nibble per byte (the usual NEON replacement of x86's movemask, see
+        // D. Kutenin, "Porting x86 vector bitmask optimizations to Arm NEON", 2022)
+        const std::uint64_t bits = vget_lane_u64(vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(special), 4)), 0);
+        if (bits != 0)
+        {
+            return p + (count_trailing_zeros(bits) >> 2u);
+        }
+#else
+        const __m128i in = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(p))); // NOLINT(bugprone-casting-through-void)
+        const __m128i special = _mm_or_si128(_mm_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8('"')), _mm_cmpeq_epi8(in, _mm_set1_epi8('\\'))),
+                                             _mm_cmplt_epi8(in, _mm_set1_epi8(0x20)));
+        const auto bits = static_cast<std::uint64_t>(static_cast<unsigned>(_mm_movemask_epi8(special)));
+        if (bits != 0)
+        {
+            return p + count_trailing_zeros(bits);
+        }
+#endif
+        p += 16;
+    }
+    return p;
+}
+#endif
+
+#if JSON_SCAN_VECTOR
+/// vector_plain_run() for runs that are already longer than a few words:
+/// inline with SSE2, out of line with NEON, where a larger string loop slows
+/// down the rest of the lexer
+#if JSON_SCAN_NEON
+    JSON_HEDLEY_NEVER_INLINE inline
+#else
+    JSON_HEDLEY_ALWAYS_INLINE
+#endif
+const unsigned char* vector_plain_run_long(const unsigned char* p, const unsigned char* e) noexcept
+{
+    return vector_plain_run(p, e);
+}
+#endif
+
+#if JSON_SCAN_SSSE3_DISPATCH
+/// whether the CPU has SSSE3 (CPUID leaf 1, ECX bit 9)
+inline bool cpu_ssse3() noexcept
+{
+#if defined(_MSC_VER) && !defined(__clang__)
+    std::array<int, 4> regs {{}};
+    __cpuid(regs.data(), 1);
+    return (static_cast<unsigned>(regs[2]) & (1u << 9u)) != 0;
+#else
+    unsigned eax = 0;
+    unsigned ebx = 0;
+    unsigned ecx = 0;
+    unsigned edx = 0;
+    return __get_cpuid(1, &eax, &ebx, &ecx, &edx) != 0 && (ecx & (1u << 9u)) != 0;
+#endif
+}
+
+/// whether the CPU has SSSE3, asked once: the answer is kept in an atomic
+/// that is initialized at compile time, so that neither a guard of a local
+/// static nor a global constructor is needed (threads that ask at the same
+/// time all store the same answer)
+JSON_HEDLEY_ALWAYS_INLINE bool cpu_has_ssse3() noexcept
+{
+    static std::atomic<int> known{0}; // 0: not asked yet, 1: no, 2: yes
+    int state = known.load(std::memory_order_relaxed);
+    if (JSON_HEDLEY_UNLIKELY(state == 0))
+    {
+        state = cpu_ssse3() ? 2 : 1;
+        known.store(state, std::memory_order_relaxed);
+    }
+    return state == 2;
+}
+#endif
+
+#if JSON_SCAN_VECTOR_UTF8
+/// Tables of the UTF-8 check of J. Keiser and D. Lemire, "Validating UTF-8 In
+/// Less Than One Instruction Per Byte" (2021), as in simdjson ("lookup4"): each
+/// maps a nibble (high and low nibble of the previous byte, high nibble of the
+/// current byte) to the errors it allows; a byte pair is ill-formed if all
+/// three have an error bit in common.
+template<typename Dummy = void>
+struct utf8_lookup4
+{
+    static constexpr std::uint8_t too_short = 1u << 0u, too_long = 1u << 1u, overlong_3 = 1u << 2u, too_large = 1u << 3u;
+    static constexpr std::uint8_t surrogate = 1u << 4u, overlong_2 = 1u << 5u, too_large_1000 = 1u << 6u, overlong_4 = 1u << 6u;
+    static constexpr std::uint8_t two_conts = 1u << 7u, carry = too_short | too_long | two_conts;
+    static const std::array<std::uint8_t, 16> byte_1_high;
+    static const std::array<std::uint8_t, 16> byte_1_low;
+    static const std::array<std::uint8_t, 16> byte_2_high;
+};
+
+template<typename Dummy>
+const std::array<std::uint8_t, 16> utf8_lookup4<Dummy>::byte_1_high =
+{
+    {
+        too_long, too_long, too_long, too_long, too_long, too_long, too_long, too_long,
+        two_conts, two_conts, two_conts, two_conts,
+        too_short | overlong_2, too_short, too_short | overlong_3 | surrogate, too_short | too_large | too_large_1000 | overlong_4
+    }
+};
+
+template<typename Dummy>
+const std::array<std::uint8_t, 16> utf8_lookup4<Dummy>::byte_1_low =
+{
+    {
+        carry | overlong_3 | overlong_2 | overlong_4, carry | overlong_2, carry, carry,
+        carry | too_large, carry | too_large | too_large_1000, carry | too_large | too_large_1000, carry | too_large | too_large_1000,
+        carry | too_large | too_large_1000, carry | too_large | too_large_1000, carry | too_large | too_large_1000, carry | too_large | too_large_1000,
+        carry | too_large | too_large_1000, carry | too_large | too_large_1000 | surrogate, carry | too_large | too_large_1000, carry | too_large | too_large_1000
+    }
+};
+
+template<typename Dummy>
+const std::array<std::uint8_t, 16> utf8_lookup4<Dummy>::byte_2_high =
+{
+    {
+        too_short, too_short, too_short, too_short, too_short, too_short, too_short, too_short,
+        static_cast<std::uint8_t>(too_long | overlong_2 | two_conts | overlong_3 | too_large_1000 | overlong_4),
+        static_cast<std::uint8_t>(too_long | overlong_2 | two_conts | overlong_3 | too_large),
+        static_cast<std::uint8_t>(too_long | overlong_2 | two_conts | surrogate | too_large),
+        static_cast<std::uint8_t>(too_long | overlong_2 | two_conts | surrogate | too_large),
+        too_short, too_short, too_short, too_short
+    }
+};
+
+/*!
+@brief the run of plain string bytes and well-formed UTF-8 at p (a character
+       boundary), 16 bytes per step
+
+The first quote, backslash, or control character is found with vector
+compares, and the UTF-8 check of J. Keiser and D. Lemire covers the bytes up
+to it. Returns true with @a block at that byte; returns false with @a block at
+the start of the 16 bytes where the check found ill-formed UTF-8 or where
+fewer than 16 bytes are left, for the caller to finish one sequence at a time.
+Out of line, so that no constants of the check occupy registers in the
+caller's loop. On x86-64, it is compiled for SSSE3 (see cpu_has_ssse3()).
+*/
+JSON_SCAN_SSSE3_TARGET JSON_HEDLEY_NEVER_INLINE inline bool vector_utf8_run(const unsigned char* p, const unsigned char* e, const unsigned char*& block_out) noexcept
+{
+    using lookup = utf8_lookup4<>;
+    const unsigned char* block = p;
+#if JSON_SCAN_NEON
+    const uint8x16_t t1h = vld1q_u8(lookup::byte_1_high.data());
+    const uint8x16_t t1l = vld1q_u8(lookup::byte_1_low.data());
+    const uint8x16_t t2h = vld1q_u8(lookup::byte_2_high.data());
+    uint8x16_t prev = vdupq_n_u8(0);
+    while (e - block >= 16)
+    {
+        const uint8x16_t in = vld1q_u8(block);
+        const uint8x16_t special = vorrq_u8(vorrq_u8(vceqq_u8(in, vdupq_n_u8('"')), vceqq_u8(in, vdupq_n_u8('\\'))), vcltq_u8(in, vdupq_n_u8(0x20)));
+        const uint8x16_t prev1 = vextq_u8(prev, in, 15);
+        const uint8x16_t sc = vandq_u8(vandq_u8(vqtbl1q_u8(t1h, vshrq_n_u8(prev1, 4)), vqtbl1q_u8(t1l, vandq_u8(prev1, vdupq_n_u8(0x0F)))), vqtbl1q_u8(t2h, vshrq_n_u8(in, 4)));
+        const uint8x16_t must23 = vorrq_u8(vqsubq_u8(vextq_u8(prev, in, 14), vdupq_n_u8(0xE0 - 0x80)), vqsubq_u8(vextq_u8(prev, in, 13), vdupq_n_u8(0xF0 - 0x80)));
+        const uint8x16_t err = veorq_u8(vandq_u8(must23, vdupq_n_u8(0x80)), sc);
+        const std::uint64_t special_bits = vget_lane_u64(vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(special), 4)), 0);
+        const std::uint64_t err_bits = vget_lane_u64(vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(vtstq_u8(err, err)), 4)), 0);
+        if (special_bits != 0)
+        {
+            // errors up to the special byte count (an incomplete sequence
+            // before a quote shows at the quote); the bytes after it do not
+            const unsigned k = static_cast<unsigned>(count_trailing_zeros(special_bits)) >> 2u;
+            const std::uint64_t upto = k == 15 ? ~std::uint64_t{0} :
+                                       (std::uint64_t{1} << (4u * (k + 1u))) - 1u;
+            if ((err_bits & upto) == 0)
+            {
+                block_out = block + k;
+                return true;
+            }
+            break;
+        }
+        if (err_bits != 0)
+        {
+            break;
+        }
+        prev = in;
+        block += 16;
+    }
+#else
+    // the same with SSSE3 (pshufb for the table lookups; nibbles from 16-bit
+    // shifts, as there are no byte shifts)
+    const __m128i t1h = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_1_high.data()))); // NOLINT(bugprone-casting-through-void)
+    const __m128i t1l = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_1_low.data()))); // NOLINT(bugprone-casting-through-void)
+    const __m128i t2h = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_2_high.data()))); // NOLINT(bugprone-casting-through-void)
+    const __m128i nibble = _mm_set1_epi8(0x0F);
+    const __m128i zero = _mm_setzero_si128();
+    __m128i prev = zero;
+    while (e - block >= 16)
+    {
+        const __m128i in = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(block))); // NOLINT(bugprone-casting-through-void)
+        const __m128i special = _mm_or_si128(_mm_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8('"')), _mm_cmpeq_epi8(in, _mm_set1_epi8('\\'))),
+                                             _mm_cmpeq_epi8(_mm_subs_epu8(in, _mm_set1_epi8(0x1F)), zero)); // in < 0x20
+        const __m128i prev1 = _mm_alignr_epi8(in, prev, 15);
+        const __m128i sc = _mm_and_si128(_mm_and_si128(_mm_shuffle_epi8(t1h, _mm_and_si128(_mm_srli_epi16(prev1, 4), nibble)),
+                                         _mm_shuffle_epi8(t1l, _mm_and_si128(prev1, nibble))),
+                                         _mm_shuffle_epi8(t2h, _mm_and_si128(_mm_srli_epi16(in, 4), nibble)));
+        const __m128i must23 = _mm_or_si128(_mm_subs_epu8(_mm_alignr_epi8(in, prev, 14), _mm_set1_epi8(0xE0 - 0x80)),
+                                            _mm_subs_epu8(_mm_alignr_epi8(in, prev, 13), _mm_set1_epi8(0xF0 - 0x80)));
+        const __m128i err = _mm_xor_si128(_mm_and_si128(must23, _mm_set1_epi8(static_cast<char>(-128))), sc);
+        const auto special_bits = static_cast<unsigned>(_mm_movemask_epi8(special));
+        const auto err_bits = ~static_cast<unsigned>(_mm_movemask_epi8(_mm_cmpeq_epi8(err, zero))) & 0xFFFFu;
+        if (special_bits != 0)
+        {
+            const auto k = static_cast<unsigned>(count_trailing_zeros(static_cast<std::uint64_t>(special_bits)));
+            if ((err_bits & ((2u << k) - 1u)) == 0)
+            {
+                block_out = block + k;
+                return true;
+            }
+            break;
+        }
+        if (err_bits != 0)
+        {
+            break;
+        }
+        prev = in;
+        block += 16;
+    }
+#endif
+    block_out = block;
+    return false;
+}
+#endif
+
+}  // namespace detail
+NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/detail/input/string_scan.hpp

@@ -14,6 +14,7 @@
 #include <cstring> // memcpy
 
 #include <nlohmann/detail/bit_ops.hpp>
+#include <nlohmann/detail/input/simd_scan.hpp>
 #include <nlohmann/detail/macro_scope.hpp>
 
 // Optional SIMD backend for bulk UTF-8 validation. This is an opt-in external
@@ -34,7 +35,7 @@
 // This file contains the byte-level string-scanning helpers used by the lexer's
 // contiguous fast path. They operate purely on raw bytes (no dependency on the
 // lexer's template parameters) so they are free functions, keeping the lexer
-// itself focused on the state machine; see lexer::scan_string_bulk().
+// itself focused on the state machine; see lexer::get_after_string_run().
 
 NLOHMANN_JSON_NAMESPACE_BEGIN
 namespace detail
@@ -66,7 +67,7 @@ inline std::uint64_t swar_string_special(std::uint64_t v) noexcept
 
 // return the index of the first is_string_special() byte in [data, data+n), or
 // n if every byte is ordinary; scans 8 bytes at a time
-inline std::size_t find_string_special(const unsigned char* data, std::size_t n) noexcept
+JSON_HEDLEY_ALWAYS_INLINE std::size_t find_string_special(const unsigned char* data, std::size_t n) noexcept
 {
     std::size_t i = 0;
     for (; i + 8 <= n; i += 8)
@@ -95,7 +96,7 @@ inline std::size_t find_string_special(const unsigned char* data, std::size_t n)
 // printable ASCII except '"' and '\\' - is emitted unchanged. Note this differs
 // from is_string_special() only in that 0x7F is also a stop (it is escaped as
 // \u007f under ensure_ascii).
-inline bool is_ascii_copyable(unsigned char c) noexcept
+constexpr bool is_ascii_copyable(unsigned char c) noexcept
 {
     return c >= 0x20u && c < 0x7Fu && c != '"' && c != '\\';
 }
@@ -235,35 +236,143 @@ inline std::size_t valid_utf8_prefix(const unsigned char* data, std::size_t n) n
     return pos;
 }
 
-// Scalar (C++11) computation of the bulk run length: the number of leading
+#if JSON_SCAN_VECTOR_UTF8
-// bytes in [data, data+n) that are ordinary ASCII or complete well-formed UTF-8
+/// the end of scan_string_vector from block, where the vector loop stopped
+/// (ill-formed UTF-8, or fewer than 16 bytes left): one byte or sequence at a
+/// time, from the start of a sequence that crosses into the block
+inline const unsigned char* scan_string_finish(const unsigned char* p, const unsigned char* block, const unsigned char* e) noexcept
+{
+    for (int i = 1; i <= 3 && block - i >= p; ++i)
+    {
+        const unsigned char c = block[-i];
+        if (c < 0x80)
+        {
+            break;
+        }
+        if (c >= 0xC0)
+        {
+            const int len = 2 + static_cast<int>(c >= 0xE0) + static_cast<int>(c >= 0xF0);
+            if (len > i)
+            {
+                block -= i;
+            }
+            break;
+        }
+    }
+    for (p = block; p != e;)
+    {
+        if (*p < 0x80)
+        {
+            if (is_string_special(*p))
+            {
+                return p;
+            }
+            ++p;
+            continue;
+        }
+        const std::size_t n = validate_one_utf8(p, static_cast<std::size_t>(e - p));
+        if (n == 0)
+        {
+            return p;
+        }
+        p += n;
+    }
+    return p;
+}
+
+/// the rest of a string from p (a character boundary), with the vector UTF-8
+/// check and the scalar check for the end of the block where it stopped
+inline const unsigned char* scan_string_vector(const unsigned char* p, const unsigned char* e) noexcept
+{
+    const unsigned char* block = p;
+    if (vector_utf8_run(p, e, block))
+    {
+        return block;
+    }
+    return scan_string_finish(p, block, e);
+}
+#endif
+
+#if JSON_SCAN_VECTOR
+/// the end of the run of plain string characters at @a p: the first quote,
+/// backslash, control character, or non-ASCII byte, or @a e. The first words
+/// are checked with SWAR (one; four with NEON, where the vector mask costs
+/// more), as most keys and short values end there; longer runs continue 16
+/// bytes at a time.
+JSON_HEDLEY_ALWAYS_INLINE const unsigned char* plain_run_end(const unsigned char* p, const unsigned char* e) noexcept
+{
+    constexpr int prefix_words = JSON_SCAN_NEON ? 4 : 1;
+    for (int words = prefix_words; words > 0 && e - p >= 8; --words)
+    {
+        const std::uint64_t special = swar_string_special(read_eight_bytes(p));
+        if (special != 0)
+        {
+            return p + (static_cast<std::size_t>(count_trailing_zeros(special)) / 8);
+        }
+        p += 8;
+    }
+    // the vector loop only for 16 bytes or more: the serializer passes a
+    // string without its closing quote, so most of its runs end at e, and a
+    // call of the out-of-line NEON loop for a shorter rest made dump() up to
+    // 10% slower
+    if (e - p >= 16)
+    {
+        p = vector_plain_run_long(p, e);
+        if (e - p >= 16)
+        {
+            return p; // the vector loop stopped at a special byte
+        }
+    }
+    return p + find_string_special(p, static_cast<std::size_t>(e - p));
+}
+#endif
+
+// Computation of the bulk run length: the number of leading bytes in
+// [data, data+n) that are ordinary ASCII or complete well-formed UTF-8
 // sequences, stopping before the first byte that needs individual handling (the
 // closing quote, an escape, a control character, or an ill-formed/truncated
-// sequence). ASCII is skipped 8 bytes at a time.
+// sequence). ASCII is skipped 16 bytes at a time with SSE2 and 8 bytes at a
-inline std::size_t scalar_string_bulk_run(const unsigned char* data, std::size_t n) noexcept
+// time otherwise; runs of non-ASCII text use the vector UTF-8 check where
+// available.
+JSON_HEDLEY_ALWAYS_INLINE std::size_t scalar_string_bulk_run(const unsigned char* data, std::size_t n) noexcept
 {
-    std::size_t pos = 0;
+    const unsigned char* const e = data + n;
-    while (pos < n)
+    const unsigned char* p = data;
+    while (p != e)
     {
-        pos += find_string_special(data + pos, n - pos);
+#if JSON_SCAN_VECTOR
-        if (pos >= n || data[pos] < 0x80u)
+        p = plain_run_end(p, e);
+#else
+        p += find_string_special(p, static_cast<std::size_t>(e - p));
+#endif
+        if (p == e || *p < 0x80u)
         {
             break; // end of buffer, or a quote/escape/control byte
         }
+#if JSON_SCAN_VECTOR_UTF8
+#if JSON_SCAN_SSSE3_DISPATCH
+        if (JSON_HEDLEY_LIKELY(cpu_has_ssse3()))
+#endif
+        {
+            return static_cast<std::size_t>(scan_string_vector(p, e) - data);
+        }
+#endif
+#if !JSON_SCAN_VECTOR_UTF8 || JSON_SCAN_SSSE3_DISPATCH
         // a run of multi-byte sequences (e.g. CJK text) is validated sequence
         // by sequence without searching for the next special byte in between
         do
         {
-            const std::size_t seq = validate_one_utf8(data + pos, n - pos);
+            const std::size_t seq = validate_one_utf8(p, static_cast<std::size_t>(e - p));
             if (seq == 0)
             {
-                return pos; // ill-formed or truncated: let the byte path diagnose it
+                return static_cast<std::size_t>(p - data); // ill-formed or truncated: let the byte path diagnose it
             }
-            pos += seq;
+            p += seq;
         }
-        while (pos < n && data[pos] >= 0x80u);
+        while (p != e && *p >= 0x80u);
+#endif
     }
-    return pos;
+    return static_cast<std::size_t>(p - data);
 }
 
 #if defined(JSON_USE_SIMDUTF) && defined(JSON_HAS_CPP_17)
@@ -304,7 +413,7 @@ inline std::size_t find_string_delimiter(const unsigned char* data, std::size_t
 // next delimiter is validated in one shot by simdutf; on the rare failure the
 // scalar helper recomputes the exact valid prefix so the byte path still
 // produces the precise diagnostic. Without it, the pure scalar path is used.
-inline std::size_t string_bulk_run(const unsigned char* data, std::size_t n) noexcept
+JSON_HEDLEY_ALWAYS_INLINE std::size_t string_bulk_run(const unsigned char* data, std::size_t n) noexcept
 {
 #if defined(JSON_USE_SIMDUTF) && defined(JSON_HAS_CPP_17)
     const std::size_t run = find_string_delimiter(data, n);
@@ -316,6 +425,42 @@ inline std::size_t string_bulk_run(const unsigned char* data, std::size_t n) noe
     return scalar_string_bulk_run(data, n);
 }
 
+#if JSON_SCAN_NEON && !(defined(JSON_USE_SIMDUTF) && defined(JSON_HAS_CPP_17))
+/// scalar_string_bulk_run() from @a start on, out of line (see
+/// lexer_string_bulk_run())
+JSON_HEDLEY_NEVER_INLINE inline std::size_t string_bulk_run_from(const unsigned char* data, std::size_t start, std::size_t n) noexcept
+{
+    return start + scalar_string_bulk_run(data + start, n - start);
+}
+#endif
+
+// string_bulk_run() for the lexer. With NEON, only the first four words are
+// checked inline (most keys and short values end there), and longer runs and
+// non-ASCII text continue out of line. The lexer's scan function runs once per
+// token, and the vector code inlined into it needs more registers, which every
+// token pays for: 5% of json::accept() on jeopardy.json with Apple Clang on
+// Apple M1, even though no string of that file reaches the vector code. The
+// serializer keeps string_bulk_run() inline, which is faster there.
+JSON_HEDLEY_ALWAYS_INLINE std::size_t lexer_string_bulk_run(const unsigned char* data, std::size_t n) noexcept
+{
+#if JSON_SCAN_NEON && !(defined(JSON_USE_SIMDUTF) && defined(JSON_HAS_CPP_17))
+    std::size_t i = 0;
+    for (int words = 4; words > 0 && n - i >= 8; --words)
+    {
+        const std::uint64_t special = swar_string_special(read_eight_bytes(data + i));
+        if (special != 0)
+        {
+            const std::size_t pos = i + (static_cast<std::size_t>(count_trailing_zeros(special)) / 8);
+            return data[pos] < 0x80u ? pos : string_bulk_run_from(data, pos, n);
+        }
+        i += 8;
+    }
+    return string_bulk_run_from(data, i, n);
+#else
+    return string_bulk_run(data, n);
+#endif
+}
+
 // Decode the 4 hex digits at [data, data+4) - the digits following a `\u`
 // escape - into a codepoint 0x0000..0xFFFF via one table lookup per byte
 // (after yyjson's read_hex_u16), or return -1 if any of the 4 bytes is not a

include/nlohmann/detail/iterators/iter_impl.hpp

@@ -108,33 +108,18 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
     {
         JSON_ASSERT(m_object != nullptr);
 
-        switch (m_object->m_data.m_type)
+        if (m_object->is_object())
         {
-            case value_t::object:
+            m_it.object_iterator = typename object_t::iterator();
-            {
+        }
-                m_it.object_iterator = typename object_t::iterator();
+        else if (m_object->is_array())
-                break;
+        {
-            }
+            m_it.array_iterator = typename array_t::iterator();
-
+        }
-            case value_t::array:
+        else
-            {
+        {
-                m_it.array_iterator = typename array_t::iterator();
+            // primitive (is_primitive(), including discarded)
-                break;
+            m_it.primitive_iterator = primitive_iterator_t();
-            }
-
-            case value_t::null:
-            case value_t::string:
-            case value_t::boolean:
-            case value_t::number_integer:
-            case value_t::number_unsigned:
-            case value_t::number_float:
-            case value_t::binary:
-            case value_t::discarded:
-            default:
-            {
-                m_it.primitive_iterator = primitive_iterator_t();
-                break;
-            }
         }
     }
 
@@ -249,33 +234,28 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
     {
         JSON_ASSERT(m_object != nullptr);
 
-        switch (m_object->m_data.m_type)
+        if (m_object->is_object())
         {
-            case value_t::object:
+            m_it.object_iterator = m_object->m_data.m_value.object->end();
-            {
+        }
-                m_it.object_iterator = m_object->m_data.m_value.object->end();
+        else if (m_object->is_array())
-                break;
+        {
-            }
+            m_it.array_iterator = m_object->m_data.m_value.array->end();
+        }
+        else
+        {
+            // primitive (is_primitive(), including discarded)
+            m_it.primitive_iterator.set_end();
+        }
+    }
 
-            case value_t::array:
+    /// @throw invalid_iterator.212 if @a other points to another container
-            {
+    template<typename IterImpl>
-                m_it.array_iterator = m_object->m_data.m_value.array->end();
+    JSON_HEDLEY_ALWAYS_INLINE void check_same_container(const IterImpl& other) const
-                break;
+    {
-            }
+        if (JSON_HEDLEY_UNLIKELY(m_object != other.m_object))
-
+        {
-            case value_t::null:
+            throw_literal<invalid_iterator>(exception_id::iterators_compare_different_values, "cannot compare iterators of different containers", m_object);
-            case value_t::string:
-            case value_t::boolean:
-            case value_t::number_integer:
-            case value_t::number_unsigned:
-            case value_t::number_float:
-            case value_t::binary:
-            case value_t::discarded:
-            default:
-            {
-                m_it.primitive_iterator.set_end();
-                break;
-            }
         }
     }
 
@@ -424,10 +404,7 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
     bool operator==(const IterImpl& other) const
     {
         // if objects are not the same, the comparison is undefined
-        if (JSON_HEDLEY_UNLIKELY(m_object != other.m_object))
+        check_same_container(other);
-        {
-            throw_literal<invalid_iterator>(exception_id::iterators_compare_different_values, "cannot compare iterators of different containers", m_object);
-        }
 
         // value-initialized forward iterators can be compared, and must compare equal to other value-initialized iterators of the same type #4493
         if (m_object == nullptr)
@@ -466,10 +443,7 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
     bool operator<(const iter_impl& other) const
     {
         // if objects are not the same, the comparison is undefined
-        if (JSON_HEDLEY_UNLIKELY(m_object != other.m_object))
+        check_same_container(other);
-        {
-            throw_literal<invalid_iterator>(exception_id::iterators_compare_different_values, "cannot compare iterators of different containers", m_object);
-        }
 
         // value-initialized forward iterators can be compared, and must compare equal to other value-initialized iterators of the same type #4493
         if (m_object == nullptr)
@@ -478,25 +452,18 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
             return false;
         }
 
-        switch (m_object->m_data.m_type)
+        if (m_object->is_object())
         {
-            case value_t::object:
+            throw_literal<invalid_iterator>(exception_id::iterator_order_on_object, "cannot compare order of object iterators", m_object);
-                throw_literal<invalid_iterator>(exception_id::iterator_order_on_object, "cannot compare order of object iterators", m_object);
-
-            case value_t::array:
-                return (m_it.array_iterator < other.m_it.array_iterator);
-
-            case value_t::null:
-            case value_t::string:
-            case value_t::boolean:
-            case value_t::number_integer:
-            case value_t::number_unsigned:
-            case value_t::number_float:
-            case value_t::binary:
-            case value_t::discarded:
-            default:
-                return (m_it.primitive_iterator < other.m_it.primitive_iterator);
         }
+
+        if (m_object->is_array())
+        {
+            return (m_it.array_iterator < other.m_it.array_iterator);
+        }
+
+        // primitive (is_primitive(), including discarded)
+        return (m_it.primitive_iterator < other.m_it.primitive_iterator);
     }
 
     /*!
@@ -534,30 +501,19 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
     {
         JSON_ASSERT(m_object != nullptr);
 
-        switch (m_object->m_data.m_type)
+        if (m_object->is_object())
         {
-            case value_t::object:
+            throw_literal<invalid_iterator>(exception_id::iterator_arithmetic_on_object, "cannot use offsets with object iterators", m_object);
-                throw_literal<invalid_iterator>(exception_id::iterator_arithmetic_on_object, "cannot use offsets with object iterators", m_object);
+        }
 
-            case value_t::array:
+        if (m_object->is_array())
-            {
+        {
-                std::advance(m_it.array_iterator, i);
+            std::advance(m_it.array_iterator, i);
-                break;
+        }
-            }
+        else
-
+        {
-            case value_t::null:
+            // primitive (is_primitive(), including discarded)
-            case value_t::string:
+            m_it.primitive_iterator += i;
-            case value_t::boolean:
-            case value_t::number_integer:
-            case value_t::number_unsigned:
-            case value_t::number_float:
-            case value_t::binary:
-            case value_t::discarded:
-            default:
-            {
-                m_it.primitive_iterator += i;
-                break;
-            }
         }
 
         return *this;
@@ -613,25 +569,18 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
     {
         JSON_ASSERT(m_object != nullptr);
 
-        switch (m_object->m_data.m_type)
+        if (m_object->is_object())
         {
-            case value_t::object:
+            throw_literal<invalid_iterator>(exception_id::iterator_arithmetic_on_object, "cannot use offsets with object iterators", m_object);
-                throw_literal<invalid_iterator>(exception_id::iterator_arithmetic_on_object, "cannot use offsets with object iterators", m_object);
-
-            case value_t::array:
-                return m_it.array_iterator - other.m_it.array_iterator;
-
-            case value_t::null:
-            case value_t::string:
-            case value_t::boolean:
-            case value_t::number_integer:
-            case value_t::number_unsigned:
-            case value_t::number_float:
-            case value_t::binary:
-            case value_t::discarded:
-            default:
-                return m_it.primitive_iterator - other.m_it.primitive_iterator;
         }
+
+        if (m_object->is_array())
+        {
+            return m_it.array_iterator - other.m_it.array_iterator;
+        }
+
+        // primitive (is_primitive(), including discarded)
+        return m_it.primitive_iterator - other.m_it.primitive_iterator;
     }
 
     /*!

include/nlohmann/detail/iterators/iteration_proxy.hpp

@@ -109,35 +109,25 @@ template<typename IteratorType> class iteration_proxy_value
     {
         JSON_ASSERT(anchor.m_object != nullptr);
 
-        switch (anchor.m_object->type())
+        if (anchor.m_object->is_array())
         {
             // use integer array index as key
-            case value_t::array:
+            if (array_index != array_index_last)
             {
-                if (array_index != array_index_last)
+                int_to_string( array_index_str, array_index );
-                {
+                array_index_last = array_index;
-                    int_to_string( array_index_str, array_index );
-                    array_index_last = array_index;
-                }
-                return array_index_str;
             }
-
+            return array_index_str;
-            // use key from the object
-            case value_t::object:
-                return anchor.key();
-
-            // use an empty key for all primitive types
-            case value_t::null:
-            case value_t::string:
-            case value_t::boolean:
-            case value_t::number_integer:
-            case value_t::number_unsigned:
-            case value_t::number_float:
-            case value_t::binary:
-            case value_t::discarded:
-            default:
-                return empty_str;
         }
+
+        if (anchor.m_object->is_object())
+        {
+            // use key from the object
+            return anchor.key();
+        }
+
+        // use an empty key for all primitive types
+        return empty_str;
     }
 
     /// return value of the iterator

include/nlohmann/detail/macro_scope.hpp

@@ -187,6 +187,22 @@
     #endif
 #endif
 
+// the byte order of the target where the compiler tells it (std::endian is
+// C++20 and cannot select code in #if): JSON_LITTLE_ENDIAN_TARGET or
+// JSON_BIG_ENDIAN_TARGET is 1, or both are 0 where it is unknown (code then
+// handles the bytes one at a time); MSVC and x86 targets are little-endian
+#if defined(_MSC_VER) || defined(__x86_64__) || defined(__i386__) \
+    || (defined(__BYTE_ORDER__) && defined(__ORDER_LITTLE_ENDIAN__) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__)
+    #define JSON_LITTLE_ENDIAN_TARGET 1 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
+    #define JSON_BIG_ENDIAN_TARGET 0 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
+#elif defined(__BYTE_ORDER__) && defined(__ORDER_BIG_ENDIAN__) && __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+    #define JSON_LITTLE_ENDIAN_TARGET 0 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
+    #define JSON_BIG_ENDIAN_TARGET 1 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
+#else
+    #define JSON_LITTLE_ENDIAN_TARGET 0 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
+    #define JSON_BIG_ENDIAN_TARGET 0 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
+#endif
+
 #ifdef JSON_HAS_CPP_17
     #define JSON_INLINE_VARIABLE inline
 #else

include/nlohmann/detail/macro_unscope.hpp

@@ -19,9 +19,20 @@
 #undef NLOHMANN_CAN_CALL_STD_FUNC_IMPL
 #undef JSON_INLINE_VARIABLE
 #undef JSON_NO_UNIQUE_ADDRESS
+#undef JSON_DISABLE_ENUM_SERIALIZATION
+#undef JSON_DISABLE_TUPLE_REFERENCE_CONVERSION
 #undef JSON_UNLOCKED_FILE_IO
 #undef JSON_DTOA_SSE2
 #undef JSON_DTOA_NEON
+#undef JSON_LITTLE_ENDIAN_TARGET
+#undef JSON_BIG_ENDIAN_TARGET
+#undef JSON_SCAN_NEON
+#undef JSON_SCAN_SSE2
+#undef JSON_SCAN_SSSE3
+#undef JSON_SCAN_SSSE3_DISPATCH
+#undef JSON_SCAN_SSSE3_TARGET
+#undef JSON_SCAN_VECTOR
+#undef JSON_SCAN_VECTOR_UTF8
 
 #ifndef JSON_TEST_KEEP_MACROS
     #undef JSON_CATCH
@@ -46,8 +57,6 @@
     #undef JSON_STRICT_BINARY_UTF8
     #undef JSON_DELETE_DEPRECATED_FUNCTIONS
     #undef JSON_USE_OBJECTS_FOR_ENUM_KEYED_MAPS
-    #undef JSON_DISABLE_ENUM_SERIALIZATION
-    #undef JSON_DISABLE_TUPLE_REFERENCE_CONVERSION
     #undef JSON_DISABLE_STREAM_BULK_SCAN
     #undef JSON_DISABLE_UNLOCKED_FILE_IO
 #endif

include/nlohmann/detail/meta/cpp_future.hpp

@@ -10,17 +10,26 @@
 #pragma once
 
 #include <cstddef> // size_t
-#include <type_traits> // conditional, enable_if, false_type, integral_constant, is_constructible, is_integral, is_same, remove_cv, remove_reference, true_type
+#include <type_traits> // conditional, enable_if, false_type, integral_constant, is_arithmetic, is_constructible, is_integral, is_same, remove_cv, remove_reference, true_type
 #include <utility> // index_sequence, make_index_sequence, index_sequence_for
 
 #include <nlohmann/detail/macro_scope.hpp>
 
+#ifdef JSON_HAS_CPP_17
+    #include <algorithm> // clamp
+#endif
+
 NLOHMANN_JSON_NAMESPACE_BEGIN
 namespace detail
 {
 
-template<typename T>
+#ifdef __cpp_lib_remove_cvref
-using uncvref_t = typename std::remove_cv<typename std::remove_reference<T>::type>::type;
+    template<typename T>
+    using uncvref_t = std::remove_cvref_t<T>;
+#else
+    template<typename T>
+    using uncvref_t = typename std::remove_cv<typename std::remove_reference<T>::type>::type;
+#endif
 
 #ifdef JSON_HAS_CPP_14
 
@@ -160,5 +169,19 @@ struct static_const
     constexpr T static_const<T>::value;
 #endif
 
+/// @a v bounded to [@a lo, @a hi] (requires !(hi < lo)); like std::clamp,
+/// but by value, so that static constexpr members can be passed without an
+/// out-of-line definition before C++17
+template<typename T, enable_if_t<std::is_arithmetic<T>::value, int> = 0>
+constexpr T clamp(T v, T lo, T hi) noexcept
+{
+#ifdef __cpp_lib_clamp
+    return std::clamp(v, lo, hi);
+#else
+    // NOLINTNEXTLINE(readability-avoid-nested-conditional-operator): a constant expression of C++11
+    return v < lo ? lo : (hi < v ? hi : v);
+#endif
+}
+
 }  // namespace detail
 NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/detail/meta/type_traits.hpp

@@ -313,6 +313,14 @@ struct char_traits<std::byte> : std::char_traits<char>
 // is_ functions //
 ///////////////////
 
+#ifdef __cpp_lib_logical_traits
+
+using std::conjunction;
+using std::disjunction;
+using std::negation;
+
+#else
+
 // https://en.cppreference.com/w/cpp/types/conjunction
 template<class...> struct conjunction : std::true_type { };
 template<class B> struct conjunction<B> : B { };
@@ -330,6 +338,8 @@ struct disjunction<B, Bn...>
 // https://en.cppreference.com/w/cpp/types/negation
 template<class B> struct negation : std::integral_constant < bool, !B::value > { };
 
+#endif
+
 // Reimplementation of is_constructible and is_default_constructible, due to them being broken for
 // std::pair and std::tuple until LWG 2367 fix (see https://cplusplus.github.io/LWG/lwg-defects.html#2367).
 // This causes compile errors in e.g., Clang 3.5 or GCC 4.9.
@@ -1060,8 +1070,12 @@ constexpr bool value_in_range_of(T val)
     return value_in_range_of_impl1<OfType, T>::test(val);
 }
 
-template<bool Value>
+#ifdef __cpp_lib_bool_constant
-using bool_constant = std::integral_constant<bool, Value>;
+    using std::bool_constant;
+#else
+    template<bool Value>
+    using bool_constant = std::integral_constant<bool, Value>;
+#endif
 
 // Stands in for number_unsigned_t in overload sets if it is the same type as
 // number_integer_t, so that the unsigned overloads do not collide with the

include/nlohmann/detail/output/output_adapters.hpp

@@ -55,6 +55,66 @@ using output_adapter_t = std::shared_ptr<output_adapter_protocol<CharType>>;
 /// output_vector_sink also appends writes of at least this size with insert()
 constexpr std::size_t max_reserve_size = 256;
 
+/// @brief copy @a length characters, at most 32, without a call of memcpy()
+///
+/// Short strings are the typical payload of a binary value, and a call of
+/// memcpy() costs more than copying them. A copy of 16 to 32 characters is two
+/// possibly overlapping 16-byte copies, one of 8 to 15 two 8-byte copies, and
+/// so on down to a single character; each is a fixed-size load and store.
+/// Nothing outside of [src, src + length) is read or written.
+template<typename CharType>
+inline void copy_short(CharType* dst, const CharType* src, const std::size_t length, std::true_type /*is_byte*/) noexcept
+{
+    JSON_ASSERT(length <= 32);
+    if (length >= 16)
+    {
+        std::array<char, 16> first; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
+        std::array<char, 16> last; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
+        std::memcpy(first.data(), src, 16);
+        std::memcpy(last.data(), src + (length - 16), 16);
+        std::memcpy(dst, first.data(), 16);
+        std::memcpy(dst + (length - 16), last.data(), 16);
+    }
+    else if (length >= 8)
+    {
+        std::array<char, 8> first; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
+        std::array<char, 8> last; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
+        std::memcpy(first.data(), src, 8);
+        std::memcpy(last.data(), src + (length - 8), 8);
+        std::memcpy(dst, first.data(), 8);
+        std::memcpy(dst + (length - 8), last.data(), 8);
+    }
+    else if (length >= 4)
+    {
+        std::array<char, 4> first; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
+        std::array<char, 4> last; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
+        std::memcpy(first.data(), src, 4);
+        std::memcpy(last.data(), src + (length - 4), 4);
+        std::memcpy(dst, first.data(), 4);
+        std::memcpy(dst + (length - 4), last.data(), 4);
+    }
+    else if (length != 0)
+    {
+        // 1 to 3: the first, the middle, and the last character
+        const CharType a = src[0];
+        const CharType b = src[length >> 1];
+        const CharType c = src[length - 1];
+        dst[0] = a;
+        dst[length >> 1] = b;
+        dst[length - 1] = c;
+    }
+}
+
+/// @brief copy @a length characters, of a character type wider than a byte
+template<typename CharType>
+inline void copy_short(CharType* dst, const CharType* src, const std::size_t length, std::false_type /*is_byte*/) noexcept
+{
+    std::memcpy(dst, src, length * sizeof(CharType));
+}
+
+/// the number of characters an empty vector is grown to by output_vector_sink
+constexpr std::size_t min_vector_sink_capacity = 64;
+
 /// @brief non-virtual output sink writing into a std::vector
 ///
 /// This sink is not part of the virtual output_adapter_protocol hierarchy: it is
@@ -78,7 +138,7 @@ class output_vector_sink
 {
   public:
     explicit output_vector_sink(std::vector<CharType, AllocatorType>& vec) noexcept
-        : v(&vec), position(vec.size())
+        : v(&vec), cursor(vec.data() + vec.size()), limit(cursor)
     {}
 
     output_vector_sink(const output_vector_sink&) = delete;
@@ -86,7 +146,7 @@ class output_vector_sink
     output_vector_sink& operator=(output_vector_sink&&) = delete;
 
     output_vector_sink(output_vector_sink&& other) noexcept
-        : v(other.v), position(other.position)
+        : v(other.v), cursor(other.cursor), limit(other.limit)
     {
         other.v = nullptr;
     }
@@ -95,7 +155,7 @@ class output_vector_sink
     {
         if (v != nullptr)
         {
-            v->resize(position);
+            v->resize(position());
         }
     }
 
@@ -104,11 +164,11 @@ class output_vector_sink
     JSON_HEDLEY_ALWAYS_INLINE
     void write_character(CharType c)
     {
-        if (JSON_HEDLEY_UNLIKELY(position == v->size()))
+        if (JSON_HEDLEY_UNLIKELY(cursor == limit))
         {
             grow(1);
         }
-        (*v)[position++] = c;
+        *cursor++ = c;
     }
 
     // no JSON_HEDLEY_NON_NULL here: binary_writer legitimately passes a null
@@ -117,7 +177,7 @@ class output_vector_sink
     JSON_HEDLEY_ALWAYS_INLINE
     void write_characters(const CharType* s, std::size_t length)
     {
-        if (JSON_HEDLEY_UNLIKELY(v->size() - position < length))
+        if (JSON_HEDLEY_UNLIKELY(space() < length))
         {
             if (length >= max_reserve_size)
             {
@@ -126,10 +186,15 @@ class output_vector_sink
             }
             grow(length);
         }
-        if (length != 0)
+        if (length <= 32)
         {
-            std::memcpy(v->data() + position, s, length * sizeof(CharType));
+            copy_short(cursor, s, length, std::integral_constant<bool, sizeof(CharType) == 1>());
-            position += length;
+            cursor += length;
+        }
+        else
+        {
+            std::memcpy(cursor, s, length * sizeof(CharType));
+            cursor += length;
         }
     }
 
@@ -144,21 +209,37 @@ class output_vector_sink
     CharType* reserve(const std::size_t length)
     {
         JSON_ASSERT(length <= max_reserve_size);
-        if (JSON_HEDLEY_UNLIKELY(v->size() - position < length))
+        if (JSON_HEDLEY_UNLIKELY(space() < length))
         {
             grow(length);
         }
-        return v->data() + position;
+        return cursor;
     }
 
     /// keep the first @a length characters written to the space from reserve()
     JSON_HEDLEY_ALWAYS_INLINE
     void commit(const std::size_t length) noexcept
     {
-        position += length;
+        cursor += length;
     }
 
+    /// nothing to pass on: the characters are in the vector (see output_adapter_sink)
+    void flush() noexcept
+    {}
+
   private:
+    /// number of characters of *v written so far
+    std::size_t position() const noexcept
+    {
+        return static_cast<std::size_t>(cursor - v->data());
+    }
+
+    /// number of characters that fit the vector behind the write position
+    std::size_t space() const noexcept
+    {
+        return static_cast<std::size_t>(limit - cursor);
+    }
+
     /// make room for at least @a length more characters after the position;
     /// kept out of line so that the write functions stay small enough for
     /// GCC to inline them into the writer
@@ -166,12 +247,15 @@ class output_vector_sink
     void grow(const std::size_t length)
     {
         // use the capacity the vector already has, else at least double it;
-        // never less than 64 characters, so that a small value does not
+        // never less than min_vector_sink_capacity, so that a small value does not
         // reallocate for every few bytes
-        const std::size_t needed = position + length;
+        const std::size_t written = position();
-        v->resize((std::max)(std::size_t{64}, needed <= v->capacity()
+        const std::size_t needed = written + length;
+        v->resize((std::max)(min_vector_sink_capacity, needed <= v->capacity()
                              ? v->capacity()
                              : (std::max)(needed, v->capacity() * 2)));
+        cursor = v->data() + written;
+        limit = v->data() + v->size();
     }
 
     /// append @a length (at least max_reserve_size) characters that do not fit
@@ -181,20 +265,24 @@ class output_vector_sink
     JSON_HEDLEY_NEVER_INLINE
     void append(const CharType* s, const std::size_t length)
     {
-        v->resize(position);
+        const std::size_t written = position();
-        if (v->capacity() - position < length)
+        v->resize(written);
+        if (v->capacity() - written < length)
         {
             // grow geometrically, with room for the writes that follow, so
             // that the next grow() need not reallocate right away
-            v->reserve((std::max)(v->capacity() * 2, position + length + max_reserve_size));
+            v->reserve((std::max)(v->capacity() * 2, written + length + max_reserve_size));
         }
         v->insert(v->end(), s, s + length);
-        position = v->size();
+        cursor = v->data() + v->size();
+        limit = cursor;
     }
 
     std::vector<CharType, AllocatorType>* v;
-    /// number of characters of *v written so far
+    /// the write position: in *v, at the number of characters written so far
-    std::size_t position;
+    CharType* cursor;
+    /// the end of *v
+    CharType* limit;
 };
 
 /// output adapter for byte vectors
@@ -277,9 +365,17 @@ class output_string_adapter : public output_adapter_protocol<CharType>
 ///
 /// Wraps the polymorphic output_adapter_t so the same binary_writer template can
 /// also target arbitrary adapters (output streams, strings, user-provided
-/// adapters) via the `output_adapter`-based overloads. Each write still goes
+/// adapters) via the `output_adapter`-based overloads.
-/// through one virtual call, exactly as before; only the concrete sinks above
+///
-/// avoid it.
+/// A write through the adapter is a virtual call, and for a stream a call with
+/// a sentry on top, which costs more than encoding the few bytes of most values.
+/// The sink therefore collects what is written in a buffer and passes it on in
+/// one piece when it is full, a write is too large for it, or @ref flush is
+/// called. Everything written reaches the adapter in the same order and with
+/// the same bytes; the destructor passes on what is left, so that a write that
+/// throws leaves the adapter with exactly the bytes written before it. Only
+/// @ref flush can report an error of the adapter (the destructor must not
+/// throw), so it has to be called once the value is written.
 template<typename CharType>
 class output_adapter_sink
 {
@@ -290,36 +386,121 @@ class output_adapter_sink
         JSON_ASSERT(oa);
     }
 
+    output_adapter_sink(const output_adapter_sink&) = delete;
+    output_adapter_sink& operator=(const output_adapter_sink&) = delete;
+    output_adapter_sink& operator=(output_adapter_sink&&) = delete;
+
+    output_adapter_sink(output_adapter_sink&& other) noexcept
+        : oa(std::move(other.oa)), used(other.used)
+    {
+        std::memcpy(buffer.data(), other.buffer.data(), other.used * sizeof(CharType));
+        other.used = 0;
+    }
+
+    ~output_adapter_sink()
+    {
+        // a normal return has flushed already, so this is for a write that threw
+        if (used != 0)
+        {
+            JSON_TRY
+            {
+                flush();
+            }
+            JSON_CATCH(...)
+            {
+                // nothing can be done about an adapter that throws here
+            }
+        }
+    }
+
+    JSON_HEDLEY_ALWAYS_INLINE
     void write_character(CharType c)
     {
-        oa->write_character(c);
+        if (JSON_HEDLEY_UNLIKELY(used == buffer_size))
+        {
+            flush();
+        }
+        buffer[used++] = c;
     }
 
     // no JSON_HEDLEY_NON_NULL: forwards (null, 0) for empty payloads, exactly as
     // the type-erased path already did before this sink existed
+    JSON_HEDLEY_ALWAYS_INLINE
     void write_characters(const CharType* s, std::size_t length)
     {
-        oa->write_characters(s, length);
+        if (JSON_HEDLEY_UNLIKELY(buffer_size - used < length))
+        {
+            write_large(s, length);
+            return;
+        }
+        if (length <= 32)
+        {
+            copy_short(buffer.data() + used, s, length, std::integral_constant<bool, sizeof(CharType) == 1>());
+            used += length;
+        }
+        else
+        {
+            std::memcpy(buffer.data() + used, s, length * sizeof(CharType));
+            used += length;
+        }
     }
 
     /// space for writing up to @a length characters (see
     /// output_vector_sink::reserve)
-    CharType* reserve(const std::size_t length) noexcept
+    JSON_HEDLEY_ALWAYS_INLINE
+    CharType* reserve(const std::size_t length)
     {
         JSON_ASSERT(length <= max_reserve_size);
-        static_cast<void>(length);
+        if (JSON_HEDLEY_UNLIKELY(buffer_size - used < length))
-        return reserved.data();
+        {
+            flush();
+        }
+        return buffer.data() + used;
     }
 
-    /// write the first @a length characters written to the space from reserve()
+    /// keep the first @a length characters written to the space from reserve()
-    void commit(const std::size_t length)
+    JSON_HEDLEY_ALWAYS_INLINE
+    void commit(const std::size_t length) noexcept
     {
-        oa->write_characters(reserved.data(), length);
+        used += length;
+    }
+
+    /// pass everything written so far on to the adapter
+    void flush()
+    {
+        if (used != 0)
+        {
+            // reset first: the characters count as written even if the adapter throws
+            const std::size_t length = used;
+            used = 0;
+            oa->write_characters(buffer.data(), length);
+        }
     }
 
   private:
+    /// a write that does not fit the space left in the buffer
+    JSON_HEDLEY_NEVER_INLINE
+    void write_large(const CharType* s, const std::size_t length)
+    {
+        flush();
+        if (length >= buffer_size)
+        {
+            oa->write_characters(s, length);
+        }
+        else
+        {
+            std::memcpy(buffer.data(), s, length * sizeof(CharType));
+            used = length;
+        }
+    }
+
+    /// large enough for reserve() at any time
+    static constexpr std::size_t buffer_size = 4 * max_reserve_size;
+
     output_adapter_t<CharType> oa;
-    std::array<CharType, max_reserve_size> reserved{};
+    /// number of characters of @ref buffer not yet passed on
+    std::size_t used = 0;
+    std::array<CharType, buffer_size> buffer{};
 };
 
 /// @brief whether std::basic_string<CharType> has a non-deprecated std::char_traits

include/nlohmann/detail/string_utils.hpp

@@ -48,6 +48,24 @@ inline std::string hex_byte(const std::uint8_t byte)
     return result;
 }
 
+/*!
+@brief write a UTF-16 code unit as four lowercase hexadecimal digits
+
+The lowercase counterpart of hex_byte(), used for the `\\uXXXX` escapes of the
+serializers, whose output is lowercase. Writes exactly four characters to
+@a out and returns the pointer past them.
+*/
+JSON_HEDLEY_ALWAYS_INLINE char* hex4_lower(const std::uint16_t codeunit, char* out) noexcept
+{
+    constexpr const char* nibble_to_hex = "0123456789abcdef";
+    const unsigned int unit = codeunit;
+    out[0] = nibble_to_hex[(unit >> 12u) & 0x0Fu];
+    out[1] = nibble_to_hex[(unit >> 8u) & 0x0Fu];
+    out[2] = nibble_to_hex[(unit >> 4u) & 0x0Fu];
+    out[3] = nibble_to_hex[unit & 0x0Fu];
+    return out + 4;
+}
+
 ///////////////////
 // UTF-8 encoding //
 ///////////////////
@@ -103,6 +121,66 @@ void encode_utf8(std::uint32_t cp, const Out& out)
     }
 }
 
+/*!
+@brief the shape of a well-formed UTF-8 sequence, by its lead byte
+
+@a length is 1 for ASCII, 2 to 4 for a valid lead byte, and 0 for a byte that
+cannot start a well-formed sequence (a continuation byte, 0xC0, 0xC1, or 0xF5
+to 0xFF). For a multibyte sequence, the second byte must lie in
+[@a second_lo, @a second_hi], and every later byte in [0x80, 0xBF]
+(RFC 3629, section 4; Unicode Table 3-7). The narrower second-byte ranges
+exclude overlong forms (0xE0, 0xF0), surrogates (0xED), and code points
+beyond U+10FFFF (0xF4).
+*/
+struct utf8_sequence_shape
+{
+    std::uint8_t length;
+    std::uint8_t second_lo;
+    std::uint8_t second_hi;
+};
+
+/// @return the shape of a UTF-8 sequence starting with @a lead, see utf8_sequence_shape
+inline utf8_sequence_shape utf8_shape(const std::uint8_t lead) noexcept
+{
+    if (lead < 0x80u)
+    {
+        return {1, 0, 0};
+    }
+    if (lead < 0xC2u)
+    {
+        return {0, 0, 0};
+    }
+    if (lead <= 0xDFu)
+    {
+        return {2, 0x80u, 0xBFu};
+    }
+    if (lead == 0xE0u)
+    {
+        return {3, 0xA0u, 0xBFu};
+    }
+    if (lead == 0xEDu)
+    {
+        return {3, 0x80u, 0x9Fu};
+    }
+    if (lead <= 0xEFu)
+    {
+        return {3, 0x80u, 0xBFu};
+    }
+    if (lead == 0xF0u)
+    {
+        return {4, 0x90u, 0xBFu};
+    }
+    if (lead <= 0xF3u)
+    {
+        return {4, 0x80u, 0xBFu};
+    }
+    if (lead == 0xF4u)
+    {
+        return {4, 0x80u, 0x8Fu};
+    }
+    return {0, 0, 0};
+}
+
 ///////////////////
 // UTF-8 decoding //
 ///////////////////
@@ -118,7 +196,7 @@ This is a single-byte step of a "shift-based" UTF-8 decoder originally
 written by Björn Hoehrmann. See
 http://bjoern.hoehrmann.de/utf-8/decoder/dfa/ for details.
 
-The library checks UTF-8 well-formedness (RFC 3629, section 4) in three
+The library checks UTF-8 well-formedness (RFC 3629, section 4) in five
 places, which differ in speed, diagnostics, and how they read the input:
 
 - decode() below: the serializer, to escape and, in strict mode, reject
@@ -132,10 +210,15 @@ places, which differ in speed, diagnostics, and how they read the input:
   bulk string scan, the bulk path of the BON8 reader, and the BON8 writer.
   They must accept exactly what the lexer's switch accepts.
 - the byte path of binary_reader::get_bon8_string(): BON8 input without bulk
-  access, and the bytes the bulk path leaves to it.
+  access, and the bytes the bulk path leaves to it. It keeps its own ranges:
+  taking them from utf8_shape() made BON8 decoding 2-3% slower (#5891).
+- check_utf8() in detail/view/edit.hpp: strings stored in an editable
+  json_document, with the index of the offending byte. It also uses
+  utf8_shape().
 
-All four must accept the same set of sequences, so a change to one needs a
+All five must accept the same set of sequences, which the test "UTF-8
-matching change to the others.
+validators accept the same sequences" in unit-class_lexer.cpp checks
+exhaustively against decode() and utf8_shape().
 
 @param[in,out] state  the current decoder state
 @param[in,out] codep  codepoint (valid only if resulting state is UTF8_ACCEPT)

include/nlohmann/detail/value_t.hpp

@@ -177,6 +177,36 @@ inline bool owns_memory(const value_t t) noexcept
     }
 }
 
+/*!
+@brief whether a value of the given type is neither an object nor an array
+
+Unlike basic_json::is_primitive(), this includes value_t::discarded: it names
+the types that iterators walk with a primitive_iterator_t (a single value, or no
+value for null and discarded) and that JSON Pointer resolution and the
+serializer treat as leaves. Every enumerator is listed so that -Wswitch-enum
+flags this function when a new type is added.
+*/
+inline bool is_primitive(const value_t t) noexcept
+{
+    switch (t)
+    {
+        case value_t::object:
+        case value_t::array:
+            return false;
+
+        case value_t::null:
+        case value_t::string:
+        case value_t::boolean:
+        case value_t::number_integer:
+        case value_t::number_unsigned:
+        case value_t::number_float:
+        case value_t::binary:
+        case value_t::discarded:
+        default:
+            return true;
+    }
+}
+
 
 /*!
 @brief compare an integer with a floating point number without precision loss

include/nlohmann/detail/view/edit.hpp

@@ -51,11 +51,6 @@ struct first_true<false, Conditions...> : std::integral_constant < int, 1 + firs
 inline void check_utf8(const char* s, std::size_t n)
 {
     const auto* const p = reinterpret_cast<const unsigned char*>(s); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-    const auto hex = [](unsigned char c)
-    {
-        constexpr const char* digits = "0123456789ABCDEF";
-        return std::string{digits[c >> 4u], digits[c & 0xFu]};
-    };
     for (std::size_t i = 0; i < n;)
     {
         const unsigned char c = p[i];
@@ -64,39 +59,22 @@ inline void check_utf8(const char* s, std::size_t n)
             ++i;
             continue;
         }
-        std::size_t len = 0;
+        const utf8_sequence_shape shape = utf8_shape(c);
-        unsigned char lo = 0x80;
+        const std::size_t len = shape.length;
-        unsigned char hi = 0xBF;
+        if (len == 0)
-        if (c >= 0xC2 && c <= 0xDF)
         {
-            len = 2;
+            throw_type_error(exception_id::invalid_utf8, concat("invalid UTF-8 byte at index ", std::to_string(i), ": 0x", hex_byte(c)));
-        }
-        else if (c >= 0xE0 && c <= 0xEF)
-        {
-            len = 3;
-            lo = c == 0xE0 ? 0xA0 : 0x80;
-            hi = c == 0xED ? 0x9F : 0xBF;
-        }
-        else if (c >= 0xF0 && c <= 0xF4)
-        {
-            len = 4;
-            lo = c == 0xF0 ? 0x90 : 0x80;
-            hi = c == 0xF4 ? 0x8F : 0xBF;
-        }
-        else
-        {
-            throw_type_error(316, concat("invalid UTF-8 byte at index ", std::to_string(i), ": 0x", hex(c)));
         }
         for (std::size_t k = 1; k < len; ++k)
         {
             if (i + k == n)
             {
-                throw_type_error(316, concat("incomplete UTF-8 string; last byte: 0x", hex(p[n - 1])));
+                throw_type_error(exception_id::invalid_utf8, concat("incomplete UTF-8 string; last byte: 0x", hex_byte(p[n - 1])));
             }
             const unsigned char b = p[i + k];
-            if (b < (k == 1 ? lo : 0x80) || b > (k == 1 ? hi : 0xBF))
+            if (b < (k == 1 ? shape.second_lo : 0x80) || b > (k == 1 ? shape.second_hi : 0xBF))
             {
-                throw_type_error(316, concat("invalid UTF-8 byte at index ", std::to_string(i + k), ": 0x", hex(b)));
+                throw_type_error(exception_id::invalid_utf8, concat("invalid UTF-8 byte at index ", std::to_string(i + k), ": 0x", hex_byte(b)));
             }
         }
         i += len;
@@ -144,7 +122,7 @@ class editor
         node* const o = own(object);
         if (o->kind != static_cast<std::uint8_t>(value_t::object) && o->kind != static_cast<std::uint8_t>(value_t::null))
         {
-            throw_type_error(305, "cannot use operator[] with a string argument with ", object.type_name());
+            throw_type_error(exception_id::subscript_wrong_type, "cannot use operator[] with a string argument with ", object.type_name());
         }
         check_utf8(key.data(), key.size());
         const encoded e = encode(std::forward<V>(value));
@@ -195,7 +173,7 @@ class editor
         node* const a = own(array);
         if (a->kind != static_cast<std::uint8_t>(value_t::array))
         {
-            throw_type_error(305, "cannot use operator[] with a numeric argument with ", array.type_name());
+            throw_type_error(exception_id::subscript_wrong_type, "cannot use operator[] with a numeric argument with ", array.type_name());
         }
         check_index(idx, a->len);
         const encoded e = encode(std::forward<V>(value));
@@ -212,7 +190,7 @@ class editor
         node* const a = own(array);
         if (a->kind != static_cast<std::uint8_t>(value_t::array) && a->kind != static_cast<std::uint8_t>(value_t::null))
         {
-            throw_type_error(308, "cannot use push_back() with ", array.type_name());
+            throw_type_error(exception_id::push_back_wrong_type, "cannot use push_back() with ", array.type_name());
         }
         const encoded e = encode(std::forward<V>(value));
         if (a->kind == static_cast<std::uint8_t>(value_t::null))
@@ -236,7 +214,7 @@ class editor
         node* const a = own(array);
         if (a->kind != static_cast<std::uint8_t>(value_t::array))
         {
-            throw_type_error(309, "cannot use insert() with ", array.type_name());
+            throw_type_error(exception_id::insert_wrong_type, "cannot use insert() with ", array.type_name());
         }
         check_index(idx, a->len + 1);
         const encoded e = encode(std::forward<V>(value));
@@ -256,7 +234,7 @@ class editor
         node* const o = own(object);
         if (o->kind != static_cast<std::uint8_t>(value_t::object))
         {
-            throw_type_error(307, "cannot use erase() with ", object.type_name());
+            throw_type_error(exception_id::erase_wrong_type, "cannot use erase() with ", object.type_name());
         }
         for (const node* k = nav::first(m_doc, o), *end = nav::end(m_doc, o); k != end; k = document_data::after(k + 1))
         {
@@ -274,7 +252,7 @@ class editor
         node* const a = own(array);
         if (a->kind != static_cast<std::uint8_t>(value_t::array))
         {
-            throw_type_error(307, "cannot use erase() with ", array.type_name());
+            throw_type_error(exception_id::erase_wrong_type, "cannot use erase() with ", array.type_name());
         }
         check_index(idx, a->len);
         node* const h = block_of(m_doc, a, 0);
@@ -297,7 +275,7 @@ class editor
     {
         if (NLOHMANN_VIEW_UNLIKELY(v.m_doc != &m_doc || v.m_node == nullptr))
         {
-            throw_invalid_iterator(202, "view does not belong to this document");
+            throw_invalid_iterator(exception_id::iterator_from_other_value, "view does not belong to this document");
         }
         edit_state_of(m_doc);
         return const_cast<node*>(v.m_node); // NOLINT(cppcoreguidelines-pro-type-const-cast): the nodes belong to this document
@@ -307,7 +285,7 @@ class editor
     {
         if (idx >= limit)
         {
-            throw_out_of_range(401, concat("array index ", std::to_string(idx), " is out of range"));
+            throw_array_index_out_of_range(idx);
         }
     }
 
@@ -448,7 +426,7 @@ class editor
     {
         if (NLOHMANN_VIEW_UNLIKELY(v.m_node == nullptr))
         {
-            throw_type_error(302, "type must be a value, but is ", "discarded");
+            throw_type_error(exception_id::type_mismatch, "type must be a value, but is ", "discarded");
         }
         encoded r;
         if (!is_container(*v.m_node))
@@ -598,7 +576,7 @@ class editor
     {
         if (NLOHMANN_VIEW_UNLIKELY(len >= 0xFFFFFFFFu))
         {
-            throw_out_of_range(416, "strings of 4 GiB or more are not supported by json_document"); // LCOV_EXCL_LINE
+            throw_out_of_range(exception_id::document_too_large, "strings of 4 GiB or more are not supported by json_document"); // LCOV_EXCL_LINE
         }
         node n = plain_node(value_t::string);
         n.flags = static_cast<std::uint8_t>(n.flags | node_flags::edited);
@@ -673,12 +651,12 @@ class editor
                 return string_node(s.data(), s.size());
             }
             case value_t::binary:
-                throw_type_error(319, "cannot store a binary value in a json_document", "");
+                throw_type_error(exception_id::document_binary_value, "cannot store a binary value in a json_document", "");
             case value_t::discarded:
             case value_t::object:
             case value_t::array:
             default:
-                throw_type_error(302, "type must be a value, but is ", "discarded");
+                throw_type_error(exception_id::type_mismatch, "type must be a value, but is ", "discarded");
         }
     }
 

include/nlohmann/detail/view/edit_storage.hpp

@@ -84,7 +84,7 @@ inline std::size_t text_capacity(std::size_t cap, std::size_t used, std::size_t
     constexpr std::size_t limit = 0xFFFFFFFFu;
     if (NLOHMANN_VIEW_UNLIKELY(used > limit || n > limit - used))
     {
-        throw_out_of_range(416, "edits of 4 GiB or more are not supported by json_document");
+        throw_out_of_range(exception_id::document_too_large, "edits of 4 GiB or more are not supported by json_document");
     }
     const std::size_t needed = used + n;
     const std::size_t wanted = needed + (std::min)(limit - needed, std::size_t{256});
@@ -135,7 +135,7 @@ inline void reserve_moved(document_data& d)
     document_data::edit_state& e = edit_state_of(d);
     if (e.moved.size() >= 0xFFFFFFFFu)
     {
-        throw_out_of_range(416, "more than 4294967295 edited arrays and objects are not supported by json_document"); // LCOV_EXCL_LINE
+        throw_out_of_range(exception_id::document_too_large, "more than 4294967295 edited arrays and objects are not supported by json_document"); // LCOV_EXCL_LINE
     }
     if (e.moved.size() == e.moved.capacity() || e.moved_cap.size() == e.moved_cap.capacity())
     {

include/nlohmann/detail/view/errors.hpp

@@ -25,32 +25,52 @@ namespace view
 // Exceptions are thrown out of line, so that the accessors that may throw stay
 // small enough to be inlined.
 
-[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_type_error(int id, const char* prefix, const char* type)
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_type_error(exception_id id, const char* prefix, const char* type)
 {
     NLOHMANN_VIEW_THROW(type_error::create(id, concat(prefix, type), nullptr));
 }
 
-[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_type_error(int id, const std::string& msg)
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_type_error(exception_id id, const std::string& msg)
 {
     NLOHMANN_VIEW_THROW(type_error::create(id, msg, nullptr));
 }
 
-[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_out_of_range(int id, const std::string& msg)
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_out_of_range(exception_id id, const std::string& msg)
 {
     NLOHMANN_VIEW_THROW(out_of_range::create(id, msg, nullptr));
 }
 
-[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_invalid_iterator(int id, const char* msg)
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_invalid_iterator(exception_id id, const char* msg)
 {
     NLOHMANN_VIEW_THROW(invalid_iterator::create(id, msg, nullptr));
 }
 
 /// a parse error without a position (as those of json_pointer)
-[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_parse_error(int id, const std::string& msg)
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_parse_error(exception_id id, const std::string& msg)
 {
     NLOHMANN_VIEW_THROW(parse_error::create(id, 0, msg, nullptr));
 }
 
+/// out_of_range.401: the array index @a idx is not below the size
+template<typename Index>
+[[noreturn]] NLOHMANN_VIEW_NOINLINE void throw_array_index_out_of_range(const Index idx)
+{
+    throw_out_of_range(exception_id::array_index_out_of_range, concat("array index ", std::to_string(idx), " is out of range"));
+}
+
+/// out_of_range.402: the JSON Pointer token '-' of an array of @a size elements
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_array_index_past_end(std::size_t size)
+{
+    throw_out_of_range(exception_id::pointer_past_the_end_index, concat("array index '-' (", std::to_string(size), ") is out of range"));
+}
+
+/// out_of_range.403: the object has no member @a key
+template<typename Key>
+[[noreturn]] NLOHMANN_VIEW_NOINLINE void throw_key_not_found(const Key& key)
+{
+    throw_out_of_range(exception_id::key_not_found, concat("key '", key, "' not found"));
+}
+
 /// SAX handler of the error replay: accepts every event without storing it,
 /// and throws the exception the parser reports
 template<typename BasicJsonType>
@@ -149,7 +169,7 @@ template<typename BasicJsonType>
     if (f.code == error_code::input_too_large)
     {
         // (the limit is detail::view::max_input_size(): 4 GiB minus 16 bytes)
-        NLOHMANN_VIEW_THROW(out_of_range::create(416, "input of 4294967280 bytes or more is not supported by json_document", nullptr));
+        NLOHMANN_VIEW_THROW(out_of_range::create(exception_id::document_too_large, "input of 4294967280 bytes or more is not supported by json_document", nullptr));
     }
     throwing_sax<BasicJsonType> sax;
     const bool accepted = BasicJsonType::sax_parse(src, src + size, &sax, input_format_t::json, true, ignore_comments, ignore_trailing_commas);
@@ -169,7 +189,7 @@ template<typename BasicJsonType>
         }
     }
     pos.chars_read_current_line = off + 1 - line_start;
-    NLOHMANN_VIEW_THROW(parse_error::create(101, pos, "syntax error while parsing value", nullptr));
+    NLOHMANN_VIEW_THROW(parse_error::create(exception_id::syntax_error, pos, "syntax error while parsing value", nullptr));
     // LCOV_EXCL_STOP
 }
 

include/nlohmann/detail/view/image.hpp

@@ -186,7 +186,7 @@ inline void compact_nodes(const document_data& d, std::size_t arena_size, std::v
 inline std::vector<std::uint8_t> save_image(const document_data& d)
 {
 #if !NLOHMANN_VIEW_LITTLE_ENDIAN
-    throw_type_error(320, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
+    throw_type_error(exception_id::document_image_unsupported, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
 #endif
     const std::size_t arena_size = d.arena_size;
     std::vector<node> compacted;
@@ -203,7 +203,7 @@ inline std::vector<std::uint8_t> save_image(const document_data& d)
     if (NLOHMANN_VIEW_UNLIKELY(text_size >= image_limit || total_arena >= image_limit || count >= image_limit))
     {
         // LCOV_EXCL_START (4 GiB)
-        throw_out_of_range(416, "images of 4 GiB or more are not supported by json_document");
+        throw_out_of_range(exception_id::document_too_large, "images of 4 GiB or more are not supported by json_document");
         // LCOV_EXCL_STOP
     }
     image_header h{};
@@ -660,7 +660,7 @@ inline bool check_image(const node* nodes, std::size_t count, const unsigned cha
 
 [[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_invalid_image(const char* what)
 {
-    throw_parse_error(116, concat("invalid json_document image: ", what));
+    throw_parse_error(exception_id::invalid_document_image, concat("invalid json_document image: ", what));
 }
 
 /// Read an image into d. The text and the decoded strings stay in the image;
@@ -668,7 +668,7 @@ inline bool check_image(const node* nodes, std::size_t count, const unsigned cha
 inline void load_image(document_data& d, const std::uint8_t* image, std::size_t size, image_check check)
 {
 #if !NLOHMANN_VIEW_LITTLE_ENDIAN
-    throw_type_error(320, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
+    throw_type_error(exception_id::document_image_unsupported, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
 #endif
     if (image == nullptr || size < sizeof(image_header))
     {

include/nlohmann/detail/view/iterator.hpp

@@ -110,7 +110,7 @@ class view_iterator
     {
         if (NLOHMANN_VIEW_UNLIKELY(m_value_offset == 0))
         {
-            throw_invalid_iterator(207, "cannot use key() for non-object iterators");
+            throw_invalid_iterator(exception_id::iterator_key_not_object, "cannot use key() for non-object iterators");
         }
         return string_view_t(m_doc->str(*m_pos), m_pos->len);
     }

include/nlohmann/detail/view/pointer.hpp

@@ -32,51 +32,15 @@ enum class pointer_mode
     contains,  ///< as basic_json::contains(): no exceptions at all
 };
 
-/// the outcome of reading an array index from a reference token
+/// the outcome of reading an array index: detail::parse_array_index(), shared with json_pointer
-enum class index_status
+using index_status = detail::array_index_status;
-{
-    ok,
-    leading_zero, ///< parse_error.106
-    not_number,   ///< parse_error.109
-    unresolved,   ///< out_of_range.404
-    too_large,    ///< out_of_range.410
-};
 
 /// reads an array index like json_pointer::array_index (RFC 6901, Sect. 4),
 /// but reports errors instead of throwing them
 template<typename StringType>
 index_status array_index(const StringType& s, std::size_t& idx) noexcept
 {
-    // as basic_json: the empty token and "-" (past the last element) are
+    return detail::parse_array_index(s, idx);
-    // unresolved rather than not a number
-    if (s.empty() || (s.size() == 1 && s[0] == '-'))
-    {
-        return index_status::unresolved;
-    }
-    if (s[0] < '0' || s[0] > '9')
-    {
-        return index_status::not_number;
-    }
-    if (s.size() > 1 && s[0] == '0')
-    {
-        return index_status::leading_zero;
-    }
-    std::uint64_t v = 0;
-    for (const auto c : s)
-    {
-        const auto d = static_cast<unsigned>(static_cast<unsigned char>(c)) - '0';
-        if (d > 9 || v > ((std::numeric_limits<std::uint64_t>::max)() - d) / 10)
-        {
-            return index_status::unresolved; // not a number, or beyond unsigned long long
-        }
-        v = (v * 10) + d;
-    }
-    if (v >= (std::numeric_limits<std::size_t>::max)()) // (std::size_t converts to std::uint64_t implicitly)
-    {
-        return index_status::too_large;
-    }
-    idx = static_cast<std::size_t>(v);
-    return index_status::ok;
 }
 
 /// throws the exception json_pointer::array_index throws for this status
@@ -86,15 +50,15 @@ template<typename StringType>
     switch (status)
     {
         case index_status::leading_zero:
-            throw_parse_error(106, concat("array index '", s, "' must not begin with '0'"));
+            throw_parse_error(exception_id::pointer_index_leading_zero, concat("array index '", s, "' must not begin with '0'"));
-        case index_status::not_number:
+        case index_status::not_a_number:
-            throw_parse_error(109, concat("array index '", s, "' is not a number"));
+            throw_parse_error(exception_id::pointer_index_not_a_number, concat("array index '", s, "' is not a number"));
-        case index_status::too_large:
+        case index_status::exceeds_size_type:
-            throw_out_of_range(410, concat("array index ", s, " exceeds size_type")); // LCOV_EXCL_LINE
+            throw_out_of_range(exception_id::value_out_of_range, concat("array index ", s, " exceeds size_type")); // LCOV_EXCL_LINE
         case index_status::unresolved:
         case index_status::ok:
         default:
-            throw_out_of_range(404, concat("unresolved reference token '", s, "'"));
+            throw_out_of_range(exception_id::pointer_unresolved, concat("unresolved reference token '", s, "'"));
     }
 }
 
@@ -119,7 +83,7 @@ View resolve_pointer(View cur, const Tokens& tokens, pointer_mode mode)
             {
                 if (mode == pointer_mode::checked)
                 {
-                    throw_out_of_range(403, concat("key '", token, "' not found"));
+                    throw_key_not_found(token);
                 }
                 return View();
             }
@@ -131,7 +95,7 @@ View resolve_pointer(View cur, const Tokens& tokens, pointer_mode mode)
             {
                 if (throwing)
                 {
-                    throw_out_of_range(402, concat("array index '-' (", std::to_string(cur.size()), ") is out of range"));
+                    throw_array_index_past_end(cur.size());
                 }
                 return View();
             }
@@ -139,7 +103,7 @@ View resolve_pointer(View cur, const Tokens& tokens, pointer_mode mode)
             const index_status status = array_index(token, idx);
             if (status != index_status::ok)
             {
-                const bool parse_error = status == index_status::leading_zero || status == index_status::not_number;
+                const bool parse_error = status == index_status::leading_zero || status == index_status::not_a_number;
                 if (throwing || (mode == pointer_mode::value && parse_error))
                 {
                     throw_array_index_error(status, token);
@@ -150,7 +114,7 @@ View resolve_pointer(View cur, const Tokens& tokens, pointer_mode mode)
             {
                 if (mode == pointer_mode::checked)
                 {
-                    throw_out_of_range(401, concat("array index ", std::to_string(idx), " is out of range"));
+                    throw_array_index_out_of_range(idx);
                 }
                 return View();
             }
@@ -160,7 +124,7 @@ View resolve_pointer(View cur, const Tokens& tokens, pointer_mode mode)
         {
             if (throwing)
             {
-                throw_out_of_range(404, concat("unresolved reference token '", token, "'"));
+                throw_out_of_range(exception_id::pointer_unresolved, concat("unresolved reference token '", token, "'"));
             }
             return View();
         }

include/nlohmann/detail/view/serializer.hpp

@@ -105,17 +105,13 @@ class output_buffer
     }
 
   private:
-    /// the size of a growth step (a function: std::min() takes a reference,
+    /// the size of a growth step
-    /// which a static constexpr member does not have before C++17)
+    static constexpr std::size_t step = 0x10000;
-    static constexpr std::size_t step() noexcept
-    {
-        return 0x10000;
-    }
 
     static StringType& sized(StringType& out, std::size_t estimate)
     {
         out.reserve(estimate);
-        out.resize((std::min)((std::max)(estimate, static_cast<std::size_t>(64)), step()));
+        out.resize(detail::clamp(estimate, std::size_t{64}, step));
         return out;
     }
 
@@ -123,8 +119,9 @@ class output_buffer
     {
         const auto used = static_cast<std::size_t>(m_pos - m_out.data());
         // (a step does not go beyond the reserved estimate, so that a good
-        // estimate is never copied to a larger allocation)
+        // estimate is never copied to a larger allocation; not a clamp: the
-        const std::size_t size = (std::max)((std::min)(m_out.size() + step(), m_out.capacity()), used + n + 256);
+        // lower bound used + n + 256 can exceed capacity(), and then it must win)
+        const std::size_t size = (std::max)((std::min)(m_out.size() + step, m_out.capacity()), used + n + 256);
         if (size > m_out.capacity())
         {
             m_out.reserve((std::max)(m_out.capacity() * 2, size));
@@ -171,6 +168,34 @@ inline std::size_t plain_output_run(const unsigned char* s, std::size_t n) noexc
     return n;
 }
 
+/// Whether dump() with ensure_ascii writes the string at s unchanged, for a
+/// string of the source without escape sequences (which has no quote,
+/// backslash, or control character): no byte is DEL (0x7F) or above. Adding 1
+/// to each byte sets its high bit exactly for 0x7F, and a carry into the next
+/// byte only comes from 0xFF, whose own high bit is set anyway.
+inline bool is_ascii_without_delete(const char* s, std::size_t n) noexcept
+{
+    constexpr std::uint64_t ones = 0x0101010101010101ull;
+    constexpr std::uint64_t high = 0x8080808080808080ull;
+    std::size_t i = 0;
+    for (; i + 8 <= n; i += 8)
+    {
+        const std::uint64_t v = read_eight_bytes(s + i);
+        if (((v | (v + ones)) & high) != 0)
+        {
+            return false;
+        }
+    }
+    for (; i < n; ++i)
+    {
+        if (static_cast<unsigned char>(s[i]) >= 0x7F)
+        {
+            return false;
+        }
+    }
+    return true;
+}
+
 /// A stack that starts in a buffer of the caller (a local array) and moves to
 /// the heap (a vector of the caller) only when that is full, so that dumps of
 /// shallow documents need no allocation. The top is a pointer, as in
@@ -286,15 +311,19 @@ class view_serializer
 
     void dump(const node* root)
     {
-        if (!m_style.pretty && !m_style.ensure_ascii)
+        if (!m_style.pretty)
         {
-            if (m_style.source_numbers)
+            if (m_style.ensure_ascii)
             {
-                dump_compact<true>(root);
+                dump_compact_ascii(root);
+            }
+            else if (m_style.source_numbers)
+            {
+                dump_compact<true, false>(root);
             }
             else
             {
-                dump_compact<false>(root);
+                dump_compact<false, false>(root);
             }
             return;
         }
@@ -400,6 +429,41 @@ class view_serializer
         m_out.put('"');
     }
 
+    /// dump_compact() with ensure_ascii, out of line: the walk without it is
+    /// faster when it is not merged with this one into dump()
+    NLOHMANN_VIEW_NOINLINE void dump_compact_ascii(const node* root)
+    {
+        if (m_style.source_numbers)
+        {
+            dump_compact<true, true>(root);
+        }
+        else
+        {
+            dump_compact<false, true>(root);
+        }
+    }
+
+    /// whether dump_compact() copies a string or key from the source: one of
+    /// the source, and with ensure_ascii one without bytes >= 0x7F (an overload
+    /// each, so that the walk without ensure_ascii is compiled exactly as
+    /// before: with GCC, a condition that only folds away later changed its
+    /// block layout and made it 4-6% slower)
+    static bool copied(const node& n, const char* /*src*/, std::false_type /*ensure_ascii*/) noexcept
+    {
+        return (n.flags & node_flags::storage) == 0;
+    }
+
+    static bool copied(const node& n, const char* src, std::true_type /*ensure_ascii*/) noexcept
+    {
+        return (n.flags & node_flags::storage) == 0 && is_ascii_without_delete(src + n.off, n.len);
+    }
+
+    /// a string with ensure_ascii (dump_compact()), out of line
+    NLOHMANN_VIEW_NOINLINE void write_ascii_string(const node& n)
+    {
+        write_string(n);
+    }
+
     /// the copies of dump_compact() that are not fixed-size moves (long
     /// strings, or near the end of the source); out of line, so that the
     /// compiler does not merge the fixed-size moves into this call
@@ -417,16 +481,18 @@ class view_serializer
     }
 
     /*!
-    @brief the compact output without ensure_ascii (the default dump())
+    @brief the compact output (the default dump(), or with ensure_ascii)
 
     The same walk as dump(), with the write position in a local variable
     (stores through char pointers would otherwise force a reload of the
     buffer's members after each one), and with strings and number tokens of
     the source copied by fixed-size moves of 32 bytes where the source has
     that many bytes left, instead of a library call per token. The buffer
-    keeps 64 bytes of slack for the overshoot.
+    keeps 64 bytes of slack for the overshoot. With ensure_ascii (Ascii), a
+    string of the source is copied only if it has no byte >= 0x7F (see
+    is_ascii_without_delete()); any other string is written by write_string().
     */
-    template<bool SourceNumbers>
+    template<bool SourceNumbers, bool Ascii>
     void dump_compact(const node* root)
     {
         struct frame
@@ -478,7 +544,14 @@ class view_serializer
         const auto escaped = [&](const node & n)
         {
             m_out.set_cursor(w);
-            write_decoded(n);
+            if (enabled(Ascii))
+            {
+                write_ascii_string(n);
+            }
+            else
+            {
+                write_decoded(n);
+            }
             w = m_out.cursor();
             lim = m_out.limit();
         };
@@ -501,7 +574,7 @@ class view_serializer
             switch (static_cast<value_t>(n->kind))
             {
                 case value_t::string:
-                    if ((n->flags & node_flags::storage) == 0)
+                    if (copied(*n, src, std::integral_constant<bool, Ascii>()))
                     {
                         room(n->len + 2);
                         *w++ = '"';
@@ -632,7 +705,7 @@ class view_serializer
             if (cur.object)
             {
                 const node& key = *at;
-                if ((key.flags & node_flags::storage) == 0)
+                if (copied(key, src, std::integral_constant<bool, Ascii>()))
                 {
                     room(key.len + 3);
                     *w++ = '"';
@@ -794,8 +867,7 @@ class view_serializer
     static char* write_double_value_at(char* w, double x)
     {
         // (from the bits: without the checks of to_chars())
-        std::uint64_t bits = 0;
+        auto bits = bit_cast<std::uint64_t>(x);
-        std::memcpy(&bits, &x, sizeof(bits));
         if (NLOHMANN_VIEW_UNLIKELY((bits & 0x7FF0000000000000u) == 0x7FF0000000000000u))
         {
             return write_text_at(w, "null", 4);
@@ -818,21 +890,17 @@ class view_serializer
             m_out.put("null");
             return;
         }
-        static constexpr bool is_ieee_single_or_double
+        write_float(x, std::integral_constant<bool, ::nlohmann::detail::has_native_float_format<number_float_t>::value>());
-            = std::numeric_limits<number_float_t>::is_iec559
-              && ((std::numeric_limits<number_float_t>::digits == 24 && std::numeric_limits<number_float_t>::max_exponent == 128)
-                  || (std::numeric_limits<number_float_t>::digits == 53 && std::numeric_limits<number_float_t>::max_exponent == 1024));
-        write_float(x, std::integral_constant<bool, is_ieee_single_or_double>());
     }
 
-    void write_float(number_float_t x, std::true_type /*is_ieee_single_or_double*/)
+    void write_float(number_float_t x, std::true_type /*has_native_float_format*/)
     {
         std::array<char, 64> buf{};
         const char* const end = ::nlohmann::detail::to_chars(buf.data(), buf.data() + buf.size(), x);
         m_out.put(buf.data(), static_cast<std::size_t>(end - buf.data()));
     }
 
-    void write_float(number_float_t x, std::false_type /*is_ieee_single_or_double*/)
+    void write_float(number_float_t x, std::false_type /*has_native_float_format*/)
     {
         // other types (e.g. long double) are rare: the library writes them
         const string_t s = BasicJsonType(x).dump();
@@ -843,9 +911,10 @@ class view_serializer
     {
         const char* const s = m_doc.str(n);
         m_out.put('"');
-        if ((n.flags & node_flags::storage) == 0 && !m_style.ensure_ascii)
+        if ((n.flags & node_flags::storage) == 0 && (!m_style.ensure_ascii || is_ascii_without_delete(s, n.len)))
         {
-            // a string of the source without escape sequences has nothing to escape
+            // a string of the source without escape sequences has nothing to
+            // escape (with ensure_ascii, if it is printable ASCII)
             m_out.put(s, n.len);
         }
         else if (m_style.ensure_ascii)
@@ -958,8 +1027,8 @@ class view_serializer
 
     void write_u_escape(std::uint32_t u)
     {
-        static constexpr const char* hex = "0123456789abcdef";
+        std::array<char, 6> e = {{'\\', 'u', 0, 0, 0, 0}};
-        const std::array<char, 6> e = {{'\\', 'u', hex[(u >> 12u) & 0xFu], hex[(u >> 8u) & 0xFu], hex[(u >> 4u) & 0xFu], hex[u & 0xFu]}};
+        hex4_lower(static_cast<std::uint16_t>(u), &e[2]);
         m_out.put(e.data(), e.size());
     }
 

include/nlohmann/detail/view/simd.hpp

@@ -50,7 +50,12 @@
 #endif
 #if NLOHMANN_VIEW_SSE2 && !NLOHMANN_VIEW_SSSE3 && !defined(NLOHMANN_VIEW_NO_TARGET_ATTRIBUTE) && ((defined(__clang__) && __clang_major__ >= 4) || (defined(__GNUC__) && !defined(__clang__) && (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 9))))
     // (GCC before 4.9 has no SSSE3 intrinsics without -mssse3)
-    #include <cpuid.h>
+    // <cpuid.h> of GCC before 11 has no include guard, and json.hpp and
+    // json_view.hpp both include it
+    #ifndef NLOHMANN_JSON_CPUID_INCLUDED
+        #define NLOHMANN_JSON_CPUID_INCLUDED
+        #include <cpuid.h>
+    #endif
     #include <tmmintrin.h>
     #define NLOHMANN_VIEW_SSSE3_DISPATCH 1 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
     #define NLOHMANN_VIEW_SSSE3_TARGET __attribute__((target("ssse3")))

include/nlohmann/detail/view/value.hpp

@@ -60,7 +60,7 @@ NLOHMANN_VIEW_ALWAYS_INLINE T arithmetic_value(const document_data& d, const nod
         case value_t::binary:
         case value_t::discarded:
         default:
-            throw_type_error(302, "type must be number, but is ", value_type_name(static_cast<value_t>(n.kind)));
+            throw_type_error(exception_id::type_mismatch, "type must be number, but is ", value_type_name(static_cast<value_t>(n.kind)));
     }
 }
 
@@ -70,7 +70,7 @@ std::vector<U, A> vector_value(const View& v)
 {
     if (NLOHMANN_VIEW_UNLIKELY(!v.is_array()))
     {
-        throw_type_error(302, "type must be array, but is ", v.type_name());
+        throw_type_error(exception_id::type_mismatch, "type must be array, but is ", v.type_name());
     }
     std::vector<U, A> r;
     r.reserve(v.size());
@@ -88,7 +88,7 @@ Map map_value(const View& v)
 {
     if (NLOHMANN_VIEW_UNLIKELY(!v.is_object()))
     {
-        throw_type_error(302, "type must be object, but is ", v.type_name());
+        throw_type_error(exception_id::type_mismatch, "type must be object, but is ", v.type_name());
     }
     Map r;
     for (auto it = v.begin(); it != v.end(); ++it)

include/nlohmann/json_view.hpp

@@ -267,7 +267,7 @@ class basic_json_view
             {
                 return {};
             }
-            detail::view::throw_type_error(305, "cannot use operator[] with a string argument with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::subscript_wrong_type, "cannot use operator[] with a string argument with ", type_name());
         }
         return lookup(key);
     }
@@ -293,7 +293,7 @@ class basic_json_view
             {
                 return {};
             }
-            detail::view::throw_type_error(305, "cannot use operator[] with a numeric argument with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::subscript_wrong_type, "cannot use operator[] with a numeric argument with ", type_name());
         }
         return idx < m_node->len ? basic_json_view(m_doc, navigation::value(detail::view::element_at<Editable>(*m_doc, m_node, idx))) : basic_json_view();
     }
@@ -326,12 +326,12 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_object()))
         {
-            detail::view::throw_type_error(304, "cannot use at() with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::at_wrong_type, "cannot use at() with ", type_name());
         }
         const basic_json_view r = lookup(key);
         if (NLOHMANN_VIEW_UNLIKELY(r.is_discarded()))
         {
-            detail::view::throw_out_of_range(403, detail::concat("key '", std::string(key.data(), key.size()), "' not found"));
+            detail::view::throw_key_not_found(std::string(key.data(), key.size()));
         }
         return r;
     }
@@ -352,11 +352,11 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_array()))
         {
-            detail::view::throw_type_error(304, "cannot use at() with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::at_wrong_type, "cannot use at() with ", type_name());
         }
         if (NLOHMANN_VIEW_UNLIKELY(idx >= m_node->len))
         {
-            detail::view::throw_out_of_range(401, detail::concat("array index ", std::to_string(idx), " is out of range"));
+            detail::view::throw_array_index_out_of_range(idx);
         }
         return basic_json_view(m_doc, navigation::value(detail::view::element_at<Editable>(*m_doc, m_node, idx)));
     }
@@ -384,7 +384,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_object()))
         {
-            detail::view::throw_type_error(306, "cannot use value() with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::value_wrong_type, "cannot use value() with ", type_name());
         }
         const basic_json_view r = lookup(key);
         return r.is_discarded() ? default_value : r.template get<T>();
@@ -403,7 +403,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_structured()))
         {
-            detail::view::throw_type_error(306, "cannot use value() with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::value_wrong_type, "cannot use value() with ", type_name());
         }
         const basic_json_view r = detail::view::resolve_pointer(*this, detail::json_pointer_access::reference_tokens(ptr), detail::view::pointer_mode::value);
         return r.is_discarded() ? default_value : r.template get<T>();
@@ -421,7 +421,7 @@ class basic_json_view
         const iterator it = begin();
         if (NLOHMANN_VIEW_UNLIKELY(it == end()))
         {
-            detail::view::throw_invalid_iterator(214, "cannot get value");
+            detail::view::throw_invalid_iterator(detail::exception_id::iterator_value_unavailable, "cannot get value");
         }
         return *it;
     }
@@ -573,7 +573,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_string()))
         {
-            detail::view::throw_type_error(302, "type must be string, but is ", type_name());
+            detail::view::throw_type_error(detail::exception_id::type_mismatch, "type must be string, but is ", type_name());
         }
         return {m_doc->str(*m_node), m_node->len};
     }
@@ -585,7 +585,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_number()))
         {
-            detail::view::throw_type_error(302, "type must be number, but is ", type_name());
+            detail::view::throw_type_error(detail::exception_id::type_mismatch, "type must be number, but is ", type_name());
         }
         return {m_doc->str(*m_node), detail::view::number_length(*m_node)};
     }
@@ -795,7 +795,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_boolean()))
         {
-            detail::view::throw_type_error(302, "type must be boolean, but is ", type_name());
+            detail::view::throw_type_error(detail::exception_id::type_mismatch, "type must be boolean, but is ", type_name());
         }
         return (m_node->flags & detail::view::node_flags::is_true) != 0;
     }
@@ -805,7 +805,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(m_node == nullptr))
         {
-            detail::view::throw_type_error(302, "type must be number, but is ", type_name());
+            detail::view::throw_type_error(detail::exception_id::type_mismatch, "type must be number, but is ", type_name());
         }
         return detail::view::arithmetic_value<T, BasicJsonType>(*m_doc, *m_node);
     }
@@ -814,7 +814,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_null()))
         {
-            detail::view::throw_type_error(302, "type must be null, but is ", type_name());
+            detail::view::throw_type_error(detail::exception_id::type_mismatch, "type must be null, but is ", type_name());
         }
         return nullptr;
     }
@@ -1123,7 +1123,7 @@ class basic_json_document
     {
         if (NLOHMANN_VIEW_UNLIKELY(!m_data || m_data->discarded))
         {
-            detail::view::throw_type_error(320, "cannot save a discarded json_document");
+            detail::view::throw_type_error(detail::exception_id::document_image_unsupported, "cannot save a discarded json_document");
         }
         return detail::view::save_image(*m_data);
     }
@@ -1224,7 +1224,7 @@ class basic_json_document
                 const std::size_t idx = pointer_index(token);
                 if (idx >= 0xFFFFFFFFu)
                 {
-                    detail::view::throw_out_of_range(401, detail::concat("array index ", std::to_string(idx), " is out of range"));
+                    detail::view::throw_array_index_out_of_range(idx);
                 }
                 for (std::size_t i = 0; i < idx; ++i)
                 {
@@ -1280,7 +1280,7 @@ class basic_json_document
     {
         if (ptr.empty())
         {
-            detail::view::throw_out_of_range(405, "JSON pointer has no parent");
+            detail::view::throw_out_of_range(detail::exception_id::patch_on_root, "JSON pointer has no parent");
         }
         const view_type parent = root().at(ptr.parent_pointer());
         const auto& token = ptr.back();
@@ -1300,7 +1300,7 @@ class basic_json_document
         static_assert(Editable, "only an editable document can be edited: use basic_json_document<BasicJsonType, true> (json_editable_document)");
         if (NLOHMANN_VIEW_UNLIKELY(!m_data || m_data->discarded))
         {
-            detail::view::throw_invalid_iterator(202, "view does not belong to this document");
+            detail::view::throw_invalid_iterator(detail::exception_id::iterator_from_other_value, "view does not belong to this document");
         }
         return detail::view::editor<BasicJsonType, view_type>(*m_data);
     }
@@ -1317,7 +1317,7 @@ class basic_json_document
     {
         if (idx < 0)
         {
-            detail::view::throw_out_of_range(401, detail::concat("array index ", std::to_string(idx), " is out of range"));
+            detail::view::throw_array_index_out_of_range(idx);
         }
         return static_cast<std::size_t>(idx);
     }

include/nlohmann/ordered_map.hpp

@@ -125,6 +125,19 @@ private:
         Container::pop_back();
     }
 
+    /// @brief remove the entry with the given key; returns the number of removed entries
+    template<class K>
+    size_type erase_impl(const K& key)
+    {
+        const auto it = find_impl(*this, key);
+        if (it != this->end())
+        {
+            erase_at(it);
+            return 1;
+        }
+        return 0;
+    }
+
 public:
     template<class V, detail::enable_if_t<
                  detail::is_constructible<T, V>::value, int> = 0>
@@ -214,26 +227,14 @@ public:
 
     size_type erase(const key_type& key)
     {
-        const auto it = find_impl(*this, key);
+        return erase_impl(key);
-        if (it != this->end())
-        {
-            erase_at(it);
-            return 1;
-        }
-        return 0;
     }
 
     template<class KeyType, detail::enable_if_t<
                  detail::is_usable_as_key_type<key_compare, key_type, KeyType>::value, int> = 0>
     size_type erase(KeyType && key) // NOLINT(cppcoreguidelines-missing-std-forward)
     {
-        const auto it = find_impl(*this, key);
+        return erase_impl(key);
-        if (it != this->end())
-        {
-            erase_at(it);
-            return 1;
-        }
-        return 0;
     }
 
     iterator erase(iterator pos)

single_include/nlohmann/json_fwd.hpp

@@ -139,6 +139,12 @@
     #define NLOHMANN_JSON_ABI_TAG_DISABLE_UNLOCKED_FILE_IO
 #endif
 
+#ifdef JSON_NO_SIMD
+    #define NLOHMANN_JSON_ABI_TAG_NO_SIMD _ns
+#else
+    #define NLOHMANN_JSON_ABI_TAG_NO_SIMD
+#endif
+
 #ifdef JSON_VIEW_NO_SIMD
     #define NLOHMANN_JSON_ABI_TAG_VIEW_NO_SIMD _vns
 #else
@@ -156,9 +162,9 @@
 #endif
 
 // Construct the namespace ABI tags component
-#define NLOHMANN_JSON_ABI_TAGS_CONCAT_EX(a, b, c, d, e, f, g, h, i, j, k, l) json_abi ## a ## b ## c ## d ## e ## f ## g ## h ## i ## j ## k ## l
+#define NLOHMANN_JSON_ABI_TAGS_CONCAT_EX(a, b, c, d, e, f, g, h, i, j, k, l, m) json_abi ## a ## b ## c ## d ## e ## f ## g ## h ## i ## j ## k ## l ## m
-#define NLOHMANN_JSON_ABI_TAGS_CONCAT(a, b, c, d, e, f, g, h, i, j, k, l) \
+#define NLOHMANN_JSON_ABI_TAGS_CONCAT(a, b, c, d, e, f, g, h, i, j, k, l, m) \
-    NLOHMANN_JSON_ABI_TAGS_CONCAT_EX(a, b, c, d, e, f, g, h, i, j, k, l)
+    NLOHMANN_JSON_ABI_TAGS_CONCAT_EX(a, b, c, d, e, f, g, h, i, j, k, l, m)
 
 #define NLOHMANN_JSON_ABI_TAGS                                       \
     NLOHMANN_JSON_ABI_TAGS_CONCAT(                                   \
@@ -172,6 +178,7 @@
             NLOHMANN_JSON_ABI_TAG_OBJECTS_FOR_ENUM_KEYED_MAPS,       \
             NLOHMANN_JSON_ABI_TAG_DISABLE_STREAM_BULK_SCAN,          \
             NLOHMANN_JSON_ABI_TAG_DISABLE_UNLOCKED_FILE_IO,          \
+            NLOHMANN_JSON_ABI_TAG_NO_SIMD,                           \
             NLOHMANN_JSON_ABI_TAG_VIEW_NO_SIMD,                      \
             NLOHMANN_JSON_ABI_TAG_VIEW_USE_SSSE3)
 

single_include/nlohmann/json_view.hpp

@@ -690,7 +690,12 @@ NLOHMANN_JSON_NAMESPACE_END
 #endif
 #if NLOHMANN_VIEW_SSE2 && !NLOHMANN_VIEW_SSSE3 && !defined(NLOHMANN_VIEW_NO_TARGET_ATTRIBUTE) && ((defined(__clang__) && __clang_major__ >= 4) || (defined(__GNUC__) && !defined(__clang__) && (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 9))))
     // (GCC before 4.9 has no SSSE3 intrinsics without -mssse3)
-    #include <cpuid.h>
+    // <cpuid.h> of GCC before 11 has no include guard, and json.hpp and
+    // json_view.hpp both include it
+    #ifndef NLOHMANN_JSON_CPUID_INCLUDED
+        #define NLOHMANN_JSON_CPUID_INCLUDED
+        #include <cpuid.h>
+    #endif
     #include <tmmintrin.h>
     #define NLOHMANN_VIEW_SSSE3_DISPATCH 1 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
     #define NLOHMANN_VIEW_SSSE3_TARGET __attribute__((target("ssse3")))
@@ -2669,32 +2674,52 @@ namespace view
 // Exceptions are thrown out of line, so that the accessors that may throw stay
 // small enough to be inlined.
 
-[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_type_error(int id, const char* prefix, const char* type)
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_type_error(exception_id id, const char* prefix, const char* type)
 {
     NLOHMANN_VIEW_THROW(type_error::create(id, concat(prefix, type), nullptr));
 }
 
-[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_type_error(int id, const std::string& msg)
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_type_error(exception_id id, const std::string& msg)
 {
     NLOHMANN_VIEW_THROW(type_error::create(id, msg, nullptr));
 }
 
-[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_out_of_range(int id, const std::string& msg)
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_out_of_range(exception_id id, const std::string& msg)
 {
     NLOHMANN_VIEW_THROW(out_of_range::create(id, msg, nullptr));
 }
 
-[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_invalid_iterator(int id, const char* msg)
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_invalid_iterator(exception_id id, const char* msg)
 {
     NLOHMANN_VIEW_THROW(invalid_iterator::create(id, msg, nullptr));
 }
 
 /// a parse error without a position (as those of json_pointer)
-[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_parse_error(int id, const std::string& msg)
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_parse_error(exception_id id, const std::string& msg)
 {
     NLOHMANN_VIEW_THROW(parse_error::create(id, 0, msg, nullptr));
 }
 
+/// out_of_range.401: the array index @a idx is not below the size
+template<typename Index>
+[[noreturn]] NLOHMANN_VIEW_NOINLINE void throw_array_index_out_of_range(const Index idx)
+{
+    throw_out_of_range(exception_id::array_index_out_of_range, concat("array index ", std::to_string(idx), " is out of range"));
+}
+
+/// out_of_range.402: the JSON Pointer token '-' of an array of @a size elements
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_array_index_past_end(std::size_t size)
+{
+    throw_out_of_range(exception_id::pointer_past_the_end_index, concat("array index '-' (", std::to_string(size), ") is out of range"));
+}
+
+/// out_of_range.403: the object has no member @a key
+template<typename Key>
+[[noreturn]] NLOHMANN_VIEW_NOINLINE void throw_key_not_found(const Key& key)
+{
+    throw_out_of_range(exception_id::key_not_found, concat("key '", key, "' not found"));
+}
+
 /// SAX handler of the error replay: accepts every event without storing it,
 /// and throws the exception the parser reports
 template<typename BasicJsonType>
@@ -2793,7 +2818,7 @@ template<typename BasicJsonType>
     if (f.code == error_code::input_too_large)
     {
         // (the limit is detail::view::max_input_size(): 4 GiB minus 16 bytes)
-        NLOHMANN_VIEW_THROW(out_of_range::create(416, "input of 4294967280 bytes or more is not supported by json_document", nullptr));
+        NLOHMANN_VIEW_THROW(out_of_range::create(exception_id::document_too_large, "input of 4294967280 bytes or more is not supported by json_document", nullptr));
     }
     throwing_sax<BasicJsonType> sax;
     const bool accepted = BasicJsonType::sax_parse(src, src + size, &sax, input_format_t::json, true, ignore_comments, ignore_trailing_commas);
@@ -2813,7 +2838,7 @@ template<typename BasicJsonType>
         }
     }
     pos.chars_read_current_line = off + 1 - line_start;
-    NLOHMANN_VIEW_THROW(parse_error::create(101, pos, "syntax error while parsing value", nullptr));
+    NLOHMANN_VIEW_THROW(parse_error::create(exception_id::syntax_error, pos, "syntax error while parsing value", nullptr));
     // LCOV_EXCL_STOP
 }
 
@@ -2888,7 +2913,7 @@ inline std::size_t text_capacity(std::size_t cap, std::size_t used, std::size_t
     constexpr std::size_t limit = 0xFFFFFFFFu;
     if (NLOHMANN_VIEW_UNLIKELY(used > limit || n > limit - used))
     {
-        throw_out_of_range(416, "edits of 4 GiB or more are not supported by json_document");
+        throw_out_of_range(exception_id::document_too_large, "edits of 4 GiB or more are not supported by json_document");
     }
     const std::size_t needed = used + n;
     const std::size_t wanted = needed + (std::min)(limit - needed, std::size_t{256});
@@ -2939,7 +2964,7 @@ inline void reserve_moved(document_data& d)
     document_data::edit_state& e = edit_state_of(d);
     if (e.moved.size() >= 0xFFFFFFFFu)
     {
-        throw_out_of_range(416, "more than 4294967295 edited arrays and objects are not supported by json_document"); // LCOV_EXCL_LINE
+        throw_out_of_range(exception_id::document_too_large, "more than 4294967295 edited arrays and objects are not supported by json_document"); // LCOV_EXCL_LINE
     }
     if (e.moved.size() == e.moved.capacity() || e.moved_cap.size() == e.moved_cap.capacity())
     {
@@ -3471,11 +3496,6 @@ struct first_true<false, Conditions...> : std::integral_constant < int, 1 + firs
 inline void check_utf8(const char* s, std::size_t n)
 {
     const auto* const p = reinterpret_cast<const unsigned char*>(s); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-    const auto hex = [](unsigned char c)
-    {
-        constexpr const char* digits = "0123456789ABCDEF";
-        return std::string{digits[c >> 4u], digits[c & 0xFu]};
-    };
     for (std::size_t i = 0; i < n;)
     {
         const unsigned char c = p[i];
@@ -3484,39 +3504,22 @@ inline void check_utf8(const char* s, std::size_t n)
             ++i;
             continue;
         }
-        std::size_t len = 0;
+        const utf8_sequence_shape shape = utf8_shape(c);
-        unsigned char lo = 0x80;
+        const std::size_t len = shape.length;
-        unsigned char hi = 0xBF;
+        if (len == 0)
-        if (c >= 0xC2 && c <= 0xDF)
         {
-            len = 2;
+            throw_type_error(exception_id::invalid_utf8, concat("invalid UTF-8 byte at index ", std::to_string(i), ": 0x", hex_byte(c)));
-        }
-        else if (c >= 0xE0 && c <= 0xEF)
-        {
-            len = 3;
-            lo = c == 0xE0 ? 0xA0 : 0x80;
-            hi = c == 0xED ? 0x9F : 0xBF;
-        }
-        else if (c >= 0xF0 && c <= 0xF4)
-        {
-            len = 4;
-            lo = c == 0xF0 ? 0x90 : 0x80;
-            hi = c == 0xF4 ? 0x8F : 0xBF;
-        }
-        else
-        {
-            throw_type_error(316, concat("invalid UTF-8 byte at index ", std::to_string(i), ": 0x", hex(c)));
         }
         for (std::size_t k = 1; k < len; ++k)
         {
             if (i + k == n)
             {
-                throw_type_error(316, concat("incomplete UTF-8 string; last byte: 0x", hex(p[n - 1])));
+                throw_type_error(exception_id::invalid_utf8, concat("incomplete UTF-8 string; last byte: 0x", hex_byte(p[n - 1])));
             }
             const unsigned char b = p[i + k];
-            if (b < (k == 1 ? lo : 0x80) || b > (k == 1 ? hi : 0xBF))
+            if (b < (k == 1 ? shape.second_lo : 0x80) || b > (k == 1 ? shape.second_hi : 0xBF))
             {
-                throw_type_error(316, concat("invalid UTF-8 byte at index ", std::to_string(i + k), ": 0x", hex(b)));
+                throw_type_error(exception_id::invalid_utf8, concat("invalid UTF-8 byte at index ", std::to_string(i + k), ": 0x", hex_byte(b)));
             }
         }
         i += len;
@@ -3564,7 +3567,7 @@ class editor
         node* const o = own(object);
         if (o->kind != static_cast<std::uint8_t>(value_t::object) && o->kind != static_cast<std::uint8_t>(value_t::null))
         {
-            throw_type_error(305, "cannot use operator[] with a string argument with ", object.type_name());
+            throw_type_error(exception_id::subscript_wrong_type, "cannot use operator[] with a string argument with ", object.type_name());
         }
         check_utf8(key.data(), key.size());
         const encoded e = encode(std::forward<V>(value));
@@ -3615,7 +3618,7 @@ class editor
         node* const a = own(array);
         if (a->kind != static_cast<std::uint8_t>(value_t::array))
         {
-            throw_type_error(305, "cannot use operator[] with a numeric argument with ", array.type_name());
+            throw_type_error(exception_id::subscript_wrong_type, "cannot use operator[] with a numeric argument with ", array.type_name());
         }
         check_index(idx, a->len);
         const encoded e = encode(std::forward<V>(value));
@@ -3632,7 +3635,7 @@ class editor
         node* const a = own(array);
         if (a->kind != static_cast<std::uint8_t>(value_t::array) && a->kind != static_cast<std::uint8_t>(value_t::null))
         {
-            throw_type_error(308, "cannot use push_back() with ", array.type_name());
+            throw_type_error(exception_id::push_back_wrong_type, "cannot use push_back() with ", array.type_name());
         }
         const encoded e = encode(std::forward<V>(value));
         if (a->kind == static_cast<std::uint8_t>(value_t::null))
@@ -3656,7 +3659,7 @@ class editor
         node* const a = own(array);
         if (a->kind != static_cast<std::uint8_t>(value_t::array))
         {
-            throw_type_error(309, "cannot use insert() with ", array.type_name());
+            throw_type_error(exception_id::insert_wrong_type, "cannot use insert() with ", array.type_name());
         }
         check_index(idx, a->len + 1);
         const encoded e = encode(std::forward<V>(value));
@@ -3676,7 +3679,7 @@ class editor
         node* const o = own(object);
         if (o->kind != static_cast<std::uint8_t>(value_t::object))
         {
-            throw_type_error(307, "cannot use erase() with ", object.type_name());
+            throw_type_error(exception_id::erase_wrong_type, "cannot use erase() with ", object.type_name());
         }
         for (const node* k = nav::first(m_doc, o), *end = nav::end(m_doc, o); k != end; k = document_data::after(k + 1))
         {
@@ -3694,7 +3697,7 @@ class editor
         node* const a = own(array);
         if (a->kind != static_cast<std::uint8_t>(value_t::array))
         {
-            throw_type_error(307, "cannot use erase() with ", array.type_name());
+            throw_type_error(exception_id::erase_wrong_type, "cannot use erase() with ", array.type_name());
         }
         check_index(idx, a->len);
         node* const h = block_of(m_doc, a, 0);
@@ -3717,7 +3720,7 @@ class editor
     {
         if (NLOHMANN_VIEW_UNLIKELY(v.m_doc != &m_doc || v.m_node == nullptr))
         {
-            throw_invalid_iterator(202, "view does not belong to this document");
+            throw_invalid_iterator(exception_id::iterator_from_other_value, "view does not belong to this document");
         }
         edit_state_of(m_doc);
         return const_cast<node*>(v.m_node); // NOLINT(cppcoreguidelines-pro-type-const-cast): the nodes belong to this document
@@ -3727,7 +3730,7 @@ class editor
     {
         if (idx >= limit)
         {
-            throw_out_of_range(401, concat("array index ", std::to_string(idx), " is out of range"));
+            throw_array_index_out_of_range(idx);
         }
     }
 
@@ -3868,7 +3871,7 @@ class editor
     {
         if (NLOHMANN_VIEW_UNLIKELY(v.m_node == nullptr))
         {
-            throw_type_error(302, "type must be a value, but is ", "discarded");
+            throw_type_error(exception_id::type_mismatch, "type must be a value, but is ", "discarded");
         }
         encoded r;
         if (!is_container(*v.m_node))
@@ -4018,7 +4021,7 @@ class editor
     {
         if (NLOHMANN_VIEW_UNLIKELY(len >= 0xFFFFFFFFu))
         {
-            throw_out_of_range(416, "strings of 4 GiB or more are not supported by json_document"); // LCOV_EXCL_LINE
+            throw_out_of_range(exception_id::document_too_large, "strings of 4 GiB or more are not supported by json_document"); // LCOV_EXCL_LINE
         }
         node n = plain_node(value_t::string);
         n.flags = static_cast<std::uint8_t>(n.flags | node_flags::edited);
@@ -4093,12 +4096,12 @@ class editor
                 return string_node(s.data(), s.size());
             }
             case value_t::binary:
-                throw_type_error(319, "cannot store a binary value in a json_document", "");
+                throw_type_error(exception_id::document_binary_value, "cannot store a binary value in a json_document", "");
             case value_t::discarded:
             case value_t::object:
             case value_t::array:
             default:
-                throw_type_error(302, "type must be a value, but is ", "discarded");
+                throw_type_error(exception_id::type_mismatch, "type must be a value, but is ", "discarded");
         }
     }
 
@@ -4726,7 +4729,7 @@ inline void compact_nodes(const document_data& d, std::size_t arena_size, std::v
 inline std::vector<std::uint8_t> save_image(const document_data& d)
 {
 #if !NLOHMANN_VIEW_LITTLE_ENDIAN
-    throw_type_error(320, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
+    throw_type_error(exception_id::document_image_unsupported, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
 #endif
     const std::size_t arena_size = d.arena_size;
     std::vector<node> compacted;
@@ -4743,7 +4746,7 @@ inline std::vector<std::uint8_t> save_image(const document_data& d)
     if (NLOHMANN_VIEW_UNLIKELY(text_size >= image_limit || total_arena >= image_limit || count >= image_limit))
     {
         // LCOV_EXCL_START (4 GiB)
-        throw_out_of_range(416, "images of 4 GiB or more are not supported by json_document");
+        throw_out_of_range(exception_id::document_too_large, "images of 4 GiB or more are not supported by json_document");
         // LCOV_EXCL_STOP
     }
     image_header h{};
@@ -5200,7 +5203,7 @@ inline bool check_image(const node* nodes, std::size_t count, const unsigned cha
 
 [[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_invalid_image(const char* what)
 {
-    throw_parse_error(116, concat("invalid json_document image: ", what));
+    throw_parse_error(exception_id::invalid_document_image, concat("invalid json_document image: ", what));
 }
 
 /// Read an image into d. The text and the decoded strings stay in the image;
@@ -5208,7 +5211,7 @@ inline bool check_image(const node* nodes, std::size_t count, const unsigned cha
 inline void load_image(document_data& d, const std::uint8_t* image, std::size_t size, image_check check)
 {
 #if !NLOHMANN_VIEW_LITTLE_ENDIAN
-    throw_type_error(320, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
+    throw_type_error(exception_id::document_image_unsupported, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
 #endif
     if (image == nullptr || size < sizeof(image_header))
     {
@@ -5562,7 +5565,7 @@ class view_iterator
     {
         if (NLOHMANN_VIEW_UNLIKELY(m_value_offset == 0))
         {
-            throw_invalid_iterator(207, "cannot use key() for non-object iterators");
+            throw_invalid_iterator(exception_id::iterator_key_not_object, "cannot use key() for non-object iterators");
         }
         return string_view_t(m_doc->str(*m_pos), m_pos->len);
     }
@@ -5914,51 +5917,15 @@ enum class pointer_mode
     contains,  ///< as basic_json::contains(): no exceptions at all
 };
 
-/// the outcome of reading an array index from a reference token
+/// the outcome of reading an array index: detail::parse_array_index(), shared with json_pointer
-enum class index_status
+using index_status = detail::array_index_status;
-{
-    ok,
-    leading_zero, ///< parse_error.106
-    not_number,   ///< parse_error.109
-    unresolved,   ///< out_of_range.404
-    too_large,    ///< out_of_range.410
-};
 
 /// reads an array index like json_pointer::array_index (RFC 6901, Sect. 4),
 /// but reports errors instead of throwing them
 template<typename StringType>
 index_status array_index(const StringType& s, std::size_t& idx) noexcept
 {
-    // as basic_json: the empty token and "-" (past the last element) are
+    return detail::parse_array_index(s, idx);
-    // unresolved rather than not a number
-    if (s.empty() || (s.size() == 1 && s[0] == '-'))
-    {
-        return index_status::unresolved;
-    }
-    if (s[0] < '0' || s[0] > '9')
-    {
-        return index_status::not_number;
-    }
-    if (s.size() > 1 && s[0] == '0')
-    {
-        return index_status::leading_zero;
-    }
-    std::uint64_t v = 0;
-    for (const auto c : s)
-    {
-        const auto d = static_cast<unsigned>(static_cast<unsigned char>(c)) - '0';
-        if (d > 9 || v > ((std::numeric_limits<std::uint64_t>::max)() - d) / 10)
-        {
-            return index_status::unresolved; // not a number, or beyond unsigned long long
-        }
-        v = (v * 10) + d;
-    }
-    if (v >= (std::numeric_limits<std::size_t>::max)()) // (std::size_t converts to std::uint64_t implicitly)
-    {
-        return index_status::too_large;
-    }
-    idx = static_cast<std::size_t>(v);
-    return index_status::ok;
 }
 
 /// throws the exception json_pointer::array_index throws for this status
@@ -5968,15 +5935,15 @@ template<typename StringType>
     switch (status)
     {
         case index_status::leading_zero:
-            throw_parse_error(106, concat("array index '", s, "' must not begin with '0'"));
+            throw_parse_error(exception_id::pointer_index_leading_zero, concat("array index '", s, "' must not begin with '0'"));
-        case index_status::not_number:
+        case index_status::not_a_number:
-            throw_parse_error(109, concat("array index '", s, "' is not a number"));
+            throw_parse_error(exception_id::pointer_index_not_a_number, concat("array index '", s, "' is not a number"));
-        case index_status::too_large:
+        case index_status::exceeds_size_type:
-            throw_out_of_range(410, concat("array index ", s, " exceeds size_type")); // LCOV_EXCL_LINE
+            throw_out_of_range(exception_id::value_out_of_range, concat("array index ", s, " exceeds size_type")); // LCOV_EXCL_LINE
         case index_status::unresolved:
         case index_status::ok:
         default:
-            throw_out_of_range(404, concat("unresolved reference token '", s, "'"));
+            throw_out_of_range(exception_id::pointer_unresolved, concat("unresolved reference token '", s, "'"));
     }
 }
 
@@ -6001,7 +5968,7 @@ View resolve_pointer(View cur, const Tokens& tokens, pointer_mode mode)
             {
                 if (mode == pointer_mode::checked)
                 {
-                    throw_out_of_range(403, concat("key '", token, "' not found"));
+                    throw_key_not_found(token);
                 }
                 return View();
             }
@@ -6013,7 +5980,7 @@ View resolve_pointer(View cur, const Tokens& tokens, pointer_mode mode)
             {
                 if (throwing)
                 {
-                    throw_out_of_range(402, concat("array index '-' (", std::to_string(cur.size()), ") is out of range"));
+                    throw_array_index_past_end(cur.size());
                 }
                 return View();
             }
@@ -6021,7 +5988,7 @@ View resolve_pointer(View cur, const Tokens& tokens, pointer_mode mode)
             const index_status status = array_index(token, idx);
             if (status != index_status::ok)
             {
-                const bool parse_error = status == index_status::leading_zero || status == index_status::not_number;
+                const bool parse_error = status == index_status::leading_zero || status == index_status::not_a_number;
                 if (throwing || (mode == pointer_mode::value && parse_error))
                 {
                     throw_array_index_error(status, token);
@@ -6032,7 +5999,7 @@ View resolve_pointer(View cur, const Tokens& tokens, pointer_mode mode)
             {
                 if (mode == pointer_mode::checked)
                 {
-                    throw_out_of_range(401, concat("array index ", std::to_string(idx), " is out of range"));
+                    throw_array_index_out_of_range(idx);
                 }
                 return View();
             }
@@ -6042,7 +6009,7 @@ View resolve_pointer(View cur, const Tokens& tokens, pointer_mode mode)
         {
             if (throwing)
             {
-                throw_out_of_range(404, concat("unresolved reference token '", token, "'"));
+                throw_out_of_range(exception_id::pointer_unresolved, concat("unresolved reference token '", token, "'"));
             }
             return View();
         }
@@ -6166,17 +6133,13 @@ class output_buffer
     }
 
   private:
-    /// the size of a growth step (a function: std::min() takes a reference,
+    /// the size of a growth step
-    /// which a static constexpr member does not have before C++17)
+    static constexpr std::size_t step = 0x10000;
-    static constexpr std::size_t step() noexcept
-    {
-        return 0x10000;
-    }
 
     static StringType& sized(StringType& out, std::size_t estimate)
     {
         out.reserve(estimate);
-        out.resize((std::min)((std::max)(estimate, static_cast<std::size_t>(64)), step()));
+        out.resize(detail::clamp(estimate, std::size_t{64}, step));
         return out;
     }
 
@@ -6184,8 +6147,9 @@ class output_buffer
     {
         const auto used = static_cast<std::size_t>(m_pos - m_out.data());
         // (a step does not go beyond the reserved estimate, so that a good
-        // estimate is never copied to a larger allocation)
+        // estimate is never copied to a larger allocation; not a clamp: the
-        const std::size_t size = (std::max)((std::min)(m_out.size() + step(), m_out.capacity()), used + n + 256);
+        // lower bound used + n + 256 can exceed capacity(), and then it must win)
+        const std::size_t size = (std::max)((std::min)(m_out.size() + step, m_out.capacity()), used + n + 256);
         if (size > m_out.capacity())
         {
             m_out.reserve((std::max)(m_out.capacity() * 2, size));
@@ -6232,6 +6196,34 @@ inline std::size_t plain_output_run(const unsigned char* s, std::size_t n) noexc
     return n;
 }
 
+/// Whether dump() with ensure_ascii writes the string at s unchanged, for a
+/// string of the source without escape sequences (which has no quote,
+/// backslash, or control character): no byte is DEL (0x7F) or above. Adding 1
+/// to each byte sets its high bit exactly for 0x7F, and a carry into the next
+/// byte only comes from 0xFF, whose own high bit is set anyway.
+inline bool is_ascii_without_delete(const char* s, std::size_t n) noexcept
+{
+    constexpr std::uint64_t ones = 0x0101010101010101ull;
+    constexpr std::uint64_t high = 0x8080808080808080ull;
+    std::size_t i = 0;
+    for (; i + 8 <= n; i += 8)
+    {
+        const std::uint64_t v = read_eight_bytes(s + i);
+        if (((v | (v + ones)) & high) != 0)
+        {
+            return false;
+        }
+    }
+    for (; i < n; ++i)
+    {
+        if (static_cast<unsigned char>(s[i]) >= 0x7F)
+        {
+            return false;
+        }
+    }
+    return true;
+}
+
 /// A stack that starts in a buffer of the caller (a local array) and moves to
 /// the heap (a vector of the caller) only when that is full, so that dumps of
 /// shallow documents need no allocation. The top is a pointer, as in
@@ -6347,15 +6339,19 @@ class view_serializer
 
     void dump(const node* root)
     {
-        if (!m_style.pretty && !m_style.ensure_ascii)
+        if (!m_style.pretty)
         {
-            if (m_style.source_numbers)
+            if (m_style.ensure_ascii)
             {
-                dump_compact<true>(root);
+                dump_compact_ascii(root);
+            }
+            else if (m_style.source_numbers)
+            {
+                dump_compact<true, false>(root);
             }
             else
             {
-                dump_compact<false>(root);
+                dump_compact<false, false>(root);
             }
             return;
         }
@@ -6461,6 +6457,41 @@ class view_serializer
         m_out.put('"');
     }
 
+    /// dump_compact() with ensure_ascii, out of line: the walk without it is
+    /// faster when it is not merged with this one into dump()
+    NLOHMANN_VIEW_NOINLINE void dump_compact_ascii(const node* root)
+    {
+        if (m_style.source_numbers)
+        {
+            dump_compact<true, true>(root);
+        }
+        else
+        {
+            dump_compact<false, true>(root);
+        }
+    }
+
+    /// whether dump_compact() copies a string or key from the source: one of
+    /// the source, and with ensure_ascii one without bytes >= 0x7F (an overload
+    /// each, so that the walk without ensure_ascii is compiled exactly as
+    /// before: with GCC, a condition that only folds away later changed its
+    /// block layout and made it 4-6% slower)
+    static bool copied(const node& n, const char* /*src*/, std::false_type /*ensure_ascii*/) noexcept
+    {
+        return (n.flags & node_flags::storage) == 0;
+    }
+
+    static bool copied(const node& n, const char* src, std::true_type /*ensure_ascii*/) noexcept
+    {
+        return (n.flags & node_flags::storage) == 0 && is_ascii_without_delete(src + n.off, n.len);
+    }
+
+    /// a string with ensure_ascii (dump_compact()), out of line
+    NLOHMANN_VIEW_NOINLINE void write_ascii_string(const node& n)
+    {
+        write_string(n);
+    }
+
     /// the copies of dump_compact() that are not fixed-size moves (long
     /// strings, or near the end of the source); out of line, so that the
     /// compiler does not merge the fixed-size moves into this call
@@ -6478,16 +6509,18 @@ class view_serializer
     }
 
     /*!
-    @brief the compact output without ensure_ascii (the default dump())
+    @brief the compact output (the default dump(), or with ensure_ascii)
 
     The same walk as dump(), with the write position in a local variable
     (stores through char pointers would otherwise force a reload of the
     buffer's members after each one), and with strings and number tokens of
     the source copied by fixed-size moves of 32 bytes where the source has
     that many bytes left, instead of a library call per token. The buffer
-    keeps 64 bytes of slack for the overshoot.
+    keeps 64 bytes of slack for the overshoot. With ensure_ascii (Ascii), a
+    string of the source is copied only if it has no byte >= 0x7F (see
+    is_ascii_without_delete()); any other string is written by write_string().
     */
-    template<bool SourceNumbers>
+    template<bool SourceNumbers, bool Ascii>
     void dump_compact(const node* root)
     {
         struct frame
@@ -6539,7 +6572,14 @@ class view_serializer
         const auto escaped = [&](const node & n)
         {
             m_out.set_cursor(w);
-            write_decoded(n);
+            if (enabled(Ascii))
+            {
+                write_ascii_string(n);
+            }
+            else
+            {
+                write_decoded(n);
+            }
             w = m_out.cursor();
             lim = m_out.limit();
         };
@@ -6562,7 +6602,7 @@ class view_serializer
             switch (static_cast<value_t>(n->kind))
             {
                 case value_t::string:
-                    if ((n->flags & node_flags::storage) == 0)
+                    if (copied(*n, src, std::integral_constant<bool, Ascii>()))
                     {
                         room(n->len + 2);
                         *w++ = '"';
@@ -6693,7 +6733,7 @@ class view_serializer
             if (cur.object)
             {
                 const node& key = *at;
-                if ((key.flags & node_flags::storage) == 0)
+                if (copied(key, src, std::integral_constant<bool, Ascii>()))
                 {
                     room(key.len + 3);
                     *w++ = '"';
@@ -6855,8 +6895,7 @@ class view_serializer
     static char* write_double_value_at(char* w, double x)
     {
         // (from the bits: without the checks of to_chars())
-        std::uint64_t bits = 0;
+        auto bits = bit_cast<std::uint64_t>(x);
-        std::memcpy(&bits, &x, sizeof(bits));
         if (NLOHMANN_VIEW_UNLIKELY((bits & 0x7FF0000000000000u) == 0x7FF0000000000000u))
         {
             return write_text_at(w, "null", 4);
@@ -6879,21 +6918,17 @@ class view_serializer
             m_out.put("null");
             return;
         }
-        static constexpr bool is_ieee_single_or_double
+        write_float(x, std::integral_constant<bool, ::nlohmann::detail::has_native_float_format<number_float_t>::value>());
-            = std::numeric_limits<number_float_t>::is_iec559
-              && ((std::numeric_limits<number_float_t>::digits == 24 && std::numeric_limits<number_float_t>::max_exponent == 128)
-                  || (std::numeric_limits<number_float_t>::digits == 53 && std::numeric_limits<number_float_t>::max_exponent == 1024));
-        write_float(x, std::integral_constant<bool, is_ieee_single_or_double>());
     }
 
-    void write_float(number_float_t x, std::true_type /*is_ieee_single_or_double*/)
+    void write_float(number_float_t x, std::true_type /*has_native_float_format*/)
     {
         std::array<char, 64> buf{};
         const char* const end = ::nlohmann::detail::to_chars(buf.data(), buf.data() + buf.size(), x);
         m_out.put(buf.data(), static_cast<std::size_t>(end - buf.data()));
     }
 
-    void write_float(number_float_t x, std::false_type /*is_ieee_single_or_double*/)
+    void write_float(number_float_t x, std::false_type /*has_native_float_format*/)
     {
         // other types (e.g. long double) are rare: the library writes them
         const string_t s = BasicJsonType(x).dump();
@@ -6904,9 +6939,10 @@ class view_serializer
     {
         const char* const s = m_doc.str(n);
         m_out.put('"');
-        if ((n.flags & node_flags::storage) == 0 && !m_style.ensure_ascii)
+        if ((n.flags & node_flags::storage) == 0 && (!m_style.ensure_ascii || is_ascii_without_delete(s, n.len)))
         {
-            // a string of the source without escape sequences has nothing to escape
+            // a string of the source without escape sequences has nothing to
+            // escape (with ensure_ascii, if it is printable ASCII)
             m_out.put(s, n.len);
         }
         else if (m_style.ensure_ascii)
@@ -7019,8 +7055,8 @@ class view_serializer
 
     void write_u_escape(std::uint32_t u)
     {
-        static constexpr const char* hex = "0123456789abcdef";
+        std::array<char, 6> e = {{'\\', 'u', 0, 0, 0, 0}};
-        const std::array<char, 6> e = {{'\\', 'u', hex[(u >> 12u) & 0xFu], hex[(u >> 8u) & 0xFu], hex[(u >> 4u) & 0xFu], hex[u & 0xFu]}};
+        hex4_lower(static_cast<std::uint16_t>(u), &e[2]);
         m_out.put(e.data(), e.size());
     }
 
@@ -7217,7 +7253,7 @@ NLOHMANN_VIEW_ALWAYS_INLINE T arithmetic_value(const document_data& d, const nod
         case value_t::binary:
         case value_t::discarded:
         default:
-            throw_type_error(302, "type must be number, but is ", value_type_name(static_cast<value_t>(n.kind)));
+            throw_type_error(exception_id::type_mismatch, "type must be number, but is ", value_type_name(static_cast<value_t>(n.kind)));
     }
 }
 
@@ -7227,7 +7263,7 @@ std::vector<U, A> vector_value(const View& v)
 {
     if (NLOHMANN_VIEW_UNLIKELY(!v.is_array()))
     {
-        throw_type_error(302, "type must be array, but is ", v.type_name());
+        throw_type_error(exception_id::type_mismatch, "type must be array, but is ", v.type_name());
     }
     std::vector<U, A> r;
     r.reserve(v.size());
@@ -7245,7 +7281,7 @@ Map map_value(const View& v)
 {
     if (NLOHMANN_VIEW_UNLIKELY(!v.is_object()))
     {
-        throw_type_error(302, "type must be object, but is ", v.type_name());
+        throw_type_error(exception_id::type_mismatch, "type must be object, but is ", v.type_name());
     }
     Map r;
     for (auto it = v.begin(); it != v.end(); ++it)
@@ -7484,7 +7520,7 @@ class basic_json_view
             {
                 return {};
             }
-            detail::view::throw_type_error(305, "cannot use operator[] with a string argument with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::subscript_wrong_type, "cannot use operator[] with a string argument with ", type_name());
         }
         return lookup(key);
     }
@@ -7510,7 +7546,7 @@ class basic_json_view
             {
                 return {};
             }
-            detail::view::throw_type_error(305, "cannot use operator[] with a numeric argument with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::subscript_wrong_type, "cannot use operator[] with a numeric argument with ", type_name());
         }
         return idx < m_node->len ? basic_json_view(m_doc, navigation::value(detail::view::element_at<Editable>(*m_doc, m_node, idx))) : basic_json_view();
     }
@@ -7543,12 +7579,12 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_object()))
         {
-            detail::view::throw_type_error(304, "cannot use at() with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::at_wrong_type, "cannot use at() with ", type_name());
         }
         const basic_json_view r = lookup(key);
         if (NLOHMANN_VIEW_UNLIKELY(r.is_discarded()))
         {
-            detail::view::throw_out_of_range(403, detail::concat("key '", std::string(key.data(), key.size()), "' not found"));
+            detail::view::throw_key_not_found(std::string(key.data(), key.size()));
         }
         return r;
     }
@@ -7569,11 +7605,11 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_array()))
         {
-            detail::view::throw_type_error(304, "cannot use at() with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::at_wrong_type, "cannot use at() with ", type_name());
         }
         if (NLOHMANN_VIEW_UNLIKELY(idx >= m_node->len))
         {
-            detail::view::throw_out_of_range(401, detail::concat("array index ", std::to_string(idx), " is out of range"));
+            detail::view::throw_array_index_out_of_range(idx);
         }
         return basic_json_view(m_doc, navigation::value(detail::view::element_at<Editable>(*m_doc, m_node, idx)));
     }
@@ -7601,7 +7637,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_object()))
         {
-            detail::view::throw_type_error(306, "cannot use value() with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::value_wrong_type, "cannot use value() with ", type_name());
         }
         const basic_json_view r = lookup(key);
         return r.is_discarded() ? default_value : r.template get<T>();
@@ -7620,7 +7656,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_structured()))
         {
-            detail::view::throw_type_error(306, "cannot use value() with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::value_wrong_type, "cannot use value() with ", type_name());
         }
         const basic_json_view r = detail::view::resolve_pointer(*this, detail::json_pointer_access::reference_tokens(ptr), detail::view::pointer_mode::value);
         return r.is_discarded() ? default_value : r.template get<T>();
@@ -7638,7 +7674,7 @@ class basic_json_view
         const iterator it = begin();
         if (NLOHMANN_VIEW_UNLIKELY(it == end()))
         {
-            detail::view::throw_invalid_iterator(214, "cannot get value");
+            detail::view::throw_invalid_iterator(detail::exception_id::iterator_value_unavailable, "cannot get value");
         }
         return *it;
     }
@@ -7790,7 +7826,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_string()))
         {
-            detail::view::throw_type_error(302, "type must be string, but is ", type_name());
+            detail::view::throw_type_error(detail::exception_id::type_mismatch, "type must be string, but is ", type_name());
         }
         return {m_doc->str(*m_node), m_node->len};
     }
@@ -7802,7 +7838,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_number()))
         {
-            detail::view::throw_type_error(302, "type must be number, but is ", type_name());
+            detail::view::throw_type_error(detail::exception_id::type_mismatch, "type must be number, but is ", type_name());
         }
         return {m_doc->str(*m_node), detail::view::number_length(*m_node)};
     }
@@ -8012,7 +8048,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_boolean()))
         {
-            detail::view::throw_type_error(302, "type must be boolean, but is ", type_name());
+            detail::view::throw_type_error(detail::exception_id::type_mismatch, "type must be boolean, but is ", type_name());
         }
         return (m_node->flags & detail::view::node_flags::is_true) != 0;
     }
@@ -8022,7 +8058,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(m_node == nullptr))
         {
-            detail::view::throw_type_error(302, "type must be number, but is ", type_name());
+            detail::view::throw_type_error(detail::exception_id::type_mismatch, "type must be number, but is ", type_name());
         }
         return detail::view::arithmetic_value<T, BasicJsonType>(*m_doc, *m_node);
     }
@@ -8031,7 +8067,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_null()))
         {
-            detail::view::throw_type_error(302, "type must be null, but is ", type_name());
+            detail::view::throw_type_error(detail::exception_id::type_mismatch, "type must be null, but is ", type_name());
         }
         return nullptr;
     }
@@ -8340,7 +8376,7 @@ class basic_json_document
     {
         if (NLOHMANN_VIEW_UNLIKELY(!m_data || m_data->discarded))
         {
-            detail::view::throw_type_error(320, "cannot save a discarded json_document");
+            detail::view::throw_type_error(detail::exception_id::document_image_unsupported, "cannot save a discarded json_document");
         }
         return detail::view::save_image(*m_data);
     }
@@ -8441,7 +8477,7 @@ class basic_json_document
                 const std::size_t idx = pointer_index(token);
                 if (idx >= 0xFFFFFFFFu)
                 {
-                    detail::view::throw_out_of_range(401, detail::concat("array index ", std::to_string(idx), " is out of range"));
+                    detail::view::throw_array_index_out_of_range(idx);
                 }
                 for (std::size_t i = 0; i < idx; ++i)
                 {
@@ -8497,7 +8533,7 @@ class basic_json_document
     {
         if (ptr.empty())
         {
-            detail::view::throw_out_of_range(405, "JSON pointer has no parent");
+            detail::view::throw_out_of_range(detail::exception_id::patch_on_root, "JSON pointer has no parent");
         }
         const view_type parent = root().at(ptr.parent_pointer());
         const auto& token = ptr.back();
@@ -8517,7 +8553,7 @@ class basic_json_document
         static_assert(Editable, "only an editable document can be edited: use basic_json_document<BasicJsonType, true> (json_editable_document)");
         if (NLOHMANN_VIEW_UNLIKELY(!m_data || m_data->discarded))
         {
-            detail::view::throw_invalid_iterator(202, "view does not belong to this document");
+            detail::view::throw_invalid_iterator(detail::exception_id::iterator_from_other_value, "view does not belong to this document");
         }
         return detail::view::editor<BasicJsonType, view_type>(*m_data);
     }
@@ -8534,7 +8570,7 @@ class basic_json_document
     {
         if (idx < 0)
         {
-            detail::view::throw_out_of_range(401, detail::concat("array index ", std::to_string(idx), " is out of range"));
+            detail::view::throw_array_index_out_of_range(idx);
         }
         return static_cast<std::size_t>(idx);
     }

tests/CMakeLists.txt

@@ -2,14 +2,12 @@ cmake_minimum_required(VERSION 3.13...4.0)
 
 option(JSON_Valgrind    "Execute test suite with Valgrind." OFF)
 option(JSON_FastTests   "Skip expensive/slow tests." OFF)
-option(JSON_TestUnityBuild "Build the unit tests in batches of several files per executable to speed up compilation." ON)
 option(JSON_TestSimdutf "Build the unit tests against the simdutf UTF-8 validation backend." OFF)
 
 set(JSON_SIMDUTF_VERSION 9.1.0 CACHE STRING "The simdutf version used by JSON_TestSimdutf.")
 
 set(JSON_32bitTest     AUTO CACHE STRING "Enable the 32bit unit test (ON/OFF/AUTO/ONLY).")
 set(JSON_TestStandards "" CACHE STRING "The list of standards to test explicitly.")
-set(JSON_TestUnityBatchSize 8 CACHE STRING "The number of unit test files compiled into one executable with JSON_TestUnityBuild.")
 set(JSON_TestShard     "" CACHE STRING "Build only a part of the unit tests, given as <index>/<count> (e.g. 0/2), to split them across CI jobs with a time limit.")
 
 # using an env var, since this will also affect targets executing cmake (such as "ci_test_compiler_default")
@@ -22,11 +20,6 @@ endif()
 
 include(test)
 
-# MinGW's GNU ld hits section and relocation limits with the large merged translation units
-if(MINGW)
-    set(JSON_TestUnityBuild OFF)
-endif()
-
 #############################################################################
 # override standard support
 #############################################################################
@@ -333,28 +326,9 @@ if(NOT "${JSON_TestShard}" STREQUAL "")
     message(STATUS "Test shard ${JSON_TestShard}: ${shard_file_count} of ${test_file_count} unit test files")
 endif()
 
-# Explicit groups of test files (file names without "unit-" and ".cpp") for
+foreach(file ${files})
-# JSON_TestUnityBuild: all files of a group are compiled into one translation
+    json_test_add_test_for(${file} MAIN test_main CXX_STANDARDS ${test_cxx_standards} ${test_force})
-# unit per C++ standard, so that related tests share their template
+endforeach()
-# instantiations (all binary formats instantiate the same readers and
-# writers). Only add a group where this was measured to pay off: grouping
-# files that share little just creates one slow translation unit. Files in no
-# group are batched alphabetically by JSON_TestUnityBatchSize.
-set(json_test_unity_groups binary)
-set(json_test_unity_group_binary binary_formats binary_utf8_error_handler binary_writer_sinks bjdata bon8 bon8-cpp17 bson byte_container_with_subtype cbor msgpack msgpack-cpp17 ubjson)
-
-if(JSON_TestUnityBuild)
-    message(STATUS "Building the unit tests in batches of ${JSON_TestUnityBatchSize} files (JSON_TestUnityBuild)")
-    json_test_add_unity_tests(FILES ${files} MAIN test_main CXX_STANDARDS ${test_cxx_standards} ${test_force}
-        BATCH_SIZE ${JSON_TestUnityBatchSize}
-        GROUPS ${json_test_unity_groups}
-        VARIANT_FILES src/unit-comparison.cpp src/unit-comparison-cpp20.cpp src/unit-class_parser.cpp src/unit-diagnostic-positions.cpp
-    )
-else()
-    foreach(file ${files})
-        json_test_add_test_for(${file} MAIN test_main CXX_STANDARDS ${test_cxx_standards} ${test_force})
-    endforeach()
-endif()
 
 # tests/src/unit-no-macro-leak.cpp #include-s the generated leak-check file,
 # so its test targets must be built after generate_hedley_undef_checks.
@@ -380,13 +354,6 @@ json_test_add_test_for(src/unit-comparison.cpp
     NAME test-comparison_legacy
     MAIN test_main CXX_STANDARDS ${test_cxx_standards} ${test_force}
 )
-json_test_set_test_options(test-comparison_legacy-cpp20
-    COMPILE_DEFINITIONS JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON=1
-)
-json_test_add_test_for(src/unit-comparison-cpp20.cpp
-    NAME test-comparison_legacy-cpp20
-    MAIN test_main CXX_STANDARDS ${test_cxx_standards} ${test_force}
-)
 
 # test the parser again with JSON_DIAGNOSTIC_POSITIONS enabled
 json_test_set_test_options(test-class_parser_diagnostic_positions
@@ -406,6 +373,25 @@ json_test_add_test_for(src/unit-diagnostic-positions.cpp
     MAIN test_main CXX_STANDARDS ${test_cxx_standards} ${test_force}
 )
 
+# the lexer again with the portable string scanning instead of SSE2/NEON, and on
+# x86-64 with SSSE3 compiled in (no check of the CPU)
+json_test_set_test_options(test-class_lexer_no_simd
+    COMPILE_DEFINITIONS JSON_NO_SIMD
+)
+json_test_add_test_for(src/unit-class_lexer.cpp
+    NAME test-class_lexer_no_simd
+    MAIN test_main CXX_STANDARDS ${test_cxx_standards} ${test_force}
+)
+if(CMAKE_SYSTEM_PROCESSOR MATCHES "^(x86_64|AMD64|amd64)$" AND NOT MSVC)
+    json_test_set_test_options(test-class_lexer_ssse3
+        COMPILE_OPTIONS -mssse3
+    )
+    json_test_add_test_for(src/unit-class_lexer.cpp
+        NAME test-class_lexer_ssse3
+        MAIN test_main CXX_STANDARDS ${test_cxx_standards} ${test_force}
+    )
+endif()
+
 # test reading from a std::istream again without scanning the get area in bulk
 json_test_set_test_options(test-stream-bulk-scan_disabled
     COMPILE_DEFINITIONS JSON_DISABLE_STREAM_BULK_SCAN=1

tests/README.md

@@ -1,92 +0,0 @@
-# Unit tests
-
-The unit tests are in [`src/unit-*.cpp`](src) and use [doctest](https://github.com/doctest/doctest). Each file becomes
-one CTest test per C++ standard it is built for, named after the file: `src/unit-foo.cpp` becomes `test-foo_cpp11`.
-
-## Build and run
-
-```sh
-cmake -S . -B build -DJSON_BuildTests=ON
-cmake --build build -j 10
-ctest --test-dir build -j 10
-```
-
-The [CMake options](../docs/mkdocs/docs/integration/cmake.md) starting with `JSON_Test` (and `JSON_FastTests`,
-`JSON_Valgrind`) control the test build. The most relevant ones:
-
-- `JSON_TestStandards`: build every test file for the given standards, e.g., `-DJSON_TestStandards=17`. By default,
-  a file is built for C++11 and for each standard whose `JSON_HAS_CPP_<N>` macro it mentions (see below).
-- `JSON_TestUnityBuild`: compile several test files together (see below). Set it to `OFF` to get one executable per
-  test file, e.g., to debug a single test in a debugger.
-- `JSON_TestShard`: build only a part of the test files, e.g., `-DJSON_TestShard=0/2`.
-
-To run the tests of one file only, run its CTest test, e.g., `ctest --test-dir build -R test-foo_cpp11`.
-
-## How test files are built
-
-Two mechanisms keep the compile time down. Both are automatic, but they set a few rules for test files.
-
-### C++ standards
-
-A test file is built for a C++ standard beyond C++11 if its text contains `JSON_HAS_CPP_<N>`, for instance in
-`#ifdef JSON_HAS_CPP_17`, or in a comment `// JSON_HAS_CPP_17` next to code that needs a macro only defined for that
-standard, such as `JSON_HAS_FILESYSTEM`. Then the *whole file* is compiled again for that standard.
-
-So that this does not happen for the large files, tests that need C++14, C++17, or C++20 go into a separate file
-`src/unit-<name>-cpp<N>.cpp` (e.g., [`src/unit-regression3-cpp17.cpp`](src/unit-regression3-cpp17.cpp)), whose body
-is wrapped in `#ifdef JSON_HAS_CPP_<N>`. The main file `src/unit-<name>.cpp` must not mention `JSON_HAS_CPP_<N>` at
-all, not even in a comment, so it is built for C++11 only. The CI jobs `ci_test_*_cxx<N>` still build every test file
-for every standard.
-
-### Unity build
-
-With `JSON_TestUnityBuild` (`ON` by default, `OFF` with MinGW), CMake compiles several test files as one translation
-unit, so they share the template instantiations of the library. CMake generates `build/tests/unity/test-unity-*.cpp`,
-which `#include` the test files of a batch. Every test file still gets its own CTest test, which runs the batch
-executable with `--source-file=*unit-foo.cpp`, so only the test cases of that file run.
-
-CMake decides from the macros a file defines *before* including `<nlohmann/json.hpp>`:
-
-| Macros defined before the include                                                         | Built as                          |
-|-------------------------------------------------------------------------------------------|-----------------------------------|
-| none (or only `SKIP_TESTS_FOR_*` and similar macros derived from global definitions)      | batch with the other plain files  |
-| only `JSON_TESTS_PRIVATE`                                                                 | batch with the other such files   |
-| any library configuration macro (`JSON_DIAGNOSTICS`, `JSON_NO_IO`, `JSON_ASSERT`, ...)    | its own executable                |
-
-Files with test-specific build options (`json_test_set_test_options(test-foo ...)` in
-[`CMakeLists.txt`](CMakeLists.txt)) also get their own executable. The batchable files are split alphabetically into
-batches of `JSON_TestUnityBatchSize` files, except for explicit groups of related files: `json_test_unity_group_binary`
-compiles all binary-format tests together, because they share the binary readers and writers. Only add a group if it
-measurably pays off; files that share little just make one slow translation unit.
-
-## Rules for test files
-
-Because the files of a batch share one translation unit, a test file must not affect the files that follow it:
-
-1. **Give file-scope helpers file-specific names.** An anonymous namespace does not help, as the batch is one
-   translation unit. Use a name such as `my_allocator_2982`, or wrap the helpers in a namespace named after the file
-   (e.g., `namespace unit_comparison_detail`). Clashes show up as compile errors.
-2. **Do not `#undef` library macros**, such as `JSON_HAS_CPP_17`, at the end of a file: this silently disables the tests
-   that depend on them in the later files of the batch. `#undef` macros you define yourself after including the library.
-3. **Put version-dependent tests into `unit-<name>-cpp<N>.cpp`** (see [C++ standards](#c-standards)).
-4. **Define test cases in the `.cpp` file itself.** The batch executable selects the tests of a file by its name, so a
-   `TEST_CASE` in a shared header is not run. The only exception is the test case in
-   [`src/make_test_data_available.hpp`](src/make_test_data_available.hpp), which CMake handles explicitly.
-
-To check a new file for clashes with all others at once, build with `-DJSON_TestUnityBatchSize=1000`, which puts all
-batchable files of a kind into one translation unit.
-
-## Where to add tests
-
-Tests are structured along the features of the library. Usually, an existing file is the right place:
-
-- For a bug fix, add a section referencing the issue to [`src/unit-regression3.cpp`](src/unit-regression3.cpp), or to
-  [`src/unit-regression3-cpp17.cpp`](src/unit-regression3-cpp17.cpp) /
-  [`src/unit-regression3-cpp20.cpp`](src/unit-regression3-cpp20.cpp) if the test needs C++17 / C++20.
-  [`src/unit-regression2.cpp`](src/unit-regression2.cpp) holds older tests and should not grow further.
-- When testing exceptions, use `CHECK_THROWS_WITH_AS`, which also checks the `what()` message.
-
-A new file `src/unit-<name>.cpp` is picked up automatically when CMake runs again; no change to `CMakeLists.txt` is
-needed.
-
-See also [`fuzzing.md`](fuzzing.md) for fuzz testing.

tests/abi/config/CMakeLists.txt

@@ -24,6 +24,7 @@ foreach(test default noversion)
         JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON=1
         JSON_DISABLE_STREAM_BULK_SCAN=1
         JSON_DISABLE_UNLOCKED_FILE_IO=1
+        JSON_NO_SIMD
         JSON_VIEW_NO_SIMD
         JSON_VIEW_USE_SSSE3)
     target_link_libraries(abi_config_${test}_all_tags PRIVATE abi_compat_main)

tests/abi/config/default.cpp

@@ -60,6 +60,10 @@ TEST_CASE("default namespace")
         expected += "_dufio";
 #endif
 
+#ifdef JSON_NO_SIMD
+        expected += "_ns";
+#endif
+
 #ifdef JSON_VIEW_NO_SIMD
         expected += "_vns";
 #endif

tests/abi/config/noversion.cpp

@@ -61,6 +61,10 @@ TEST_CASE("default namespace without version component")
         expected += "_dufio";
 #endif
 
+#ifdef JSON_NO_SIMD
+        expected += "_ns";
+#endif
+
 #ifdef JSON_VIEW_NO_SIMD
         expected += "_vns";
 #endif

tests/benchmarks/README.md

@@ -22,6 +22,15 @@ Micro-benchmarks for parsing, serialization and the binary formats, written with
 | `ViewAccept` | validate with `json_document::accept`; compare with `Accept` |
 | `ViewMaterialize` | convert a parsed `json_document` into a `json` value |
 | `ViewDump` | serialize a parsed `json_document`; compare with `Dump` |
+| `SaxParse` | parse with a SAX handler that only counts events, so no values are built |
+| `Copy`, `CopyAssign`, `CopyRing` | copy a parsed document and destroy a copy, both timed: a temporary copy, an assignment over an earlier copy, and replacing the oldest of eight live copies |
+| `CopyOnly`, `DestroyOnly` | only the copy or only the destruction, the other half untimed; a fast destructor can leave work to the next allocations, so these tell the halves apart but do not compare versions |
+| `Equal`, `Iterate` | compare a parsed document with a copy, or visit every value with range-based `for` loops |
+| `Flatten`, `FlattenOrdered`, `Unflatten` | `flatten()` for `json` and `ordered_json`, and `unflatten()` |
+| `Diff`, `Patch` | `diff()` against the document with every eighth scalar changed, and applying that patch |
+| `JsonPointerParse`, `JsonPointerToString`, `JsonPointerAt`, `JsonPointerContains` | the JSON pointers of every scalar in a document: parse them from strings, turn them back into strings, look them up with `at()` and `contains()` |
+| `GetVectorInt`, `GetVectorDouble`, `GetMap` | `get<std::vector<std::int64_t>>()`, `get<std::vector<double>>()` and `get<std::map<std::string, json>>()` on large arrays and a large flat object |
+| `ToJsonStrings` | create a `json` array from a `std::vector` of 100,000 strings, copied or moved, and destroy it again |
 
 The input files are those of [nativejson-benchmark](https://github.com/miloyip/nativejson-benchmark) (`canada`,
 `citm_catalog`, `twitter`), a large `jeopardy` file, and number-heavy files (`floats`, `signed_ints`, ...).

tests/benchmarks/json_view/.gitignore

@@ -0,0 +1 @@
+build/

tests/benchmarks/json_view/README.md

@@ -0,0 +1,90 @@
+# json_view compared with other libraries
+
+The in-tree benchmarks in [`tests/benchmarks`](../README.md) measure `json_document` against `json::parse` only. The
+programs here compare it with [yyjson](https://github.com/ibireme/yyjson),
+[simdjson](https://github.com/simdjson/simdjson), and [Boost.JSON](https://github.com/boostorg/json): the question
+users ask when they pick a library. They are not built by CMake or run by CI.
+
+## Reproducing the numbers
+
+`compare.py` builds the programs against `include/` of this checkout, runs them, and writes the results together with
+everything needed to reproduce them to `results/<date>-<host>.md` (and `.csv`): the date, the commit, the CPU, the
+OS, the compiler, the flags, and the versions of all libraries.
+
+```sh
+python3 tests/benchmarks/json_view/compare.py --data <json_test_data directory> [--native] [--rounds 30]
+```
+
+- `--data` is the downloaded [test data](https://github.com/nlohmann/json_test_data), e.g. the `test_files` directory
+  of a CMake build directory. It needs `nativejson-benchmark/{twitter,citm_catalog,canada}.json` and
+  `jeopardy/jeopardy.json`.
+- The other libraries come from the system: pkg-config, or Homebrew (`brew install yyjson simdjson boost`). With
+  `--download`, pinned releases are downloaded instead and checked against their SHA-256. Without Boost headers (or
+  with `--no-boost`), the Boost.JSON columns are skipped, and the results say so.
+- `--corpus file...` adds files to the corpus benchmark, e.g. those of
+  [simdjson-data](https://github.com/simdjson/simdjson-data) or the
+  [yyjson benchmark](https://github.com/ibireme/yyjson_benchmark).
+- Only the Python 3 standard library is used; a C++17 compiler is needed (`CXX` and `CC` are honored).
+
+For numbers worth publishing, use a quiet machine (see [Getting stable numbers](../README.md#getting-stable-numbers)),
+the default 30 rounds or more, and `--native` only if the other libraries were built for the same CPU.
+
+### On GitHub-hosted runners
+
+The workflow [json_view benchmarks](../../../.github/workflows/json_view_benchmarks.yml) runs `compare.py --download`
+on demand: by hand (Actions → "json_view benchmarks" → "Run workflow"), on an x86-64 or AArch64 Ubuntu runner with GCC
+or Clang, or when a pull request gets the label `benchmark`, on both architectures with GCC. The results appear as the
+job summary and as an artifact. Shared runners are noisy, so these numbers show
+where `json_view` stands on another architecture; they are not meant for publication.
+
+## What is measured
+
+`bench_view.cpp` runs four workloads on twitter, citm_catalog, canada, jeopardy, a single tweet (`status`), and a
+JSON-RPC request (`rpc`):
+
+| workload | what it does |
+|---|---|
+| parse | build and free a document |
+| traverse | parse, then visit every value, convert every number, touch every string and key |
+| select | parse, then read a few fields per record (e.g. id, user name, and retweet count of each tweet) |
+| dump | serialize a parsed document (compact) |
+
+`bench_corpus.cpp` runs parse, traverse, and dump on any list of files, so that no library is tuned to a handful of
+documents. Its dump also writes the numbers as they are in the input: `json_view` with `number_format::source`, and
+yyjson with numbers read as raw text (`YYJSON_READ_NUMBER_AS_RAW`), without converting them.
+
+`bench_edit.cpp` measures read-modify-write: parse, apply the same logical edits with each library's own API, and
+serialize (compact). Workloads: `patch` (a handful of edits at fixed places) and `update` (edits in every record).
+An editable `json_document` edits in place; yyjson copies its immutable document into a mutable one first
+(`yyjson_doc_mut_copy`); Boost.JSON and `json::parse` build mutable DOMs; simdjson cannot edit a document. All
+outputs are checked to describe the same value.
+
+Before anything is timed, all engines must accept each document and agree on the traversal: the number of values, the
+bytes of all strings and keys, and the sum of all numbers. All engines run interleaved in every round, and the best
+round is reported, as time and as a factor of the `json_view` time (below 1 means faster than `json_view`). Each timed
+call follows an untimed call of the same engine: otherwise the engine after `json::parse` pays for the allocator
+cleaning up the tens of thousands of nodes `json::parse` just freed (with glibc, this made `json_view` look 1.7 times
+slower on citm_catalog traverse).
+
+The engines do not all offer the same features, which the numbers should be read with:
+
+| engine | document | random access | editable | notes |
+|---|---|---|---|---|
+| `json_view` | immutable index into the text | yes | no | a fresh document per parse; "reused" parses into the same document |
+| yyjson | immutable (`yyjson_read`) | yes | via a mutable copy | |
+| simdjson DOM | immutable, parser reused | yes | no | "fresh" uses a new parser per parse |
+| simdjson On-Demand | none: forward-only, lazy | no | no | only traverse and select |
+| Boost.JSON | owning, mutable DOM | yes | yes | monotonic resource |
+| `json::parse` | owning, mutable DOM | yes | yes | |
+
+Reusing memory matters as much as the parser. simdjson DOM reuses its parser, so it writes into memory it already
+touched; a fresh `json_view` document or yyjson document gets new memory for every parse. On Linux, glibc returns large
+blocks to the system when they are freed, so every fresh parse of a large document pays a page fault per 4 KiB page:
+on x86-64 Linux, a fresh `json_view` parse of jeopardy took about twice as long as a reused one. On macOS on Apple
+silicon, with 16 KiB pages, the difference is much smaller. Compare "json_view (reused)" with "simdjson DOM", and the
+fresh `json_view` with "simdjson DOM (fresh)" and yyjson.
+
+## Published results
+
+Results are only published with the file `compare.py` wrote, which names the machine and the versions; see
+`results/`. Numbers from one machine and compiler do not carry over to another: rerun the script.

tests/benchmarks/json_view/bench_corpus.cpp

@@ -0,0 +1,348 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  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
+
+// Corpus benchmark: the read-only workloads of bench_view.cpp on any list of
+// JSON files (for example the benchmark sets of simdjson and yyjson).
+//
+//   ./bench_corpus [--rounds N] file...
+//
+// For every file, all engines must accept it and agree on a traversal (value
+// count, string bytes, sum of numbers) before anything is timed. Workloads:
+// parse (build and free a document), traverse (visit every value, convert
+// every number), dump (compact), and for json_view also dump with the source
+// number text, compared with yyjson writing numbers read as raw text
+// (YYJSON_READ_NUMBER_AS_RAW). Results go to bench_corpus.csv.
+#include <nlohmann/json_view.hpp>
+
+#if JSON_VIEW_BENCH_BOOST
+    #include <boost/json.hpp>
+    #include <boost/json/src.hpp>
+#endif
+#include <simdjson.h>
+#include <yyjson.h>
+
+#include <algorithm>
+#include <chrono>
+#include <cmath>
+#include <cstdio>
+#include <cstdlib>
+#include <cstring>
+#include <fstream>
+#include <functional>
+#include <sstream>
+#include <string>
+#include <vector>
+
+using nlohmann::json;
+using nlohmann::json_document;
+using nlohmann::json_view;
+
+static volatile double g_sink;
+
+struct stats
+{
+    double num = 0;
+    std::size_t str = 0, nodes = 0;
+};
+
+static void walk(json_view v, stats& st)
+{
+    ++st.nodes;
+    switch (v.type())
+    {
+        case json::value_t::object:
+            for (auto it = v.begin(); it != v.end(); ++it)
+            {
+                st.str += it.key().size();
+                walk(*it, st);
+            }
+            break;
+        case json::value_t::array:
+            for (const json_view e : v)
+            {
+                walk(e, st);
+            }
+            break;
+        case json::value_t::string:
+            st.str += v.get_string().size();
+            break;
+        case json::value_t::number_integer:
+            st.num += static_cast<double>(v.get<std::int64_t>());
+            break;
+        case json::value_t::number_unsigned:
+            st.num += static_cast<double>(v.get<std::uint64_t>());
+            break;
+        case json::value_t::number_float:
+            st.num += v.get<double>();
+            break;
+        default:
+            break;
+    }
+}
+
+static void walk(yyjson_val* v, stats& st)
+{
+    ++st.nodes;
+    switch (yyjson_get_type(v))
+    {
+        case YYJSON_TYPE_OBJ:
+        {
+            std::size_t idx, max;
+            yyjson_val* k, * val;
+            yyjson_obj_foreach(v, idx, max, k, val)
+            {
+                st.str += yyjson_get_len(k);
+                walk(val, st);
+            }
+            break;
+        }
+        case YYJSON_TYPE_ARR:
+        {
+            std::size_t idx, max;
+            yyjson_val* val;
+            yyjson_arr_foreach(v, idx, max, val)
+            {
+                walk(val, st);
+            }
+            break;
+        }
+        case YYJSON_TYPE_STR:
+            st.str += yyjson_get_len(v);
+            break;
+        case YYJSON_TYPE_NUM:
+            st.num += yyjson_is_sint(v) ? static_cast<double>(yyjson_get_sint(v)) : yyjson_is_uint(v) ? static_cast<double>(yyjson_get_uint(v)) : yyjson_get_real(v);
+            break;
+        default:
+            break;
+    }
+}
+
+static void walk(simdjson::dom::element e, stats& st)
+{
+    ++st.nodes;
+    switch (e.type())
+    {
+        case simdjson::dom::element_type::OBJECT:
+            for (auto f : simdjson::dom::object(e))
+            {
+                st.str += f.key.size();
+                walk(f.value, st);
+            }
+            break;
+        case simdjson::dom::element_type::ARRAY:
+            for (auto c : simdjson::dom::array(e))
+            {
+                walk(c, st);
+            }
+            break;
+        case simdjson::dom::element_type::STRING:
+            st.str += std::string_view(e).size();
+            break;
+        case simdjson::dom::element_type::INT64:
+            st.num += static_cast<double>(int64_t(e));
+            break;
+        case simdjson::dom::element_type::UINT64:
+            st.num += static_cast<double>(uint64_t(e));
+            break;
+        case simdjson::dom::element_type::DOUBLE:
+            st.num += double(e);
+            break;
+        default:
+            break;
+    }
+}
+
+#if JSON_VIEW_BENCH_BOOST
+static void walk(const boost::json::value& v, stats& st)
+{
+    ++st.nodes;
+    switch (v.kind())
+    {
+        case boost::json::kind::object:
+            for (const auto& kv : v.get_object())
+            {
+                st.str += kv.key().size();
+                walk(kv.value(), st);
+            }
+            break;
+        case boost::json::kind::array:
+            for (const auto& c : v.get_array())
+            {
+                walk(c, st);
+            }
+            break;
+        case boost::json::kind::string:
+            st.str += v.get_string().size();
+            break;
+        case boost::json::kind::int64:
+            st.num += static_cast<double>(v.get_int64());
+            break;
+        case boost::json::kind::uint64:
+            st.num += static_cast<double>(v.get_uint64());
+            break;
+        case boost::json::kind::double_:
+            st.num += v.get_double();
+            break;
+        default:
+            break;
+    }
+}
+#endif
+
+static std::string slurp(const std::string& p)
+{
+    std::ifstream f(p, std::ios::binary);
+    if (!f)
+    {
+        std::fprintf(stderr, "cannot open %s\n", p.c_str());
+        std::exit(1);
+    }
+    std::stringstream ss;
+    ss << f.rdbuf();
+    return ss.str();
+}
+
+static bool same(const stats& a, const stats& b)
+{
+    return a.nodes == b.nodes && a.str == b.str && (a.num == b.num || std::fabs(a.num - b.num) <= 1e-9 * std::fabs(a.num));
+}
+
+int main(int argc, char** argv)
+{
+    int rounds = 0; // 0: by size
+    std::vector<std::string> files;
+    for (int i = 1; i < argc; ++i)
+    {
+        if (std::strcmp(argv[i], "--rounds") == 0 && i + 1 < argc)
+        {
+            // (clamped: 0 rounds by size, at most a million)
+            rounds = static_cast<int>((std::min)((std::max)(std::strtol(argv[++i], nullptr, 10), 0L), 1000000L));
+        }
+        else
+        {
+            files.push_back(argv[i]);
+        }
+    }
+    std::FILE* csv = std::fopen("bench_corpus.csv", "w");
+    if (csv == nullptr)
+    {
+        std::perror("bench_corpus.csv");
+        return 1;
+    }
+    std::fprintf(csv, "file,bytes,workload,engine,ns\n");
+    json_document reused;
+    simdjson::dom::parser sj;
+    for (const auto& path : files)
+    {
+        const std::string s = slurp(path);
+        const std::string name = path.substr(path.rfind('/') + 1);
+        const simdjson::padded_string ps(s);
+
+        // all engines must agree before timing
+        stats a, b, c, d;
+        const json_document doc = json_document::parse(s);
+        walk(doc.root(), a);
+        yyjson_doc* y = yyjson_read(s.data(), s.size(), 0);
+        auto sjr = sj.parse(ps);
+#if JSON_VIEW_BENCH_BOOST
+        boost::json::parse_options opt;
+        opt.numbers = boost::json::number_precision::precise;
+        boost::json::monotonic_resource mr0;
+        const boost::json::value bv = boost::json::parse(s, &mr0, opt);
+#endif
+        if (y == nullptr || sjr.error())
+        {
+            std::printf("%-34s skipped (an engine rejects it)\n", name.c_str());
+            yyjson_doc_free(y);
+            continue;
+        }
+        walk(yyjson_doc_get_root(y), b);
+        walk(sjr.value_unsafe(), c);
+#if JSON_VIEW_BENCH_BOOST
+        walk(bv, d);
+#else
+        d = a;
+#endif
+        yyjson_doc_free(y);
+        const bool ok = same(a, b) && same(a, c) && same(a, d);
+
+        const int r = rounds > 0 ? rounds : static_cast<int>(std::max<std::size_t>(3, std::min<std::size_t>(60, 400000000 / (s.size() + 1))));
+        struct engine
+        {
+            std::string name;
+            std::function<void()> fn;
+        };
+        json_document vd = json_document::parse(s);
+        yyjson_doc* yd = yyjson_read(s.data(), s.size(), 0);
+        yyjson_doc* yd_raw = yyjson_read(s.data(), s.size(), YYJSON_READ_NUMBER_AS_RAW);
+        simdjson::dom::parser sjd;
+        const simdjson::dom::element se = sjd.parse(ps).value_unsafe();
+        const std::vector<std::pair<std::string, std::vector<engine>>> workloads =
+        {
+            {
+                "parse", {
+                    {"json_view", [&] { auto x = json_document::parse(s); g_sink = static_cast<double>(x.node_count()); }},
+                    {"json_view (reused)", [&] { reused.read(s); g_sink = static_cast<double>(reused.node_count()); }},
+                    {"yyjson", [&] { yyjson_doc* x = yyjson_read(s.data(), s.size(), 0); g_sink = static_cast<double>(yyjson_doc_get_val_count(x)); yyjson_doc_free(x); }},
+                    {"simdjson DOM", [&] { auto e = sj.parse(ps).value_unsafe(); g_sink = e.is_object(); }},
+                    {"simdjson DOM (fresh)", [&] { simdjson::dom::parser p; auto e = p.parse(ps).value_unsafe(); g_sink = e.is_object(); }},
+#if JSON_VIEW_BENCH_BOOST
+                    {"Boost.JSON", [&] { boost::json::monotonic_resource mr; auto v = boost::json::parse(s, &mr); g_sink = v.is_object(); }},
+#endif
+                }
+            },
+            {
+                "traverse", {
+                    {"json_view", [&] { auto x = json_document::parse(s); stats st; walk(x.root(), st); g_sink = st.num; }},
+                    {"yyjson", [&] { yyjson_doc* x = yyjson_read(s.data(), s.size(), 0); stats st; walk(yyjson_doc_get_root(x), st); g_sink = st.num; yyjson_doc_free(x); }},
+                    {"simdjson DOM", [&] { stats st; walk(sj.parse(ps).value_unsafe(), st); g_sink = st.num; }},
+#if JSON_VIEW_BENCH_BOOST
+                    {"Boost.JSON", [&] { boost::json::monotonic_resource mr; auto v = boost::json::parse(s, &mr); stats st; walk(v, st); g_sink = st.num; }},
+#endif
+                }
+            },
+            {
+                "dump", {
+                    {"json_view", [&] { std::string o = vd.root().dump(); g_sink = static_cast<double>(o.size()); }},
+                    {"yyjson", [&] { std::size_t n = 0; char* o = yyjson_write(yd, 0, &n); g_sink = static_cast<double>(n); std::free(o); }},
+                    {"simdjson DOM", [&] { std::string o = simdjson::to_string(se); g_sink = static_cast<double>(o.size()); }},
+                    {"json_view (source numbers)", [&] { std::string o = vd.root().dump(-1, ' ', false, json_view::number_format::source); g_sink = static_cast<double>(o.size()); }},
+                    {"yyjson (raw numbers)", [&] { std::size_t n = 0; char* o = yyjson_write(yd_raw, 0, &n); g_sink = static_cast<double>(n); std::free(o); }},
+                }
+            },
+        };
+        std::printf("%-34s %9zu B%s\n", name.c_str(), s.size(), ok ? "" : "  [ENGINES DISAGREE]");
+        for (const auto& wl : workloads)
+        {
+            std::vector<double> best(wl.second.size(), 1e300);
+            for (int i = 0; i < r; ++i)
+            {
+                for (std::size_t k = 0; k < wl.second.size(); ++k)
+                {
+                    // an untimed call first: whatever the previous engine left to the allocator
+                    // (e.g. thousands of freed json nodes) is cleaned up here, not in the timing
+                    wl.second[k].fn();
+                    const auto t0 = std::chrono::steady_clock::now();
+                    wl.second[k].fn();
+                    best[k] = std::min(best[k], std::chrono::duration<double, std::nano>(std::chrono::steady_clock::now() - t0).count());
+                }
+            }
+            std::printf("  %-9s", wl.first.c_str());
+            for (std::size_t k = 0; k < wl.second.size(); ++k)
+            {
+                std::printf("  %s %.2f GB/s (%.2fx)", wl.second[k].name.c_str(), static_cast<double>(s.size()) / best[k], best[k] / best[0]);
+                std::fprintf(csv, "%s,%zu,%s,%s,%.1f\n", name.c_str(), s.size(), wl.first.c_str(), wl.second[k].name.c_str(), best[k]);
+            }
+            std::printf("\n");
+            std::fflush(stdout);
+        }
+        yyjson_doc_free(yd);
+        yyjson_doc_free(yd_raw);
+    }
+    std::fclose(csv);
+}

tests/benchmarks/json_view/bench_edit.cpp

@@ -0,0 +1,589 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  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
+
+// Read-modify-write benchmark: parse a document, apply the same logical edits
+// with each library's own API, and serialize it (compact).
+//
+//   json_view     json_editable_document: edits in place, unchanged values stay in the index
+//   yyjson        yyjson_read + yyjson_doc_mut_copy (the way to edit a parsed document)
+//   Boost.JSON    parse into a mutable DOM (monotonic resource, precise numbers), serialize
+//   json::parse   nlohmann::json today
+// simdjson has no mutable document and is not part of this comparison.
+//
+// Workloads:
+//   patch   a handful of edits at fixed places (scalars, a new member, a new array element)
+//   update  edits in every record (twitter: 100 statuses, citm: 243 performances,
+//           canada: 480 rings, jeopardy: 216,930 questions): set scalars, erase a
+//           member, add a member (canada: replace the first point of every ring)
+//
+// Build: see README.md (same flags as bench_view.cpp).
+#include <nlohmann/json_view.hpp>
+
+#if JSON_VIEW_BENCH_BOOST
+    #include <boost/json.hpp>
+    #include <boost/json/src.hpp>
+#endif
+#include <yyjson.h>
+
+#include <algorithm>
+#include <chrono>
+#include <cstdio>
+#include <cstdlib>
+#include <fstream>
+#include <functional>
+#include <sstream>
+
+using nlohmann::json;
+using nlohmann::json_editable_document;
+using nlohmann::json_editable_view;
+#if JSON_VIEW_BENCH_BOOST
+    namespace bj = boost::json;
+#endif
+
+static volatile std::size_t g_sink;
+
+// ---------------- json_view ----------------
+
+static std::string edit_view(const std::string& name, const std::string& s, bool update)
+{
+    json_editable_document d = json_editable_document::parse(s);
+    const json_editable_view r = d.root();
+    if (name == "twitter")
+    {
+        if (update)
+        {
+            std::int64_t i = 0;
+            for (const json_editable_view st : r["statuses"])
+            {
+                d.set(st, "retweet_count", i++);
+                d.set(st, "favorited", true);
+                d.set(st, "text", "redacted");
+                d.erase(st, "entities");
+                d.set(st, "edited", true);
+            }
+        }
+        else
+        {
+            d.set(r["search_metadata"], "count", 200);
+            d.set(r["statuses"][0], "text", "patched");
+            d.set(r["statuses"][0]["user"], "followers_count", 1);
+            d.set(r["statuses"][99], "favorited", true);
+            d.set(r, "patched", true);
+        }
+    }
+    else if (name == "citm_catalog")
+    {
+        if (update)
+        {
+            for (const json_editable_view p : r["performances"])
+            {
+                d.set(p, "name", "performance");
+                d.set(p, "start", p["start"].get<std::int64_t>() + 1);
+                d.erase(p, "seatMapImage");
+                d.set(p, "edited", true);
+            }
+        }
+        else
+        {
+            d.set(r["events"]["138586341"], "name", "patched");
+            d.set(r["performances"][0], "start", 0);
+            d.set(r["venueNames"], "PLEYEL_PLEYEL", "Salle");
+            d.set(r, "patched", true);
+        }
+    }
+    else if (name == "canada")
+    {
+        const json_editable_view coords = r["features"][0]["geometry"]["coordinates"];
+        if (update)
+        {
+            for (const json_editable_view ring : coords)
+            {
+                d.set(ring, 0, json::array({0.5, 0.5}));
+            }
+        }
+        else
+        {
+            d.set(r["features"][0]["properties"], "name", "patched");
+            d.set(r, "type", "FeatureCollection2");
+            d.set(coords[0], 0, json::array({0.0, 0.0}));
+        }
+    }
+    else if (name == "jeopardy")
+    {
+        if (update)
+        {
+            for (const json_editable_view q : r)
+            {
+                d.set(q, "value", "$1");
+                d.erase(q, "air_date");
+            }
+        }
+        else
+        {
+            d.set(r[0], "value", "$0");
+            d.set(r[100000], "answer", "patched");
+            d.set(r[216929], "round", "x");
+            d.push_back(r, json::object({{"category", "NEW"}, {"value", "$5"}}));
+        }
+    }
+    else if (name == "status")
+    {
+        d.set(r, "retweet_count", 1);
+        d.set(r["user"], "name", "x");
+    }
+    else if (name == "rpc")
+    {
+        d.set(r, "id", 4);
+        d.set(r["params"], "subtrahend", 24);
+    }
+    return r.dump();
+}
+
+// ---------------- nlohmann::json ----------------
+
+static std::string edit_json(const std::string& name, const std::string& s, bool update)
+{
+    json r = json::parse(s);
+    if (name == "twitter")
+    {
+        if (update)
+        {
+            std::int64_t i = 0;
+            for (auto& st : r["statuses"])
+            {
+                st["retweet_count"] = i++;
+                st["favorited"] = true;
+                st["text"] = "redacted";
+                st.erase("entities");
+                st["edited"] = true;
+            }
+        }
+        else
+        {
+            r["search_metadata"]["count"] = 200;
+            r["statuses"][0]["text"] = "patched";
+            r["statuses"][0]["user"]["followers_count"] = 1;
+            r["statuses"][99]["favorited"] = true;
+            r["patched"] = true;
+        }
+    }
+    else if (name == "citm_catalog")
+    {
+        if (update)
+        {
+            for (auto& p : r["performances"])
+            {
+                p["name"] = "performance";
+                p["start"] = p["start"].get<std::int64_t>() + 1;
+                p.erase("seatMapImage");
+                p["edited"] = true;
+            }
+        }
+        else
+        {
+            r["events"]["138586341"]["name"] = "patched";
+            r["performances"][0]["start"] = 0;
+            r["venueNames"]["PLEYEL_PLEYEL"] = "Salle";
+            r["patched"] = true;
+        }
+    }
+    else if (name == "canada")
+    {
+        json& coords = r["features"][0]["geometry"]["coordinates"];
+        if (update)
+        {
+            for (auto& ring : coords)
+            {
+                ring[0] = json::array({0.5, 0.5});
+            }
+        }
+        else
+        {
+            r["features"][0]["properties"]["name"] = "patched";
+            r["type"] = "FeatureCollection2";
+            coords[0][0] = json::array({0.0, 0.0});
+        }
+    }
+    else if (name == "jeopardy")
+    {
+        if (update)
+        {
+            for (auto& q : r)
+            {
+                q["value"] = "$1";
+                q.erase("air_date");
+            }
+        }
+        else
+        {
+            r[0]["value"] = "$0";
+            r[100000]["answer"] = "patched";
+            r[216929]["round"] = "x";
+            r.push_back(json::object({{"category", "NEW"}, {"value", "$5"}}));
+        }
+    }
+    else if (name == "status")
+    {
+        r["retweet_count"] = 1;
+        r["user"]["name"] = "x";
+    }
+    else if (name == "rpc")
+    {
+        r["id"] = 4;
+        r["params"]["subtrahend"] = 24;
+    }
+    return r.dump();
+}
+
+// ---------------- yyjson ----------------
+
+static std::string edit_yyjson(const std::string& name, const std::string& s, bool update)
+{
+    yyjson_doc* idoc = yyjson_read(s.data(), s.size(), 0);
+    yyjson_mut_doc* d = yyjson_doc_mut_copy(idoc, nullptr);
+    yyjson_doc_free(idoc);
+    yyjson_mut_val* r = yyjson_mut_doc_get_root(d);
+    auto get = [](yyjson_mut_val * o, const char* k)
+    {
+        return yyjson_mut_obj_get(o, k);
+    };
+    if (name == "twitter")
+    {
+        yyjson_mut_val* sts = get(r, "statuses");
+        if (update)
+        {
+            std::size_t idx, max;
+            yyjson_mut_val* st;
+            std::int64_t i = 0;
+            yyjson_mut_arr_foreach(sts, idx, max, st)
+            {
+                yyjson_mut_set_sint(get(st, "retweet_count"), i++);
+                yyjson_mut_set_bool(get(st, "favorited"), true);
+                yyjson_mut_set_str(get(st, "text"), "redacted");
+                yyjson_mut_obj_remove_key(st, "entities");
+                yyjson_mut_obj_add_bool(d, st, "edited", true);
+            }
+        }
+        else
+        {
+            yyjson_mut_set_sint(get(get(r, "search_metadata"), "count"), 200);
+            yyjson_mut_val* s0 = yyjson_mut_arr_get(sts, 0);
+            yyjson_mut_set_str(get(s0, "text"), "patched");
+            yyjson_mut_set_sint(get(get(s0, "user"), "followers_count"), 1);
+            yyjson_mut_set_bool(get(yyjson_mut_arr_get(sts, 99), "favorited"), true);
+            yyjson_mut_obj_add_bool(d, r, "patched", true);
+        }
+    }
+    else if (name == "citm_catalog")
+    {
+        if (update)
+        {
+            std::size_t idx, max;
+            yyjson_mut_val* p;
+            yyjson_mut_arr_foreach(get(r, "performances"), idx, max, p)
+            {
+                yyjson_mut_set_str(get(p, "name"), "performance");
+                yyjson_mut_val* start = get(p, "start");
+                yyjson_mut_set_sint(start, yyjson_mut_get_sint(start) + 1);
+                yyjson_mut_obj_remove_key(p, "seatMapImage");
+                yyjson_mut_obj_add_bool(d, p, "edited", true);
+            }
+        }
+        else
+        {
+            yyjson_mut_set_str(get(get(get(r, "events"), "138586341"), "name"), "patched");
+            yyjson_mut_set_sint(get(yyjson_mut_arr_get(get(r, "performances"), 0), "start"), 0);
+            yyjson_mut_set_str(get(get(r, "venueNames"), "PLEYEL_PLEYEL"), "Salle");
+            yyjson_mut_obj_add_bool(d, r, "patched", true);
+        }
+    }
+    else if (name == "canada")
+    {
+        yyjson_mut_val* f0 = yyjson_mut_arr_get(get(r, "features"), 0);
+        yyjson_mut_val* coords = get(get(f0, "geometry"), "coordinates");
+        if (update)
+        {
+            static const double half[2] = {0.5, 0.5};
+            std::size_t idx, max;
+            yyjson_mut_val* ring;
+            yyjson_mut_arr_foreach(coords, idx, max, ring)
+            {
+                yyjson_mut_arr_replace(ring, 0, yyjson_mut_arr_with_real(d, half, 2));
+            }
+        }
+        else
+        {
+            static const double zero[2] = {0.0, 0.0};
+            yyjson_mut_set_str(get(get(f0, "properties"), "name"), "patched");
+            yyjson_mut_set_str(get(r, "type"), "FeatureCollection2");
+            yyjson_mut_arr_replace(yyjson_mut_arr_get(coords, 0), 0, yyjson_mut_arr_with_real(d, zero, 2));
+        }
+    }
+    else if (name == "jeopardy")
+    {
+        if (update)
+        {
+            std::size_t idx, max;
+            yyjson_mut_val* q;
+            yyjson_mut_arr_foreach(r, idx, max, q)
+            {
+                yyjson_mut_set_str(get(q, "value"), "$1");
+                yyjson_mut_obj_remove_key(q, "air_date");
+            }
+        }
+        else
+        {
+            yyjson_mut_set_str(get(yyjson_mut_arr_get(r, 0), "value"), "$0");
+            yyjson_mut_set_str(get(yyjson_mut_arr_get(r, 100000), "answer"), "patched");
+            yyjson_mut_set_str(get(yyjson_mut_arr_get(r, 216929), "round"), "x");
+            yyjson_mut_val* o = yyjson_mut_obj(d);
+            yyjson_mut_obj_add_str(d, o, "category", "NEW");
+            yyjson_mut_obj_add_str(d, o, "value", "$5");
+            yyjson_mut_arr_append(r, o);
+        }
+    }
+    else if (name == "status")
+    {
+        yyjson_mut_set_sint(get(r, "retweet_count"), 1);
+        yyjson_mut_set_str(get(get(r, "user"), "name"), "x");
+    }
+    else if (name == "rpc")
+    {
+        yyjson_mut_set_sint(get(r, "id"), 4);
+        yyjson_mut_set_sint(get(get(r, "params"), "subtrahend"), 24);
+    }
+    std::size_t n = 0;
+    char* out = yyjson_mut_write(d, 0, &n);
+    std::string result(out, n);
+    std::free(out);
+    yyjson_mut_doc_free(d);
+    return result;
+}
+
+#if JSON_VIEW_BENCH_BOOST
+// ---------------- Boost.JSON ----------------
+
+static std::string edit_boost(const std::string& name, const std::string& s, bool update)
+{
+    bj::monotonic_resource mr;
+    bj::parse_options opt;
+    opt.numbers = bj::number_precision::precise; // correctly rounded, like the others
+    bj::value v = bj::parse(s, &mr, opt);
+    bj::object* const obj = v.if_object(); // nullptr for jeopardy (an array)
+    if (name == "twitter")
+    {
+        bj::array& sts = (*obj)["statuses"].as_array();
+        if (update)
+        {
+            std::int64_t i = 0;
+            for (auto& e : sts)
+            {
+                bj::object& st = e.as_object();
+                st["retweet_count"] = i++;
+                st["favorited"] = true;
+                st["text"] = "redacted";
+                st.erase("entities");
+                st["edited"] = true;
+            }
+        }
+        else
+        {
+            (*obj)["search_metadata"].as_object()["count"] = 200;
+            bj::object& s0 = sts[0].as_object();
+            s0["text"] = "patched";
+            s0["user"].as_object()["followers_count"] = 1;
+            sts[99].as_object()["favorited"] = true;
+            (*obj)["patched"] = true;
+        }
+    }
+    else if (name == "citm_catalog")
+    {
+        if (update)
+        {
+            for (auto& e : (*obj)["performances"].as_array())
+            {
+                bj::object& p = e.as_object();
+                p["name"] = "performance";
+                p["start"] = p["start"].as_int64() + 1;
+                p.erase("seatMapImage");
+                p["edited"] = true;
+            }
+        }
+        else
+        {
+            (*obj)["events"].as_object()["138586341"].as_object()["name"] = "patched";
+            (*obj)["performances"].as_array()[0].as_object()["start"] = 0;
+            (*obj)["venueNames"].as_object()["PLEYEL_PLEYEL"] = "Salle";
+            (*obj)["patched"] = true;
+        }
+    }
+    else if (name == "canada")
+    {
+        bj::object& f0 = (*obj)["features"].as_array()[0].as_object();
+        bj::array& coords = f0["geometry"].as_object()["coordinates"].as_array();
+        if (update)
+        {
+            for (auto& ring : coords)
+            {
+                ring.as_array()[0] = bj::array({0.5, 0.5});
+            }
+        }
+        else
+        {
+            f0["properties"].as_object()["name"] = "patched";
+            (*obj)["type"] = "FeatureCollection2";
+            coords[0].as_array()[0] = bj::array({0.0, 0.0});
+        }
+    }
+    else if (name == "jeopardy")
+    {
+        bj::array& a = v.as_array();
+        if (update)
+        {
+            for (auto& e : a)
+            {
+                bj::object& q = e.as_object();
+                q["value"] = "$1";
+                q.erase("air_date");
+            }
+        }
+        else
+        {
+            a[0].as_object()["value"] = "$0";
+            a[100000].as_object()["answer"] = "patched";
+            a[216929].as_object()["round"] = "x";
+            a.push_back(bj::object({{"category", "NEW"}, {"value", "$5"}}));
+        }
+    }
+    else if (name == "status")
+    {
+        (*obj)["retweet_count"] = 1;
+        (*obj)["user"].as_object()["name"] = "x";
+    }
+    else if (name == "rpc")
+    {
+        (*obj)["id"] = 4;
+        (*obj)["params"].as_object()["subtrahend"] = 24;
+    }
+    return bj::serialize(v);
+}
+#endif
+
+// ---------------- harness ----------------
+
+static std::string slurp(const std::string& p)
+{
+    std::ifstream f(p, std::ios::binary);
+    if (!f)
+    {
+        std::fprintf(stderr, "cannot open %s\n", p.c_str());
+        std::exit(1);
+    }
+    std::stringstream ss;
+    ss << f.rdbuf();
+    return ss.str();
+}
+
+int main(int argc, char** argv)
+{
+    if (argc < 2)
+    {
+        std::fprintf(stderr, "usage: %s <json_test_data directory> [rounds] [document]\n", argv[0]);
+        return 1;
+    }
+    const std::string T = std::string(argv[1]) + "/";
+    // (clamped to 1 to a million)
+    const int rounds = argc > 2 ? static_cast<int>((std::min)((std::max)(std::strtol(argv[2], nullptr, 10), 1L), 1000000L)) : 20;
+    const std::string only = argc > 3 ? argv[3] : "";
+    struct doc
+    {
+        std::string name, text;
+        int batch;
+    };
+    std::vector<doc> docs;
+    for (const char* f :
+            {"nativejson-benchmark/twitter.json", "nativejson-benchmark/citm_catalog.json", "nativejson-benchmark/canada.json", "jeopardy/jeopardy.json"
+            })
+    {
+        std::string n = std::string(f).substr(std::string(f).find('/') + 1);
+        docs.push_back({n.substr(0, n.size() - 5), slurp(T + f), 1});
+    }
+    docs.push_back({"status", json::parse(docs[0].text)["statuses"][0].dump(), 200});
+    docs.push_back({"rpc", R"({"jsonrpc": "2.0", "method": "subtract", "params": {"minuend": 42, "subtrahend": 23}, "id": 3})", 5000});
+
+    using fn = std::string (*)(const std::string&, const std::string&, bool);
+    const std::vector<std::pair<std::string, fn>> engines =
+    {
+        {"json_view", edit_view}, {"yyjson", edit_yyjson},
+#if JSON_VIEW_BENCH_BOOST
+        {"Boost.JSON", edit_boost},
+#endif
+        {"json::parse", edit_json}
+    };
+
+    std::FILE* csv = std::fopen("bench_edit.csv", "w");
+    if (csv == nullptr)
+    {
+        std::perror("bench_edit.csv");
+        return 1;
+    }
+    std::fprintf(csv, "doc,bytes,workload,engine,ns\n");
+    for (const auto& dc : docs)
+    {
+        if (!only.empty() && dc.name != only)
+        {
+            continue;
+        }
+        for (const bool update :
+                {
+                    false, true
+                })
+        {
+            if (update && (dc.name == "status" || dc.name == "rpc"))
+            {
+                continue;
+            }
+            // all engines must produce the same value
+            const json expected = json::parse(edit_json(dc.name, dc.text, update));
+            bool ok = true;
+            for (const auto& e : engines)
+            {
+                ok = ok && json::parse(e.second(dc.name, dc.text, update)) == expected;
+            }
+            std::vector<double> best(engines.size(), 1e300);
+            const int r = dc.text.size() > 10000000 ? std::max(3, rounds / 4) : rounds;
+            for (int i = 0; i < r; ++i)
+            {
+                for (std::size_t k = 0; k < engines.size(); ++k)
+                {
+                    // an untimed call first: whatever the previous engine left to the allocator
+                    // (e.g. thousands of freed json nodes) is cleaned up here, not in the timing
+                    g_sink = engines[k].second(dc.name, dc.text, update).size();
+                    const auto t0 = std::chrono::steady_clock::now();
+                    for (int b = 0; b < dc.batch; ++b)
+                    {
+                        g_sink = engines[k].second(dc.name, dc.text, update).size();
+                    }
+                    const double ns = std::chrono::duration<double, std::nano>(std::chrono::steady_clock::now() - t0).count() / dc.batch;
+                    best[k] = std::min(best[k], ns);
+                }
+            }
+            const char* wl = update ? "update" : "patch";
+            std::printf("%-13s %-7s %s", dc.name.c_str(), wl, ok ? "" : "[OUTPUT MISMATCH] ");
+            for (std::size_t k = 0; k < engines.size(); ++k)
+            {
+                const double us = best[k] / 1e3;
+                std::printf("  %s %.*fus (%.2fx)", engines[k].first.c_str(), us < 10 ? 3 : (us < 1000 ? 1 : 0), us, best[k] / best[0]);
+                std::fprintf(csv, "%s,%zu,%s,%s,%.1f\n", dc.name.c_str(), dc.text.size(), wl, engines[k].first.c_str(), best[k]);
+            }
+            std::printf("\n");
+            std::fflush(stdout);
+        }
+    }
+    std::fclose(csv);
+}

tests/benchmarks/json_view/bench_view.cpp

@@ -0,0 +1,755 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  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
+
+// Same-feature-set benchmark: read-only JSON documents with random access.
+//
+//   json_view      nlohmann/json_view.hpp (fresh document per parse / reused)
+//   yyjson         yyjson_read(): immutable document, random access
+//   simdjson DOM   dom::parser (reused, as recommended; "fresh": a new parser
+//                  per parse): immutable, random access
+// references (different feature sets):
+//   simdjson OD    On-Demand: forward-only, lazy
+//   Boost.JSON     owning, mutable DOM (monotonic resource)
+//   json::parse    owning, mutable DOM (nlohmann today)
+//
+// Workloads: parse (build + free), traverse (visit everything, convert every
+// number, touch every string and key), select (a few fields per document),
+// dump (compact serialization of the parsed document).
+// All engines run interleaved in every round, each timed call after an untimed
+// one of the same engine; the best round is reported.
+#include <nlohmann/json_view.hpp>
+
+#if JSON_VIEW_BENCH_BOOST
+    #include <boost/json.hpp>
+    #include <boost/json/src.hpp>
+#endif
+#include <simdjson.h>
+#include <yyjson.h>
+
+#include <algorithm>
+#include <chrono>
+#include <cmath>
+#include <cstdio>
+#include <cstdlib>
+#include <fstream>
+#include <functional>
+#include <map>
+#include <sstream>
+
+using nlohmann::json;
+using nlohmann::json_document;
+using nlohmann::json_view;
+
+static volatile double g_sink;
+
+struct stats
+{
+    double num = 0;
+    std::size_t str = 0, nodes = 0;
+};
+
+// ---------------- traversal ----------------
+
+static void walk(json_view v, stats& st)
+{
+    ++st.nodes;
+    switch (v.type())
+    {
+        case json::value_t::object:
+            for (auto it = v.begin(); it != v.end(); ++it)
+            {
+                st.str += it.key().size();
+                walk(*it, st);
+            }
+            break;
+        case json::value_t::array:
+            for (const json_view e : v)
+            {
+                walk(e, st);
+            }
+            break;
+        case json::value_t::string:
+            st.str += v.get_string().size();
+            break;
+        case json::value_t::number_integer:
+            st.num += static_cast<double>(v.get<std::int64_t>());
+            break;
+        case json::value_t::number_unsigned:
+            st.num += static_cast<double>(v.get<std::uint64_t>());
+            break;
+        case json::value_t::number_float:
+            st.num += v.get<double>();
+            break;
+        default:
+            break;
+    }
+}
+
+static void walk(const json& j, stats& st)
+{
+    ++st.nodes;
+    switch (j.type())
+    {
+        case json::value_t::object:
+            for (const auto& kv : j.get_ref<const json::object_t&>())
+            {
+                st.str += kv.first.size();
+                walk(kv.second, st);
+            }
+            break;
+        case json::value_t::array:
+            for (const auto& e : j.get_ref<const json::array_t&>())
+            {
+                walk(e, st);
+            }
+            break;
+        case json::value_t::string:
+            st.str += j.get_ref<const std::string&>().size();
+            break;
+        case json::value_t::number_integer:
+            st.num += static_cast<double>(*j.get_ptr<const json::number_integer_t*>());
+            break;
+        case json::value_t::number_unsigned:
+            st.num += static_cast<double>(*j.get_ptr<const json::number_unsigned_t*>());
+            break;
+        case json::value_t::number_float:
+            st.num += *j.get_ptr<const json::number_float_t*>();
+            break;
+        default:
+            break;
+    }
+}
+
+static void walk(yyjson_val* v, stats& st)
+{
+    ++st.nodes;
+    switch (yyjson_get_type(v))
+    {
+        case YYJSON_TYPE_OBJ:
+        {
+            std::size_t idx, max;
+            yyjson_val* k, * val;
+            yyjson_obj_foreach(v, idx, max, k, val)
+            {
+                st.str += yyjson_get_len(k);
+                walk(val, st);
+            }
+            break;
+        }
+        case YYJSON_TYPE_ARR:
+        {
+            std::size_t idx, max;
+            yyjson_val* val;
+            yyjson_arr_foreach(v, idx, max, val)
+            {
+                walk(val, st);
+            }
+            break;
+        }
+        case YYJSON_TYPE_STR:
+            st.str += yyjson_get_len(v);
+            break;
+        case YYJSON_TYPE_NUM:
+            if (yyjson_is_sint(v))
+            {
+                st.num += static_cast<double>(yyjson_get_sint(v));
+            }
+            else if (yyjson_is_uint(v))
+            {
+                st.num += static_cast<double>(yyjson_get_uint(v));
+            }
+            else
+            {
+                st.num += yyjson_get_real(v);
+            }
+            break;
+        default:
+            break;
+    }
+}
+
+static void walk(simdjson::dom::element e, stats& st)
+{
+    ++st.nodes;
+    switch (e.type())
+    {
+        case simdjson::dom::element_type::OBJECT:
+            for (auto f : simdjson::dom::object(e))
+            {
+                st.str += f.key.size();
+                walk(f.value, st);
+            }
+            break;
+        case simdjson::dom::element_type::ARRAY:
+            for (auto c : simdjson::dom::array(e))
+            {
+                walk(c, st);
+            }
+            break;
+        case simdjson::dom::element_type::STRING:
+            st.str += std::string_view(e).size();
+            break;
+        case simdjson::dom::element_type::INT64:
+            st.num += static_cast<double>(int64_t(e));
+            break;
+        case simdjson::dom::element_type::UINT64:
+            st.num += static_cast<double>(uint64_t(e));
+            break;
+        case simdjson::dom::element_type::DOUBLE:
+            st.num += double(e);
+            break;
+        default:
+            break;
+    }
+}
+
+static void walk_od(simdjson::ondemand::value v, stats& st)
+{
+    ++st.nodes;
+    switch (v.type())
+    {
+        case simdjson::ondemand::json_type::object:
+            for (auto f : v.get_object())
+            {
+                st.str += std::string_view(f.unescaped_key()).size();
+                walk_od(f.value(), st);
+            }
+            break;
+        case simdjson::ondemand::json_type::array:
+            for (auto c : v.get_array())
+            {
+                walk_od(c.value(), st);
+            }
+            break;
+        case simdjson::ondemand::json_type::string:
+            st.str += std::string_view(v.get_string()).size();
+            break;
+        case simdjson::ondemand::json_type::number:
+        {
+            simdjson::ondemand::number n = v.get_number();
+            switch (n.get_number_type())
+            {
+                case simdjson::ondemand::number_type::signed_integer:
+                    st.num += static_cast<double>(n.get_int64());
+                    break;
+                case simdjson::ondemand::number_type::unsigned_integer:
+                    st.num += static_cast<double>(n.get_uint64());
+                    break;
+                default:
+                    st.num += n.get_double();
+                    break;
+            }
+            break;
+        }
+        case simdjson::ondemand::json_type::boolean:
+            (void)bool(v.get_bool());
+            break;
+        default:
+            (void)v.is_null();
+            break;
+    }
+}
+
+#if JSON_VIEW_BENCH_BOOST
+static void walk(const boost::json::value& v, stats& st)
+{
+    ++st.nodes;
+    switch (v.kind())
+    {
+        case boost::json::kind::object:
+            for (const auto& kv : v.get_object())
+            {
+                st.str += kv.key().size();
+                walk(kv.value(), st);
+            }
+            break;
+        case boost::json::kind::array:
+            for (const auto& c : v.get_array())
+            {
+                walk(c, st);
+            }
+            break;
+        case boost::json::kind::string:
+            st.str += v.get_string().size();
+            break;
+        case boost::json::kind::int64:
+            st.num += static_cast<double>(v.get_int64());
+            break;
+        case boost::json::kind::uint64:
+            st.num += static_cast<double>(v.get_uint64());
+            break;
+        case boost::json::kind::double_:
+            st.num += v.get_double();
+            break;
+        default:
+            break;
+    }
+}
+#endif
+
+// ---------------- selective access ----------------
+// twitter: per status id, user.screen_name, retweet_count
+// citm: per performance id, eventId, #seatCategories; #events
+// canada: type, features[0].geometry.type, #coordinates
+// jeopardy: per question: round == "Final Jeopardy!", len(category)
+// status (one tweet): id, user.screen_name, retweet_count
+// rpc: method, params.minuend, id
+
+static double pick(const std::string& name, json_view r)
+{
+    double acc = 0;
+    if (name == "twitter" || name == "status")
+    {
+        auto one = [&](json_view s)
+        {
+            acc += static_cast<double>(s["id"].get<std::uint64_t>());
+            acc += static_cast<double>(s["user"]["screen_name"].get_string().size());
+            acc += static_cast<double>(s["retweet_count"].get<std::int64_t>());
+        };
+        if (name == "twitter")
+        {
+            for (const json_view s : r["statuses"])
+            {
+                one(s);
+            }
+        }
+        else
+        {
+            one(r);
+        }
+    }
+    else if (name == "citm_catalog")
+    {
+        for (const json_view p : r["performances"])
+        {
+            acc += static_cast<double>(p["id"].get<std::uint64_t>() + p["eventId"].get<std::uint64_t>() + p["seatCategories"].size());
+        }
+        acc += static_cast<double>(r["events"].size());
+    }
+    else if (name == "canada")
+    {
+        const json_view g = r["features"][0]["geometry"];
+        acc += static_cast<double>(r["type"].get_string().size() + g["type"].get_string().size() + g["coordinates"].size());
+    }
+    else if (name == "jeopardy")
+    {
+        for (const json_view q : r)
+        {
+            acc += q["round"].get_string() == "Final Jeopardy!" ? 1 : 0;
+            acc += static_cast<double>(q["category"].get_string().size());
+        }
+    }
+    else if (name == "rpc")
+    {
+        acc += static_cast<double>(r["method"].get_string().size());
+        acc += static_cast<double>(r["params"]["minuend"].get<std::int64_t>() + r["id"].get<std::int64_t>());
+    }
+    return acc;
+}
+
+static double pick(const std::string& name, const json& r)
+{
+    double acc = 0;
+    if (name == "twitter" || name == "status")
+    {
+        auto one = [&](const json & s)
+        {
+            acc += static_cast<double>(s["id"].get<std::uint64_t>());
+            acc += static_cast<double>(s["user"]["screen_name"].get_ref<const std::string&>().size());
+            acc += static_cast<double>(s["retweet_count"].get<std::int64_t>());
+        };
+        if (name == "twitter")
+        {
+            for (const auto& s : r["statuses"])
+            {
+                one(s);
+            }
+        }
+        else
+        {
+            one(r);
+        }
+    }
+    else if (name == "citm_catalog")
+    {
+        for (const auto& p : r["performances"])
+        {
+            acc += static_cast<double>(p["id"].get<std::uint64_t>() + p["eventId"].get<std::uint64_t>() + p["seatCategories"].size());
+        }
+        acc += static_cast<double>(r["events"].size());
+    }
+    else if (name == "canada")
+    {
+        const json& g = r["features"][0]["geometry"];
+        acc += static_cast<double>(r["type"].get_ref<const std::string&>().size() + g["type"].get_ref<const std::string&>().size() + g["coordinates"].size());
+    }
+    else if (name == "jeopardy")
+    {
+        for (const auto& q : r)
+        {
+            acc += q["round"].get_ref<const std::string&>() == "Final Jeopardy!" ? 1 : 0;
+            acc += static_cast<double>(q["category"].get_ref<const std::string&>().size());
+        }
+    }
+    else if (name == "rpc")
+    {
+        acc += static_cast<double>(r["method"].get_ref<const std::string&>().size());
+        acc += static_cast<double>(r["params"]["minuend"].get<std::int64_t>() + r["id"].get<std::int64_t>());
+    }
+    return acc;
+}
+
+static double pick(const std::string& name, yyjson_val* r)
+{
+    double acc = 0;
+    auto get = [](yyjson_val * o, const char* k)
+    {
+        return yyjson_obj_get(o, k);
+    };
+    if (name == "twitter" || name == "status")
+    {
+        auto one = [&](yyjson_val * s)
+        {
+            acc += static_cast<double>(yyjson_get_uint(get(s, "id")));
+            acc += static_cast<double>(yyjson_get_len(get(get(s, "user"), "screen_name")));
+            acc += static_cast<double>(yyjson_get_sint(get(s, "retweet_count")));
+        };
+        if (name == "twitter")
+        {
+            std::size_t idx, max;
+            yyjson_val* s;
+            yyjson_arr_foreach(get(r, "statuses"), idx, max, s)
+            {
+                one(s);
+            }
+        }
+        else
+        {
+            one(r);
+        }
+    }
+    else if (name == "citm_catalog")
+    {
+        std::size_t idx, max;
+        yyjson_val* p;
+        yyjson_arr_foreach(get(r, "performances"), idx, max, p)
+        {
+            acc += static_cast<double>(yyjson_get_uint(get(p, "id")) + yyjson_get_uint(get(p, "eventId")) + yyjson_arr_size(get(p, "seatCategories")));
+        }
+        acc += static_cast<double>(yyjson_obj_size(get(r, "events")));
+    }
+    else if (name == "canada")
+    {
+        yyjson_val* g = get(yyjson_arr_get(get(r, "features"), 0), "geometry");
+        acc += static_cast<double>(yyjson_get_len(get(r, "type")) + yyjson_get_len(get(g, "type")) + yyjson_arr_size(get(g, "coordinates")));
+    }
+    else if (name == "jeopardy")
+    {
+        std::size_t idx, max;
+        yyjson_val* q;
+        yyjson_arr_foreach(r, idx, max, q)
+        {
+            acc += yyjson_equals_str(get(q, "round"), "Final Jeopardy!") ? 1 : 0;
+            acc += static_cast<double>(yyjson_get_len(get(q, "category")));
+        }
+    }
+    else if (name == "rpc")
+    {
+        acc += static_cast<double>(yyjson_get_len(get(r, "method")));
+        acc += static_cast<double>(yyjson_get_sint(get(get(r, "params"), "minuend")) + yyjson_get_sint(get(r, "id")));
+    }
+    return acc;
+}
+
+static double pick(const std::string& name, simdjson::dom::element r)
+{
+    double acc = 0;
+    if (name == "twitter" || name == "status")
+    {
+        auto one = [&](simdjson::dom::element s)
+        {
+            acc += static_cast<double>(uint64_t(s["id"]));
+            acc += static_cast<double>(std::string_view(s["user"]["screen_name"]).size());
+            acc += static_cast<double>(int64_t(s["retweet_count"]));
+        };
+        if (name == "twitter")
+        {
+            for (auto s : simdjson::dom::array(r["statuses"]))
+            {
+                one(s);
+            }
+        }
+        else
+        {
+            one(r);
+        }
+    }
+    else if (name == "citm_catalog")
+    {
+        for (auto p : simdjson::dom::array(r["performances"]))
+        {
+            acc += static_cast<double>(uint64_t(p["id"]) + uint64_t(p["eventId"]) + simdjson::dom::array(p["seatCategories"]).size());
+        }
+        acc += static_cast<double>(simdjson::dom::object(r["events"]).size());
+    }
+    else if (name == "canada")
+    {
+        auto g = r["features"].at(0)["geometry"];
+        acc += static_cast<double>(std::string_view(r["type"]).size() + std::string_view(g["type"]).size() + simdjson::dom::array(g["coordinates"]).size());
+    }
+    else if (name == "jeopardy")
+    {
+        for (auto q : simdjson::dom::array(r))
+        {
+            acc += std::string_view(q["round"]) == "Final Jeopardy!" ? 1 : 0;
+            acc += static_cast<double>(std::string_view(q["category"]).size());
+        }
+    }
+    else if (name == "rpc")
+    {
+        acc += static_cast<double>(std::string_view(r["method"]).size());
+        acc += static_cast<double>(int64_t(r["params"]["minuend"]) + int64_t(r["id"]));
+    }
+    return acc;
+}
+
+static double pick_od(const std::string& name, simdjson::ondemand::document& d)
+{
+    double acc = 0;
+    if (name == "twitter" || name == "status")
+    {
+        auto one = [&](simdjson::ondemand::object s)
+        {
+            acc += static_cast<double>(uint64_t(s["id"]));
+            acc += static_cast<double>(std::string_view(s["user"]["screen_name"]).size());
+            acc += static_cast<double>(int64_t(s["retweet_count"]));
+        };
+        if (name == "twitter")
+        {
+            for (auto s : d["statuses"])
+            {
+                one(s.get_object());
+            }
+        }
+        else
+        {
+            one(d.get_object());
+        }
+    }
+    else if (name == "citm_catalog")
+    {
+        simdjson::ondemand::object ev = d["events"].get_object();
+        acc += static_cast<double>(ev.count_fields());
+        for (auto p : d["performances"])
+        {
+            simdjson::ondemand::object o = p.get_object();
+            const auto a = uint64_t(o["eventId"]) + uint64_t(o["id"]);
+            simdjson::ondemand::array sc = o["seatCategories"].get_array();
+            acc += static_cast<double>(a + sc.count_elements());
+        }
+    }
+    else if (name == "canada")
+    {
+        acc += static_cast<double>(std::string_view(d["type"]).size());
+        auto g = d["features"].at(0)["geometry"];
+        acc += static_cast<double>(std::string_view(g["type"]).size());
+        simdjson::ondemand::array co = g["coordinates"].get_array();
+        acc += static_cast<double>(co.count_elements());
+    }
+    else if (name == "jeopardy")
+    {
+        for (auto q : d)
+        {
+            simdjson::ondemand::object o = q.get_object();
+            acc += static_cast<double>(std::string_view(o["category"]).size());
+            acc += std::string_view(o["round"]) == "Final Jeopardy!" ? 1 : 0;
+        }
+    }
+    else if (name == "rpc")
+    {
+        acc += static_cast<double>(std::string_view(d["method"]).size());
+        acc += static_cast<double>(int64_t(d["params"]["minuend"]));
+        acc += static_cast<double>(int64_t(d["id"]));
+    }
+    return acc;
+}
+
+// ---------------- harness ----------------
+
+static std::string slurp(const std::string& p)
+{
+    std::ifstream f(p, std::ios::binary);
+    if (!f)
+    {
+        std::fprintf(stderr, "cannot open %s\n", p.c_str());
+        std::exit(1);
+    }
+    std::stringstream ss;
+    ss << f.rdbuf();
+    return ss.str();
+}
+
+struct engine
+{
+    std::string name;
+    std::function<void()> fn;
+};
+
+int main(int argc, char** argv)
+{
+    if (argc < 2)
+    {
+        std::fprintf(stderr, "usage: %s <json_test_data directory> [rounds] [document]\n", argv[0]);
+        return 1;
+    }
+    const std::string T = std::string(argv[1]) + "/";
+    // (clamped to 1 to a million)
+    const int rounds = argc > 2 ? static_cast<int>((std::min)((std::max)(std::strtol(argv[2], nullptr, 10), 1L), 1000000L)) : 30;
+    const std::string only = argc > 3 ? argv[3] : "";
+    struct doc
+    {
+        std::string name, text;
+        int batch;
+    };
+    std::vector<doc> docs;
+    for (const char* f :
+            {"nativejson-benchmark/twitter.json", "nativejson-benchmark/citm_catalog.json", "nativejson-benchmark/canada.json", "jeopardy/jeopardy.json"
+            })
+    {
+        std::string n = std::string(f).substr(std::string(f).find('/') + 1);
+        docs.push_back({n.substr(0, n.size() - 5), slurp(T + f), 1});
+    }
+    docs.push_back({"status", json::parse(docs[0].text)["statuses"][0].dump(), 200});
+    docs.push_back({"rpc", R"({"jsonrpc": "2.0", "method": "subtract", "params": {"minuend": 42, "subtrahend": 23}, "id": 3})", 5000});
+
+    // correctness cross-check of the workloads
+    for (const auto& dc : docs)
+    {
+        stats a, b, c, dd;
+        walk(json::parse(dc.text), a);
+        auto d = json_document::parse(dc.text);
+        walk(d.root(), b);
+        yyjson_doc* y = yyjson_read(dc.text.data(), dc.text.size(), 0);
+        walk(yyjson_doc_get_root(y), c);
+        simdjson::dom::parser p;
+        walk(p.parse(dc.text).value(), dd);
+        const bool ok = a.nodes == b.nodes && a.nodes == c.nodes && a.nodes == dd.nodes && a.str == b.str && a.str == c.str && a.str == dd.str
+                        && std::fabs(a.num - b.num) <= 1e-9 * std::fabs(a.num) && std::fabs(a.num - c.num) <= 1e-9 * std::fabs(a.num);
+        const double pa = pick(dc.name, json::parse(dc.text)), pb = pick(dc.name, d.root()), pc = pick(dc.name, yyjson_doc_get_root(y)), pd = pick(dc.name, p.parse(dc.text).value());
+        std::printf("check %-13s traverse %s select %s\n", dc.name.c_str(), ok ? "OK" : "MISMATCH", (pa == pb && pa == pc && pa == pd) ? "OK" : "MISMATCH");
+        yyjson_doc_free(y);
+    }
+
+    std::FILE* csv = std::fopen("bench_view.csv", "w");
+    if (csv == nullptr)
+    {
+        std::perror("bench_view.csv");
+        return 1;
+    }
+    std::fprintf(csv, "doc,bytes,workload,engine,ns\n");
+    json_document reused;
+    simdjson::dom::parser sj;
+    simdjson::ondemand::parser od;
+    for (const auto& dc : docs)
+    {
+        if (!only.empty() && dc.name != only)
+        {
+            continue;
+        }
+        const std::string& s = dc.text;
+        const simdjson::padded_string ps(s);
+        const std::string name = dc.name;
+        std::vector<std::pair<std::string, std::vector<engine>>> workloads;
+
+        workloads.push_back({"parse", {
+                {"json_view", [&] { auto d = json_document::parse(s); g_sink = static_cast<double>(d.node_count()); }},
+                {"json_view (reused)", [&] { reused.read(s); g_sink = static_cast<double>(reused.node_count()); }},
+                {"yyjson", [&] { yyjson_doc* d = yyjson_read(s.data(), s.size(), 0); g_sink = static_cast<double>(yyjson_doc_get_val_count(d)); yyjson_doc_free(d); }},
+                {"simdjson DOM", [&] { auto e = sj.parse(ps).value_unsafe(); g_sink = e.is_object(); }},
+                {"simdjson DOM (fresh)", [&] { simdjson::dom::parser p; auto e = p.parse(ps).value_unsafe(); g_sink = e.is_object(); }},
+#if JSON_VIEW_BENCH_BOOST
+                {"Boost.JSON", [&] { boost::json::monotonic_resource mr; auto v = boost::json::parse(s, &mr); g_sink = v.is_object(); }},
+#endif
+                {"json::parse", [&] { json j = json::parse(s); g_sink = static_cast<double>(j.size()); }},
+            }});
+        workloads.push_back({"traverse", {
+                {"json_view", [&] { auto d = json_document::parse(s); stats st; walk(d.root(), st); g_sink = st.num; }},
+                {"json_view (reused)", [&] { reused.read(s); stats st; walk(reused.root(), st); g_sink = st.num; }},
+                {"yyjson", [&] { yyjson_doc* d = yyjson_read(s.data(), s.size(), 0); stats st; walk(yyjson_doc_get_root(d), st); g_sink = st.num; yyjson_doc_free(d); }},
+                {"simdjson DOM", [&] { stats st; walk(sj.parse(ps).value_unsafe(), st); g_sink = st.num; }},
+                {"simdjson OD", [&] { auto d = od.iterate(ps).value_unsafe(); stats st; walk_od(d.get_value().value_unsafe(), st); g_sink = st.num; }},
+#if JSON_VIEW_BENCH_BOOST
+                {"Boost.JSON", [&] { boost::json::monotonic_resource mr; auto v = boost::json::parse(s, &mr); stats st; walk(v, st); g_sink = st.num; }},
+#endif
+                {"json::parse", [&] { json j = json::parse(s); stats st; walk(j, st); g_sink = st.num; }},
+            }});
+        workloads.push_back({"select", {
+                {"json_view", [&] { auto d = json_document::parse(s); g_sink = pick(name, d.root()); }},
+                {"json_view (reused)", [&] { reused.read(s); g_sink = pick(name, reused.root()); }},
+                {"yyjson", [&] { yyjson_doc* d = yyjson_read(s.data(), s.size(), 0); g_sink = pick(name, yyjson_doc_get_root(d)); yyjson_doc_free(d); }},
+                {"simdjson DOM", [&] { g_sink = pick(name, sj.parse(ps).value_unsafe()); }},
+                {"simdjson OD", [&] { auto d = od.iterate(ps).value_unsafe(); g_sink = pick_od(name, d); }},
+                {"json::parse", [&] { json j = json::parse(s); g_sink = pick(name, j); }},
+            }});
+        {
+            // serialization of an already parsed document
+            static json_document vd;
+            vd.read(s);
+            static yyjson_doc* yd = nullptr;
+            if (yd)
+            {
+                yyjson_doc_free(yd);
+            }
+            yd = yyjson_read(s.data(), s.size(), 0);
+            static simdjson::dom::parser sjd;
+            static simdjson::dom::element se;
+            se = sjd.parse(ps).value_unsafe();
+            static json jd;
+            jd = json::parse(s);
+            workloads.push_back({"dump", {
+                    {"json_view", [&] { std::string o = vd.root().dump(); g_sink = static_cast<double>(o.size()); }},
+                    {"yyjson", [&] { std::size_t n = 0; char* o = yyjson_write(yd, 0, &n); g_sink = static_cast<double>(n); std::free(o); }},
+                    {"simdjson DOM", [&] { std::string o = simdjson::to_string(se); g_sink = static_cast<double>(o.size()); }},
+                    {"json::parse", [&] { std::string o = jd.dump(); g_sink = static_cast<double>(o.size()); }},
+                }});
+        }
+
+        for (auto& wl : workloads)
+        {
+            std::vector<double> best(wl.second.size(), 1e300);
+            const int r = s.size() > 10000000 ? std::max(3, rounds / 5) : rounds;
+            for (int i = 0; i < r; ++i)
+            {
+                for (std::size_t k = 0; k < wl.second.size(); ++k)
+                {
+                    // an untimed call first: whatever the previous engine left to the allocator
+                    // (e.g. thousands of freed json nodes) is cleaned up here, not in the timing
+                    wl.second[k].fn();
+                    const auto t0 = std::chrono::steady_clock::now();
+                    for (int b = 0; b < dc.batch; ++b)
+                    {
+                        wl.second[k].fn();
+                    }
+                    const double ns = std::chrono::duration<double, std::nano>(std::chrono::steady_clock::now() - t0).count() / dc.batch;
+                    best[k] = std::min(best[k], ns);
+                }
+            }
+            const double ref = best[0];
+            std::printf("%-13s %-9s", dc.name.c_str(), wl.first.c_str());
+            for (std::size_t k = 0; k < wl.second.size(); ++k)
+            {
+                const double us = best[k] / 1e3;
+                std::printf("  %s %s%s (%.2fx)", wl.second[k].name.c_str(), us >= 100 ? "" : "", (us >= 1000 ? std::to_string(static_cast<long>(us)) + "us" : (std::to_string(us).substr(0, 5) + "us")).c_str(), best[k] / ref);
+                std::fprintf(csv, "%s,%zu,%s,%s,%.1f\n", dc.name.c_str(), s.size(), wl.first.c_str(), wl.second[k].name.c_str(), best[k]);
+            }
+            std::printf("\n");
+            std::fflush(stdout);
+        }
+    }
+    std::fclose(csv);
+}

tests/benchmarks/json_view/compare.py

@@ -0,0 +1,342 @@
+#!/usr/bin/env python3
+#     __ _____ _____ _____
+#  __|  |   __|     |   | |  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
+
+"""Compare json_view with yyjson, simdjson, Boost.JSON, and json::parse.
+
+Builds bench_view.cpp, bench_corpus.cpp, and bench_edit.cpp against the include/ directory of
+this checkout, runs them, and writes the results with everything needed to
+reproduce them (date, commit, CPU, OS, compiler, library versions, flags) to
+results/<date>-<host>.md and .csv next to this script.
+
+The other libraries come from the system (--system, the default: pkg-config
+or Homebrew) or are downloaded as pinned releases and checked against their
+SHA-256 (--download). Boost.JSON is optional: without Boost headers, its
+columns are skipped, and the results say so.
+
+Only the Python 3 standard library is used; a C++17 compiler is needed.
+"""
+
+import argparse
+import datetime
+import hashlib
+import os
+import platform
+import re
+import shlex
+import shutil
+# runs only the compilers and benchmark binaries this script builds
+import subprocess  # nosec B404
+import sys
+import tarfile
+import tempfile
+import urllib.request
+
+HERE = os.path.dirname(os.path.abspath(__file__))
+REPO = os.path.abspath(os.path.join(HERE, '..', '..', '..'))
+
+# seconds without data after which a download fails
+DOWNLOAD_TIMEOUT = 60
+
+# pinned releases for --download; the hashes are those of the archives
+#
+# The yyjson and simdjson archives are the tag archives GitHub generates
+# (archive/refs/tags/...), whose bytes GitHub does not guarantee to be stable. A SHA-256
+# mismatch for one of them means that GitHub regenerated the archive: check the upstream
+# tag, then pin the new hash.
+PINNED = {
+    'yyjson': {
+        'version': '0.13.0',
+        'url': 'https://github.com/ibireme/yyjson/archive/refs/tags/0.13.0.tar.gz',
+        'sha256': '34e0f62a2bc11ab20d601e8ca1cc2b2079503aa45119a19133d89d19b94a0fae',
+        'dir': 'yyjson-0.13.0',
+    },
+    'simdjson': {
+        'version': '4.6.11',
+        'url': 'https://github.com/simdjson/simdjson/archive/refs/tags/v4.6.11.tar.gz',
+        'sha256': '61d948fc24f0d793829ad658058e7597d064988a89b4607ea02e401a82df98ff',
+        'dir': 'simdjson-4.6.11',
+    },
+    'boost': {
+        'version': '1.92.0',
+        'url': 'https://archives.boost.io/release/1.92.0/source/boost_1_92_0.tar.gz',
+        'sha256': 'c4a3b310ddd2472416e091067166b0713be97c63f38c212c484ada022fd296ce',
+        'dir': 'boost_1_92_0',
+    },
+}
+
+# the documents of bench_view.cpp, relative to the json_test_data directory
+DEFAULT_CORPUS = [
+    'nativejson-benchmark/twitter.json',
+    'nativejson-benchmark/citm_catalog.json',
+    'nativejson-benchmark/canada.json',
+    'jeopardy/jeopardy.json',
+]
+
+
+def run(cmd, **kwargs):
+    print('+ ' + ' '.join(shlex.quote(c) for c in cmd), flush=True)
+    # cmd is an argument list built by this script, never a shell string
+    return subprocess.run(cmd, check=True, **kwargs)  # nosec B603
+
+
+def output(cmd):
+    try:
+        # cmd is an argument list built by this script, never a shell string
+        return subprocess.run(cmd, check=True, capture_output=True, text=True).stdout.strip()  # nosec B603
+    except (OSError, subprocess.CalledProcessError):
+        return ''
+
+
+# ---------------------------------------------------------------------------
+# libraries
+# ---------------------------------------------------------------------------
+
+class Library:
+    """include directories, sources to compile, and linker flags of a library"""
+
+    def __init__(self, name, include=None, sources=None, link=None, version=''):
+        self.name = name
+        self.include = include or []
+        self.sources = sources or []
+        self.link = link or []
+        self.version = version
+
+
+def header_version(path, pattern):
+    try:
+        with open(path, encoding='utf-8', errors='replace') as f:
+            m = re.search(pattern, f.read())
+        return m.group(1) if m else ''
+    except OSError:
+        return ''
+
+
+def library_version(name, include_dirs):
+    patterns = {
+        'yyjson': ('yyjson.h', r'#define\s+YYJSON_VERSION_STRING\s+"([^"]+)"'),
+        'simdjson': ('simdjson.h', r'#define\s+SIMDJSON_VERSION\s+"?([0-9.]+)"?'),
+        'boost': (os.path.join('boost', 'version.hpp'), r'#define\s+BOOST_LIB_VERSION\s+"([^"]+)"'),
+    }
+    header, pattern = patterns[name]
+    for d in include_dirs:
+        v = header_version(os.path.join(d, header), pattern)
+        if v:
+            return v.replace('_', '.')
+    return ''
+
+
+def system_library(name):
+    """a library found with pkg-config or Homebrew, or None"""
+    flags = output(['pkg-config', '--cflags', '--libs', name]).split()
+    if flags:
+        include = [f[2:] for f in flags if f.startswith('-I')]
+        link = [f for f in flags if f.startswith('-L') or f.startswith('-l')]
+        libdirs = [f[2:] for f in link if f.startswith('-L')]
+        link += ['-Wl,-rpath,' + d for d in libdirs]
+        return Library(name, include, [], link, library_version(name, include))
+    prefix = output(['brew', '--prefix', name]) if shutil.which('brew') else ''
+    if prefix and os.path.isdir(os.path.join(prefix, 'include')):
+        include = [os.path.join(prefix, 'include')]
+        link = []
+        if name != 'boost':
+            lib = os.path.join(prefix, 'lib')
+            link = ['-L' + lib, '-l' + name, '-Wl,-rpath,' + lib]
+        return Library(name, include, [], link, library_version(name, include))
+    if name == 'boost':
+        for d in ['/usr/include', '/usr/local/include']:
+            if os.path.isfile(os.path.join(d, 'boost', 'json.hpp')):
+                return Library(name, [d], [], [], library_version(name, [d]))
+    return None
+
+
+def sha256_file(path):
+    """SHA-256 of a file, read in chunks (the Boost archive is more than 100 MB)"""
+    h = hashlib.sha256()
+    with open(path, 'rb') as f:
+        for chunk in iter(lambda: f.read(1 << 20), b''):
+            h.update(chunk)
+    return h.hexdigest()
+
+
+def download_library(name, work):
+    """a pinned release, downloaded and checked, or an error"""
+    pin = PINNED[name]
+    archive = os.path.join(work, 'download', os.path.basename(pin['url']))
+    os.makedirs(os.path.dirname(archive), exist_ok=True)
+    if not os.path.isfile(archive):
+        print(f'downloading {pin["url"]}', flush=True)
+        # the URLs are the https constants in PINNED, and the SHA-256 is checked below
+        # (into a .part file first, so that an interrupted download is not kept)
+        with urllib.request.urlopen(pin['url'], timeout=DOWNLOAD_TIMEOUT) as response:  # nosec B310
+            with open(archive + '.part', 'wb') as f:
+                shutil.copyfileobj(response, f)
+        os.replace(archive + '.part', archive)
+    digest = sha256_file(archive)
+    if digest != pin['sha256']:
+        os.remove(archive)  # downloaded again by the next run
+        sys.exit(f'error: SHA-256 of {archive} is {digest}, expected {pin["sha256"]} (removed)')
+    src = os.path.join(work, 'download', pin['dir'])
+    if not os.path.isdir(src):
+        # extracted into a temporary directory first, so that an interrupted extraction
+        # is not mistaken for a complete one
+        tmp = tempfile.mkdtemp(prefix=pin['dir'] + '.part-', dir=os.path.join(work, 'download'))
+        try:
+            with tarfile.open(archive) as t:
+                # (the 'data' filter rejects links and paths outside the target where Python has it)
+                kwargs = {'filter': 'data'} if hasattr(tarfile, 'data_filter') else {}
+                t.extractall(tmp, **kwargs)  # noqa: S202 (checked archive)  # nosec B202
+            os.rename(os.path.join(tmp, pin['dir']), src)
+        finally:
+            shutil.rmtree(tmp, ignore_errors=True)
+    if name == 'yyjson':
+        return Library(name, [os.path.join(src, 'src')], [os.path.join(src, 'src', 'yyjson.c')], [], pin['version'])
+    if name == 'simdjson':
+        single = os.path.join(src, 'singleheader')
+        return Library(name, [single], [os.path.join(single, 'simdjson.cpp')], [], pin['version'])
+    return Library(name, [src], [], [], pin['version'])
+
+
+# ---------------------------------------------------------------------------
+# machine description
+# ---------------------------------------------------------------------------
+
+def cpu_model():
+    if sys.platform == 'darwin':
+        return output(['sysctl', '-n', 'machdep.cpu.brand_string'])
+    try:
+        with open('/proc/cpuinfo', encoding='utf-8') as f:
+            for line in f:
+                if line.startswith('model name') or line.startswith('Model'):
+                    return line.split(':', 1)[1].strip()
+    except OSError:
+        pass
+    # (AArch64 Linux: /proc/cpuinfo has no model name, lscpu knows it)
+    for line in output(['lscpu']).splitlines():
+        if line.startswith('Model name:'):
+            return line.split(':', 1)[1].strip()
+    return platform.processor() or platform.machine()
+
+
+def git_commit():
+    commit = output(['git', '-C', REPO, 'rev-parse', '--short=12', 'HEAD'])
+    dirty = output(['git', '-C', REPO, 'status', '--porcelain', '--untracked-files=no'])
+    return commit + (' (with local changes)' if dirty else '')
+
+
+# ---------------------------------------------------------------------------
+# main
+# ---------------------------------------------------------------------------
+
+def main():
+    ap = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
+    ap.add_argument('--data', required=True, help='json_test_data directory (with nativejson-benchmark/ and jeopardy/)')
+    ap.add_argument('--download', action='store_true', help='use pinned downloads instead of system libraries')
+    ap.add_argument('--no-boost', action='store_true', help='skip Boost.JSON')
+    ap.add_argument('--native', action='store_true', help='compile for this CPU (-march=native / -mcpu=native)')
+    ap.add_argument('--rounds', type=int, default=30, help='rounds of bench_view (default: 30)')
+    ap.add_argument('--corpus', nargs='*', default=[], help='more files for bench_corpus')
+    ap.add_argument('--build-dir', default=os.path.join(HERE, 'build'), help='where to build (default: build/ next to this script)')
+    args = ap.parse_args()
+    # the benchmarks run in the build directory: make the paths absolute
+    args.data = os.path.abspath(args.data)
+    args.corpus = [os.path.abspath(f) for f in args.corpus]
+    args.build_dir = os.path.abspath(args.build_dir)
+
+    # (CXX and CC may contain arguments, e.g. 'ccache g++')
+    cxx = shlex.split(os.environ.get('CXX', 'c++'))
+    cc = shlex.split(os.environ.get('CC', 'cc'))
+    os.makedirs(args.build_dir, exist_ok=True)
+
+    libs = {}
+    for name in ['yyjson', 'simdjson', 'boost']:
+        if name == 'boost' and args.no_boost:
+            continue
+        lib = download_library(name, args.build_dir) if args.download else system_library(name)
+        if lib is None and name != 'boost':
+            sys.exit(f'error: {name} not found; install it, or use --download')
+        if lib is not None:
+            libs[name] = lib
+    with_boost = 'boost' in libs
+    if not with_boost:
+        print('Boost.JSON not found: its columns are skipped', flush=True)
+
+    flags = ['-std=c++17', '-O3', '-DNDEBUG', f'-DJSON_VIEW_BENCH_BOOST={1 if with_boost else 0}']
+    if args.native:
+        flags.append('-mcpu=native' if platform.machine().lower() in ('arm64', 'aarch64') else '-march=native')
+    include = ['-I' + os.path.join(REPO, 'include')] + ['-I' + d for lib in libs.values() for d in lib.include]
+    link = [f for lib in libs.values() for f in lib.link]
+
+    # C sources of downloaded libraries are compiled once
+    objects = []
+    for lib in libs.values():
+        for src in lib.sources:
+            obj = os.path.join(args.build_dir, os.path.basename(src) + '.o')
+            is_c = src.endswith('.c')
+            run((cc if is_c else cxx) + ([] if is_c else ['-std=c++17']) + ['-O3', '-DNDEBUG', '-c', src, '-o', obj]
+                + ['-I' + d for d in lib.include])
+            objects.append(obj)
+
+    binaries = {}
+    for bench in ['bench_view', 'bench_corpus', 'bench_edit']:
+        exe = os.path.join(args.build_dir, bench)
+        run(cxx + flags + include + [os.path.join(HERE, bench + '.cpp')] + objects + link + ['-o', exe])
+        binaries[bench] = exe
+
+    # run: bench_view on its documents, bench_corpus on those and the given files
+    corpus = [os.path.join(args.data, f) for f in DEFAULT_CORPUS] + args.corpus
+    outputs = {}
+    outputs['bench_view'] = run([binaries['bench_view'], args.data, str(args.rounds)], cwd=args.build_dir,
+                                capture_output=True, text=True).stdout
+    outputs['bench_corpus'] = run([binaries['bench_corpus']] + corpus, cwd=args.build_dir,
+                                  capture_output=True, text=True).stdout
+    outputs['bench_edit'] = run([binaries['bench_edit'], args.data, str(max(1, args.rounds // 2))], cwd=args.build_dir,
+                                capture_output=True, text=True).stdout
+    for name, text in outputs.items():
+        print(text)
+
+    # results with their metadata
+    now = datetime.datetime.now()
+    host = re.sub(r'[^A-Za-z0-9-]+', '-', platform.node().split('.')[0]) or 'host'
+    stem = os.path.join(HERE, 'results', f'{now:%Y-%m-%d}-{host}')
+    os.makedirs(os.path.dirname(stem), exist_ok=True)
+    cxx_version = output(cxx + ['--version'])
+    compiler_version = cxx_version.splitlines()[0] if cxx_version else ' '.join(cxx)
+    meta = [
+        ('date', f'{now:%Y-%m-%d %H:%M}'),
+        ('commit', git_commit()),
+        ('CPU', cpu_model()),
+        ('OS', f'{platform.system()} {platform.release()} ({platform.machine()})'),
+        ('compiler', compiler_version),
+        ('flags', ' '.join(flags)),
+        ('yyjson', libs['yyjson'].version),
+        ('simdjson', libs['simdjson'].version),
+        ('Boost.JSON', libs['boost'].version if with_boost else 'skipped (not found)'),
+        ('libraries from', 'pinned downloads' if args.download else 'the system'),
+        ('rounds', str(args.rounds)),
+    ]
+    with open(stem + '.md', 'w', encoding='utf-8') as f:
+        f.write(f'# json_view comparison, {now:%Y-%m-%d}\n\n')
+        f.write('Generated by `tests/benchmarks/json_view/compare.py`; best of the interleaved rounds.\n\n')
+        f.write('| | |\n|---|---|\n')
+        for key, value in meta:
+            f.write(f'| {key} | {value} |\n')
+        for name, text in outputs.items():
+            f.write(f'\n## {name}\n\n```\n{text.rstrip()}\n```\n')
+    with open(stem + '.csv', 'w', encoding='utf-8') as out:
+        out.write(''.join(f'# {key}: {value}\n' for key, value in meta))
+        for name in ['bench_view', 'bench_corpus', 'bench_edit']:
+            path = os.path.join(args.build_dir, name + '.csv')
+            if os.path.isfile(path):
+                with open(path, encoding='utf-8') as f:
+                    out.write(f'# {name}\n' + f.read())
+    print(f'results: {stem}.md, {stem}.csv')
+
+
+if __name__ == '__main__':
+    main()

tests/benchmarks/src/benchmarks.cpp

@@ -9,12 +9,15 @@
 #include <benchmark/benchmark.h>
 #include <nlohmann/json.hpp>
 #include <array>
+#include <cstdint>
 #include <cstdio>
 #include <deque>
 #include <fstream>
+#include <map>
 #include <numeric>
 #include <set>
 #include <sstream>
+#include <string>
 #include <vector>
 #include <test_data.hpp>
 
@@ -710,6 +713,584 @@ static void FromCborChunkedString(benchmark::State& state, const std::size_t chu
 
 BENCHMARK_CAPTURE(FromCborChunkedString, 10000 chunks, 10000);
 
+//////////////////////////////////////////////////////////////////////////////
+// SAX-parse JSON from string
+//
+// sax_parse() with a handler that does next to nothing runs the lexer and
+// parser without building values, so the gap to ParseString above is the cost
+// of building the DOM.
+//////////////////////////////////////////////////////////////////////////////
+
+static std::string read_file(const char* filename)
+{
+    std::ifstream f(filename);
+    return std::string((std::istreambuf_iterator<char>(f)), std::istreambuf_iterator<char>());
+}
+
+static json load_json(const char* filename)
+{
+    return json::parse(read_file(filename));
+}
+
+/// SAX handler that only counts the events, so that the handler costs next to nothing
+class counting_sax : public nlohmann::json_sax<json>
+{
+  public:
+    std::size_t events = 0;
+
+    bool null() override
+    {
+        return count();
+    }
+    bool boolean(bool /*val*/) override
+    {
+        return count();
+    }
+    bool number_integer(number_integer_t /*val*/) override
+    {
+        return count();
+    }
+    bool number_unsigned(number_unsigned_t /*val*/) override
+    {
+        return count();
+    }
+    bool number_float(number_float_t /*val*/, const string_t& /*s*/) override
+    {
+        return count();
+    }
+    bool string(string_t& /*val*/) override
+    {
+        return count();
+    }
+    bool binary(binary_t& /*val*/) override
+    {
+        return count();
+    }
+    bool start_object(std::size_t /*elements*/) override
+    {
+        return count();
+    }
+    bool key(string_t& /*val*/) override
+    {
+        return count();
+    }
+    bool end_object() override
+    {
+        return count();
+    }
+    bool start_array(std::size_t /*elements*/) override
+    {
+        return count();
+    }
+    bool end_array() override
+    {
+        return count();
+    }
+    bool parse_error(std::size_t /*position*/, const std::string& /*last_token*/, const json::exception& /*ex*/) override
+    {
+        return false;
+    }
+
+  private:
+    bool count()
+    {
+        ++events;
+        return true;
+    }
+};
+
+static void SaxParse(benchmark::State& state, const char* filename)
+{
+    const std::string str = read_file(filename);
+
+    for (auto _ : state)
+    {
+        counting_sax sax;
+        bool result = json::sax_parse(str, &sax);
+        benchmark::DoNotOptimize(result);
+        benchmark::DoNotOptimize(sax.events);
+    }
+
+    state.SetBytesProcessed(state.iterations() * str.size());
+}
+BENCHMARK_CAPTURE(SaxParse, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(SaxParse, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(SaxParse, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+//////////////////////////////////////////////////////////////////////////////
+// work with values: copy, destroy, compare, iterate
+//
+// The parsed test files stand in for a document an application keeps around.
+// Each benchmark times one whole-document operation; setup and cleanup run
+// outside the timed section.
+//
+// A copy is always destroyed again, and how a document is freed shapes the
+// heap the next copy allocates from: a destructor that frees quickly can leave
+// work to the allocator's next calls. Copy, CopyAssign and CopyRing therefore
+// time the copy together with the destruction of a copy; CopyOnly and
+// DestroyOnly time one half each and are meant for telling the halves apart,
+// not for comparing versions.
+//////////////////////////////////////////////////////////////////////////////
+
+/// copy a document and destroy the copy again, as a temporary copy is used
+static void Copy(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+
+    for (auto _ : state)
+    {
+        json copy = j;
+        benchmark::DoNotOptimize(copy);
+    }
+}
+BENCHMARK_CAPTURE(Copy, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(Copy, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(Copy, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+/// copy-assign a document over an earlier copy of it, which is freed in the process
+static void CopyAssign(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+    json target = j;
+
+    for (auto _ : state)
+    {
+        target = j;
+        benchmark::DoNotOptimize(target);
+    }
+}
+BENCHMARK_CAPTURE(CopyAssign, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(CopyAssign, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(CopyAssign, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+/// keep eight copies alive and replace the oldest one, as a cache or an undo
+/// history does, so that the copy is not made from memory just freed by an
+/// identical document
+static void CopyRing(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+    std::vector<json> ring(8, j);
+    std::size_t oldest = 0;
+
+    for (auto _ : state)
+    {
+        ring[oldest] = j;
+        benchmark::DoNotOptimize(ring[oldest]);
+        oldest = (oldest + 1) % ring.size();
+    }
+}
+BENCHMARK_CAPTURE(CopyRing, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(CopyRing, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(CopyRing, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+/// only the copy; the copy is destroyed with the timer paused (diagnostic)
+static void CopyOnly(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+
+    for (auto _ : state)
+    {
+        auto* copy = new json(j);
+
+        state.PauseTiming();
+        delete copy;
+        state.ResumeTiming();
+    }
+}
+BENCHMARK_CAPTURE(CopyOnly, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(CopyOnly, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(CopyOnly, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+/// only the destruction; the copy is made with the timer paused (diagnostic)
+static void DestroyOnly(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+
+    for (auto _ : state)
+    {
+        state.PauseTiming();
+        auto* copy = new json(j);
+        state.ResumeTiming();
+
+        delete copy;
+    }
+}
+BENCHMARK_CAPTURE(DestroyOnly, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(DestroyOnly, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(DestroyOnly, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+static void Equal(benchmark::State& state, const char* filename)
+{
+    // two separate values, so that the comparison cannot stop at identical addresses
+    const json j = load_json(filename);
+    const json copy = j;
+
+    for (auto _ : state)
+    {
+        bool result = (j == copy);
+        benchmark::DoNotOptimize(result);
+    }
+}
+BENCHMARK_CAPTURE(Equal, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(Equal, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(Equal, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+/// visit every value with range-based for loops, as client code walks a document
+static std::size_t count_values(const json& j)
+{
+    std::size_t result = 1;
+    if (j.is_structured())
+    {
+        for (const auto& element : j)
+        {
+            result += count_values(element);
+        }
+    }
+    return result;
+}
+
+static void Iterate(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+
+    for (auto _ : state)
+    {
+        std::size_t result = count_values(j);
+        benchmark::DoNotOptimize(result);
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(count_values(j)));
+}
+BENCHMARK_CAPTURE(Iterate, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(Iterate, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(Iterate, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+//////////////////////////////////////////////////////////////////////////////
+// flatten and unflatten
+//////////////////////////////////////////////////////////////////////////////
+
+static void Flatten(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+
+    for (auto _ : state)
+    {
+        json flat = j.flatten();
+        benchmark::DoNotOptimize(flat);
+    }
+}
+BENCHMARK_CAPTURE(Flatten, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(Flatten, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(Flatten, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+// ordered_json objects look keys up linearly, which flatten() used to do for
+// every value; canada (330,000 values in one flat object) is left out, as it
+// would take minutes with such versions
+static void FlattenOrdered(benchmark::State& state, const char* filename)
+{
+    const nlohmann::ordered_json j = nlohmann::ordered_json::parse(read_file(filename));
+
+    for (auto _ : state)
+    {
+        nlohmann::ordered_json flat = j.flatten();
+        benchmark::DoNotOptimize(flat);
+    }
+}
+BENCHMARK_CAPTURE(FlattenOrdered, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(FlattenOrdered, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+static void Unflatten(benchmark::State& state, const char* filename)
+{
+    const json flat = load_json(filename).flatten();
+
+    for (auto _ : state)
+    {
+        json j = flat.unflatten();
+        benchmark::DoNotOptimize(j);
+    }
+}
+BENCHMARK_CAPTURE(Unflatten, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(Unflatten, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(Unflatten, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+//////////////////////////////////////////////////////////////////////////////
+// diff and patch
+//
+// The target is the document with every eighth scalar changed, so the patch
+// has one "replace" operation per changed value and the structure stays the
+// same.
+//////////////////////////////////////////////////////////////////////////////
+
+static void change_every_eighth_scalar(json& j, std::size_t& counter)
+{
+    if (j.is_structured())
+    {
+        for (auto& element : j)
+        {
+            change_every_eighth_scalar(element, counter);
+        }
+        return;
+    }
+
+    if (++counter % 8 != 0)
+    {
+        return;
+    }
+
+    switch (j.type())
+    {
+        case json::value_t::number_integer:
+            j = j.get<json::number_integer_t>() + 1;
+            break;
+        case json::value_t::number_unsigned:
+            j = j.get<json::number_unsigned_t>() + 1;
+            break;
+        case json::value_t::number_float:
+            j = j.get<json::number_float_t>() + 0.5;
+            break;
+        case json::value_t::string:
+            j = j.get<std::string>() + "!";
+            break;
+        case json::value_t::boolean:
+            j = !j.get<bool>();
+            break;
+        case json::value_t::null:
+        case json::value_t::object:
+        case json::value_t::array:
+        case json::value_t::binary:
+        case json::value_t::discarded:
+        default:
+            j = 0;
+            break;
+    }
+}
+
+static json changed_copy(const json& j)
+{
+    json result = j;
+    std::size_t counter = 0;
+    change_every_eighth_scalar(result, counter);
+    return result;
+}
+
+static void Diff(benchmark::State& state, const char* filename)
+{
+    const json source = load_json(filename);
+    const json target = changed_copy(source);
+
+    for (auto _ : state)
+    {
+        json patch = json::diff(source, target);
+        benchmark::DoNotOptimize(patch);
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(json::diff(source, target).size()));
+}
+BENCHMARK_CAPTURE(Diff, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(Diff, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(Diff, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+static void Patch(benchmark::State& state, const char* filename)
+{
+    const json source = load_json(filename);
+    const json patch = json::diff(source, changed_copy(source));
+
+    for (auto _ : state)
+    {
+        json result = source.patch(patch);
+        benchmark::DoNotOptimize(result);
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(patch.size()));
+}
+BENCHMARK_CAPTURE(Patch, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(Patch, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(Patch, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+//////////////////////////////////////////////////////////////////////////////
+// JSON Pointer
+//
+// The pointers are those of every scalar in the document, i.e., the keys of
+// its flattened form.
+//////////////////////////////////////////////////////////////////////////////
+
+static std::vector<std::string> pointer_strings(const json& j)
+{
+    std::vector<std::string> result;
+    const json flat = j.flatten();
+    result.reserve(flat.size());
+    for (auto it = flat.begin(); it != flat.end(); ++it)
+    {
+        result.push_back(it.key());
+    }
+    return result;
+}
+
+static std::vector<json::json_pointer> pointers(const json& j)
+{
+    const std::vector<std::string> strings = pointer_strings(j);
+    std::vector<json::json_pointer> result;
+    result.reserve(strings.size());
+    for (const auto& s : strings)
+    {
+        result.emplace_back(s);
+    }
+    return result;
+}
+
+static void JsonPointerParse(benchmark::State& state, const char* filename)
+{
+    const std::vector<std::string> strings = pointer_strings(load_json(filename));
+
+    for (auto _ : state)
+    {
+        for (const auto& s : strings)
+        {
+            json::json_pointer ptr(s);
+            benchmark::DoNotOptimize(ptr);
+        }
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(strings.size()));
+}
+BENCHMARK_CAPTURE(JsonPointerParse, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(JsonPointerParse, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+static void JsonPointerToString(benchmark::State& state, const char* filename)
+{
+    const std::vector<json::json_pointer> ptrs = pointers(load_json(filename));
+
+    for (auto _ : state)
+    {
+        for (const auto& ptr : ptrs)
+        {
+            std::string s = ptr.to_string();
+            benchmark::DoNotOptimize(s);
+        }
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(ptrs.size()));
+}
+BENCHMARK_CAPTURE(JsonPointerToString, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(JsonPointerToString, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+static void JsonPointerAt(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+    const std::vector<json::json_pointer> ptrs = pointers(j);
+
+    for (auto _ : state)
+    {
+        for (const auto& ptr : ptrs)
+        {
+            const json& value = j.at(ptr);
+            benchmark::DoNotOptimize(&value);
+        }
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(ptrs.size()));
+}
+BENCHMARK_CAPTURE(JsonPointerAt, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(JsonPointerAt, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+static void JsonPointerContains(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+    const std::vector<json::json_pointer> ptrs = pointers(j);
+
+    for (auto _ : state)
+    {
+        for (const auto& ptr : ptrs)
+        {
+            bool result = j.contains(ptr);
+            benchmark::DoNotOptimize(result);
+        }
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(ptrs.size()));
+}
+BENCHMARK_CAPTURE(JsonPointerContains, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(JsonPointerContains, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+//////////////////////////////////////////////////////////////////////////////
+// conversions from and to C++ containers
+//////////////////////////////////////////////////////////////////////////////
+
+static void GetVectorInt(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+
+    for (auto _ : state)
+    {
+        auto v = j.get<std::vector<std::int64_t>>();
+        benchmark::DoNotOptimize(v);
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(j.size()));
+}
+BENCHMARK_CAPTURE(GetVectorInt, signed_ints, TEST_DATA_DIRECTORY "/regression/signed_ints.json");
+
+static void GetVectorDouble(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+
+    for (auto _ : state)
+    {
+        auto v = j.get<std::vector<double>>();
+        benchmark::DoNotOptimize(v);
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(j.size()));
+}
+BENCHMARK_CAPTURE(GetVectorDouble, floats, TEST_DATA_DIRECTORY "/regression/floats.json");
+
+// a large flat object: the flattened document, one member per scalar
+static void GetMap(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename).flatten();
+
+    for (auto _ : state)
+    {
+        auto m = j.get<std::map<std::string, json>>();
+        benchmark::DoNotOptimize(m);
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(j.size()));
+}
+BENCHMARK_CAPTURE(GetMap, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+
+/// 100,000 strings, each too long for the small string optimization
+static std::vector<std::string> make_strings()
+{
+    std::vector<std::string> result;
+    result.reserve(100000);
+    for (std::size_t i = 0; i < 100000; ++i)
+    {
+        result.push_back("a string that does not fit in place: " + std::to_string(i));
+    }
+    return result;
+}
+
+static void ToJsonStrings(benchmark::State& state, const bool move)
+{
+    const std::vector<std::string> strings = make_strings();
+
+    for (auto _ : state)
+    {
+        state.PauseTiming();
+        std::vector<std::string> input = strings;
+        state.ResumeTiming();
+
+        // destroyed inside the timed section, like the copies above
+        auto* j = move ? new json(std::move(input)) : new json(input);
+        delete j;
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(strings.size()));
+}
+BENCHMARK_CAPTURE(ToJsonStrings, copy, false);
+BENCHMARK_CAPTURE(ToJsonStrings, move, true);
+
 // conversion of a JSON array into standard containers
 template<typename Container>
 static void GetArray(benchmark::State& state)

tests/src/unit-allocator-cpp17.cpp

@@ -1,98 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++ (supporting code)
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-License-Identifier: MIT
-
-// This file contains the C++17-only part of unit-allocator.cpp (std::string_view key
-// lookup with a failing allocator). It is kept in a separate translation unit so the (much
-// larger) unit-allocator.cpp is built for C++11 only and not rebuilt for every C++
-// standard.
-
-#include "doctest_compatibility.h"
-
-#include <nlohmann/json.hpp>
-
-#ifdef JSON_HAS_CPP_17
-#include <memory>
-#include <new>
-#include <string_view>
-#include <utility>
-
-namespace
-{
-bool next_construct_fails_cpp17 = false;
-bool next_destroy_fails_cpp17 = false;
-bool next_deallocate_fails_cpp17 = false;
-
-template<class T>
-struct my_allocator_cpp17 : std::allocator<T>
-{
-    using std::allocator<T>::allocator;
-
-    template<class... Args>
-    void construct(T* p, Args&& ... args)
-    {
-        if (next_construct_fails_cpp17)
-        {
-            next_construct_fails_cpp17 = false;
-            throw std::bad_alloc();
-        }
-
-        ::new (reinterpret_cast<void*>(p)) T(std::forward<Args>(args)...);
-    }
-
-    void deallocate(T* p, std::size_t n)
-    {
-        if (next_deallocate_fails_cpp17)
-        {
-            next_deallocate_fails_cpp17 = false;
-            throw std::bad_alloc();
-        }
-
-        std::allocator<T>::deallocate(p, n);
-    }
-
-    void destroy(T* p)
-    {
-        if (next_destroy_fails_cpp17)
-        {
-            next_destroy_fails_cpp17 = false;
-            throw std::bad_alloc();
-        }
-
-        static_cast<void>(p); // fix MSVC's C4100 warning
-        p->~T();
-    }
-
-    template <class U>
-    struct rebind
-    {
-        using other = my_allocator_cpp17<U>;
-    };
-};
-} // namespace
-
-// the no-exceptions CI job skips every CHECK_THROWS_AS, which would leave
-// next_construct_fails_cpp17 set for the next allocation outside a check
-#if !defined(JSON_NOEXCEPTION)
-TEST_CASE("a failed allocation leaves the value unchanged (C++17)")
-{
-    // create JSON type using the throwing allocator
-    using my_json = nlohmann::json::with_allocator_t<my_allocator_cpp17>;
-
-    SECTION("turning a null value into an array or object")
-    {
-        my_json j;
-
-        next_construct_fails_cpp17 = true;
-        CHECK_THROWS_AS(j[std::string_view("key")], std::bad_alloc&);
-        CHECK(j.is_null());
-
-        next_construct_fails_cpp17 = false;
-    }
-}
-#endif
-#endif

tests/src/unit-allocator-cpp20.cpp

@@ -1,115 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++ (supporting code)
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-License-Identifier: MIT
-
-// This file contains the C++20-only part of unit-allocator.cpp (creating a value from a
-// std::ranges view with a failing allocator). It is kept in a separate translation unit so
-// the (much larger) unit-allocator.cpp is built for C++11 only and not rebuilt for every
-// C++ standard.
-
-#include "doctest_compatibility.h"
-
-#include <nlohmann/json.hpp>
-
-#ifdef JSON_HAS_CPP_20
-#if JSON_HAS_RANGES
-    #include <ranges>
-#endif
-
-#include <memory>
-#include <new>
-#include <utility>
-#include <vector>
-
-namespace
-{
-bool next_construct_fails_cpp20 = false;
-bool next_destroy_fails_cpp20 = false;
-bool next_deallocate_fails_cpp20 = false;
-
-template<class T>
-struct my_allocator_cpp20 : std::allocator<T>
-{
-    using std::allocator<T>::allocator;
-
-    template<class... Args>
-    void construct(T* p, Args&& ... args)
-    {
-        if (next_construct_fails_cpp20)
-        {
-            next_construct_fails_cpp20 = false;
-            throw std::bad_alloc();
-        }
-
-        ::new (reinterpret_cast<void*>(p)) T(std::forward<Args>(args)...);
-    }
-
-    void deallocate(T* p, std::size_t n)
-    {
-        if (next_deallocate_fails_cpp20)
-        {
-            next_deallocate_fails_cpp20 = false;
-            throw std::bad_alloc();
-        }
-
-        std::allocator<T>::deallocate(p, n);
-    }
-
-    void destroy(T* p)
-    {
-        if (next_destroy_fails_cpp20)
-        {
-            next_destroy_fails_cpp20 = false;
-            throw std::bad_alloc();
-        }
-
-        static_cast<void>(p); // fix MSVC's C4100 warning
-        p->~T();
-    }
-
-    template <class U>
-    struct rebind
-    {
-        using other = my_allocator_cpp20<U>;
-    };
-};
-} // namespace
-
-// the no-exceptions CI job skips every CHECK_THROWS_AS, which would leave
-// next_construct_fails_cpp20 set for the next allocation outside a check
-#if !defined(JSON_NOEXCEPTION)
-TEST_CASE("a failed allocation leaves the value unchanged (C++20)")
-{
-    // create JSON type using the throwing allocator
-    using my_json = nlohmann::json::with_allocator_t<my_allocator_cpp20>;
-
-    // With iterator debugging, VS 2015's containers construct a proxy with the
-    // allocator in constructors that cannot report its failure, so a failing
-    // allocator crashes this section there (SIGSEGV with VS 2015 Debug x86).
-#if !(defined(_MSC_VER) && _MSC_VER < 1910 && defined(_ITERATOR_DEBUG_LEVEL) && _ITERATOR_DEBUG_LEVEL > 0)
-    SECTION("converting into an existing value")
-    {
-        // to_json replaces the value it is given; the old one must survive a
-        // failed creation of the new one
-        my_json j = "old";
-
-#if JSON_HAS_RANGES && !defined(__MINGW32__)
-        const std::vector<int> numbers = {1, 2};
-        next_construct_fails_cpp20 = true;
-        CHECK_THROWS_AS(nlohmann::to_json(j, numbers | std::views::filter([](int /*unused*/)
-        {
-            return true;
-        })), std::bad_alloc&);
-        CHECK(j == "old");
-#endif
-
-        next_construct_fails_cpp20 = false;
-    }
-#endif
-}
-#endif
-#endif

tests/src/unit-allocator.cpp

@@ -13,6 +13,9 @@
 using nlohmann::json;
 
 #include <valarray>
+#if JSON_HAS_RANGES
+    #include <ranges>
+#endif
 
 namespace
 {
@@ -681,6 +684,12 @@ TEST_CASE("a failed allocation leaves the value unchanged")
         CHECK_THROWS_AS(j["key"], std::bad_alloc&);
         CHECK(j.is_null());
 
+#ifdef JSON_HAS_CPP_17
+        next_construct_fails = true;
+        CHECK_THROWS_AS(j[std::string_view("key")], std::bad_alloc&);
+        CHECK(j.is_null());
+#endif
+
         next_construct_fails = true;
         CHECK_THROWS_AS(j.push_back(my_json(1)), std::bad_alloc&);
         CHECK(j.is_null());
@@ -778,6 +787,16 @@ TEST_CASE("a failed allocation leaves the value unchanged")
         CHECK_THROWS_AS(nlohmann::to_json(j, std::valarray<int> {1, 2}), std::bad_alloc&);
         CHECK(j == "old");
 
+#if JSON_HAS_RANGES && !defined(__MINGW32__)
+        const std::vector<int> numbers = {1, 2};
+        next_construct_fails = true;
+        CHECK_THROWS_AS(nlohmann::to_json(j, numbers | std::views::filter([](int /*unused*/)
+        {
+            return true;
+        })), std::bad_alloc&);
+        CHECK(j == "old");
+#endif
+
         next_construct_fails = false;
         nlohmann::to_json(j, std::vector<int> {1, 2});
         CHECK(j == my_json({1, 2}));

tests/src/unit-binary_writer_sinks.cpp

@@ -492,3 +492,278 @@ TEST_CASE("binary_reserve_hint never over-reserves")
         CHECK(nlohmann::detail::binary_reserve_hint(json({{"a", 1}, {"b", 2}})) == 5);
     }
 }
+
+namespace
+{
+
+// numbers around every boundary of the integer encodings, and floats of each
+// kind (exact in float, needing double, special values)
+std::vector<json> boundary_numbers()
+{
+    std::vector<json> numbers;
+    for (int k = 0; k < 64; ++k)
+    {
+        const std::uint64_t p = std::uint64_t{1} << k;
+        for (const std::uint64_t d :
+                {
+                    p - 1, p, p + 1
+                })
+        {
+            numbers.emplace_back(d);
+            if (d <= static_cast<std::uint64_t>((std::numeric_limits<std::int64_t>::max)()))
+            {
+                numbers.emplace_back(static_cast<std::int64_t>(d));
+                numbers.emplace_back(-static_cast<std::int64_t>(d));
+                numbers.emplace_back(-static_cast<std::int64_t>(d) - 1);
+            }
+        }
+    }
+    numbers.emplace_back((std::numeric_limits<std::int64_t>::min)());
+    numbers.emplace_back((std::numeric_limits<std::uint64_t>::max)());
+    for (const double f :
+            {
+                0.0, -0.0, 1.0, -1.0, 0.5, 0.1, 3.25, 1e300, -1e-300, 3.4028234663852886e38, 1e39,
+                std::numeric_limits<double>::infinity(), -std::numeric_limits<double>::infinity(),
+                std::numeric_limits<double>::quiet_NaN()
+            })
+    {
+        numbers.emplace_back(f);
+    }
+    return numbers;
+}
+
+// the concatenation of the encodings of the elements of @a numbers[first, first + count)
+template<typename Single>
+std::vector<std::uint8_t> concat_singles(const std::vector<json>& numbers, const std::size_t first, const std::size_t count, Single single)
+{
+    std::vector<std::uint8_t> bytes;
+    for (std::size_t i = first; i < first + count; ++i)
+    {
+        const auto one = single(numbers[i]);
+        bytes.insert(bytes.end(), one.begin(), one.end());
+    }
+    return bytes;
+}
+
+} // namespace
+
+// Runs of numbers in arrays are encoded straight into space reserved from the
+// sink, by code that is separate from the encoding of a single value. Both have
+// to agree on every number: an array is its head and the encodings of its
+// elements, one after the other.
+TEST_CASE("runs of numbers in arrays are encoded as the numbers one by one")
+{
+    const std::vector<json> numbers = boundary_numbers();
+
+    // arrays of every length that a one-byte head covers, so that runs are as
+    // long as, and longer and shorter than, what fits one reservation
+    for (const std::size_t count :
+            {
+                1u, 2u, 3u, 5u, 14u, 15u, 23u
+            })
+    {
+        for (std::size_t first = 0; first + count <= numbers.size(); first += 7)
+        {
+            const json array(std::vector<json>(numbers.begin() + static_cast<std::ptrdiff_t>(first),
+                                               numbers.begin() + static_cast<std::ptrdiff_t>(first + count)));
+            CAPTURE(array.dump(-1, ' ', false, json::error_handler_t::replace))
+
+            std::vector<std::uint8_t> expected{static_cast<std::uint8_t>(0x80 + count)};
+            auto elements = concat_singles(numbers, first, count, [](const json & j)
+            {
+                return json::to_cbor(j);
+            });
+            expected.insert(expected.end(), elements.begin(), elements.end());
+            CHECK(json::to_cbor(array) == expected);
+
+            expected.assign(1, static_cast<std::uint8_t>(count <= 15 ? 0x90 + count : 0xDC));
+            if (count > 15)
+            {
+                expected.push_back(0);
+                expected.push_back(static_cast<std::uint8_t>(count));
+            }
+            elements = concat_singles(numbers, first, count, [](const json & j)
+            {
+                return json::to_msgpack(j);
+            });
+            expected.insert(expected.end(), elements.begin(), elements.end());
+            CHECK(json::to_msgpack(array) == expected);
+
+            for (const bool bjdata :
+                    {
+                        false, true
+                    })
+            {
+                expected.assign(1, static_cast<std::uint8_t>('['));
+                elements = concat_singles(numbers, first, count, [bjdata](const json & j)
+                {
+                    return bjdata ? json::to_bjdata(j) : json::to_ubjson(j);
+                });
+                expected.insert(expected.end(), elements.begin(), elements.end());
+                expected.push_back(static_cast<std::uint8_t>(']'));
+                CHECK((bjdata ? json::to_bjdata(array) : json::to_ubjson(array)) == expected);
+            }
+
+            // BON8 has no integers above the int64 range
+            bool representable = true;
+            for (std::size_t i = first; i < first + count; ++i)
+            {
+                representable = representable && bon8_representable(numbers[i]);
+            }
+            if (representable)
+            {
+                expected.assign(1, static_cast<std::uint8_t>(count <= 4 ? 0x80 + count : 0x85));
+                elements = concat_singles(numbers, first, count, [](const json & j)
+                {
+                    return json::to_bon8(j);
+                });
+                expected.insert(expected.end(), elements.begin(), elements.end());
+                if (count > 4)
+                {
+                    expected.push_back(0xFE);
+                }
+                CHECK(json::to_bon8(array) == expected);
+            }
+            else
+            {
+                CHECK_THROWS_AS(json::to_bon8(array), json::out_of_range&);
+            }
+        }
+    }
+}
+
+// An array that is written in more than one reservation (more numbers than fit
+// one), and arrays of an index with more digits, round trip for every format.
+TEST_CASE("large arrays and many digits of indices round trip")
+{
+    json array = json::array();
+    for (int i = 0; i < 12000; ++i)
+    {
+        switch (i % 4)
+        {
+            case 0:
+                array.push_back(i);
+                break;
+            case 1:
+                array.push_back(-i);
+                break;
+            case 2:
+                array.push_back(i * 0.25);
+                break;
+            default:
+                array.push_back(i % 8 == 3);
+                break;
+        }
+    }
+    json document = json::object();
+    document["numbers"] = array;
+    document["nested"] = json::array({array, "text", array});
+
+    CHECK(json::from_cbor(json::to_cbor(document)) == document);
+    CHECK(json::from_msgpack(json::to_msgpack(document)) == document);
+    CHECK(json::from_ubjson(json::to_ubjson(document)) == document);
+    CHECK(json::from_ubjson(json::to_ubjson(document, true, true)) == document);
+    CHECK(json::from_bjdata(json::to_bjdata(document)) == document);
+    CHECK(json::from_bson(json::to_bson(document)) == document);
+    CHECK(json::from_bon8(json::to_bon8(document)) == document);
+}
+
+// Strings and keys are written with their head in one reservation up to a
+// length; around that length, and with every kind of head, they must read back.
+TEST_CASE("strings of every head length round trip")
+{
+    json document = json::object();
+    json array = json::array();
+    for (const std::size_t length :
+            {
+                0u, 1u, 2u, 3u, 4u, 7u, 8u, 15u, 16u, 17u, 23u, 24u, 25u, 31u, 32u, 33u, 63u, 127u, 128u, 129u, 200u, 245u, 246u, 247u, 248u, 249u, 250u, 251u, 252u, 253u, 254u, 255u, 256u, 257u, 300u, 1000u, 65535u, 65536u, 70000u
+            })
+    {
+        const std::string text(length, 'x');
+        array.push_back(text);
+        document[std::string(length, 'k')] = text;
+    }
+    document["array"] = array;
+
+    CHECK(json::from_cbor(json::to_cbor(document)) == document);
+    CHECK(json::from_msgpack(json::to_msgpack(document)) == document);
+    CHECK(json::from_ubjson(json::to_ubjson(document)) == document);
+    CHECK(json::from_ubjson(json::to_ubjson(document, true, true)) == document);
+    CHECK(json::from_bjdata(json::to_bjdata(document)) == document);
+    CHECK(json::from_bson(json::to_bson(document)) == document);
+    CHECK(json::from_bon8(json::to_bon8(document)) == document);
+}
+
+#if !defined(JSON_NOEXCEPTION)
+// What a write that throws leaves behind in an output adapter is what was written
+// before it, whatever the adapter and however the adapter sink buffers. (Without
+// exceptions, the writes in CHECK_THROWS_AS do not run.)
+TEST_CASE("a write that throws leaves the same bytes in every kind of output")
+{
+    json array = json::array();
+    for (int i = 0; i < 700; ++i)
+    {
+        array.push_back(i * 1000);
+        array.push_back("text " + std::to_string(i));
+    }
+    array.push_back("bad \xFF byte");
+    json document = json::object();
+    document["first"] = array;
+    document["second"] = 1;
+
+    const auto strict = json::error_handler_t::strict;
+
+    SECTION("cbor")
+    {
+        std::vector<std::uint8_t> as_vector;
+        std::string as_string;
+        std::ostringstream as_stream;
+        CHECK_THROWS_AS(json::to_cbor(document, as_vector, strict), json::type_error&);
+        CHECK_THROWS_AS(json::to_cbor(document, as_string, strict), json::type_error&);
+        CHECK_THROWS_AS(json::to_cbor(document, as_stream, strict), json::type_error&);
+        CHECK(!as_vector.empty());
+        CHECK(std::string(reinterpret_cast<const char*>(as_vector.data()), as_vector.size()) == as_string); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+        CHECK(as_stream.str() == as_string);
+    }
+
+    SECTION("msgpack")
+    {
+        std::vector<std::uint8_t> as_vector;
+        std::string as_string;
+        std::ostringstream as_stream;
+        CHECK_THROWS_AS(json::to_msgpack(document, as_vector, strict), json::type_error&);
+        CHECK_THROWS_AS(json::to_msgpack(document, as_string, strict), json::type_error&);
+        CHECK_THROWS_AS(json::to_msgpack(document, as_stream, strict), json::type_error&);
+        CHECK(!as_vector.empty());
+        CHECK(std::string(reinterpret_cast<const char*>(as_vector.data()), as_vector.size()) == as_string); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+        CHECK(as_stream.str() == as_string);
+    }
+
+    SECTION("ubjson")
+    {
+        std::vector<std::uint8_t> as_vector;
+        std::string as_string;
+        std::ostringstream as_stream;
+        CHECK_THROWS_AS(json::to_ubjson(document, as_vector, false, false, strict), json::type_error&);
+        CHECK_THROWS_AS(json::to_ubjson(document, as_string, false, false, strict), json::type_error&);
+        CHECK_THROWS_AS(json::to_ubjson(document, as_stream, false, false, strict), json::type_error&);
+        CHECK(!as_vector.empty());
+        CHECK(std::string(reinterpret_cast<const char*>(as_vector.data()), as_vector.size()) == as_string); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+        CHECK(as_stream.str() == as_string);
+    }
+
+    SECTION("bson")
+    {
+        // the size pass finds the string before anything is written
+        std::vector<std::uint8_t> as_vector;
+        std::string as_string;
+        std::ostringstream as_stream;
+        CHECK_THROWS_AS(json::to_bson(document, as_vector, strict), json::type_error&);
+        CHECK_THROWS_AS(json::to_bson(document, as_string, strict), json::type_error&);
+        CHECK_THROWS_AS(json::to_bson(document, as_stream, strict), json::type_error&);
+        CHECK(as_vector.empty());
+        CHECK(as_string.empty());
+        CHECK(as_stream.str().empty());
+    }
+}
+#endif

tests/src/unit-bon8-cpp17.cpp

@@ -1,60 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++ (supporting code)
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-License-Identifier: MIT
-
-// This file contains the C++17-only part of unit-bon8.cpp (BON8 with std::byte
-// containers). It is kept in a separate translation unit so the (much larger) unit-
-// bon8.cpp is built for C++11 only and not rebuilt for every C++ standard.
-
-#include "doctest_compatibility.h"
-
-#include <nlohmann/json.hpp>
-using nlohmann::json;
-
-#ifdef JSON_HAS_CPP_17
-#include <cstddef>
-#include <cstdint>
-#include <vector>
-
-TEST_CASE("BON8 with std::byte")
-{
-    SECTION("vector roundtrip")
-    {
-        const json original =
-        {
-            {"name", "test"},
-            {"value", 42},
-            {"array", {1, 2, 3}}
-        };
-
-        const std::vector<uint8_t> temp = json::to_bon8(original);
-        std::vector<std::byte> bon8_data(temp.size());
-        for (size_t i = 0; i < temp.size(); ++i)
-        {
-            bon8_data[i] = std::byte(temp[i]);
-        }
-
-        json from_bytes;
-        CHECK_NOTHROW(from_bytes = json::from_bon8(bon8_data));
-        CHECK(from_bytes == original);
-    }
-
-    SECTION("empty vector")
-    {
-        const std::vector<std::byte> empty_data;
-        CHECK_THROWS_WITH_AS([&]()
-        {
-            [[maybe_unused]] auto result = json::from_bon8(empty_data);
-            return true;
-        }
-        (),
-        "[json.exception.parse_error.110] parse error at byte 1: syntax error while parsing BON8 value: unexpected end of input",
-        json::parse_error&);
-    }
-}
-
-#endif

tests/src/unit-bon8.cpp

@@ -1099,3 +1099,41 @@ TEST_CASE("issue #5648 - from_bon8(ptr, len) must read len bytes, not treat ptr
 #endif
 }
 
+#ifdef JSON_HAS_CPP_17
+TEST_CASE("BON8 with std::byte")
+{
+    SECTION("vector roundtrip")
+    {
+        const json original =
+        {
+            {"name", "test"},
+            {"value", 42},
+            {"array", {1, 2, 3}}
+        };
+
+        const std::vector<uint8_t> temp = json::to_bon8(original);
+        std::vector<std::byte> bon8_data(temp.size());
+        for (size_t i = 0; i < temp.size(); ++i)
+        {
+            bon8_data[i] = std::byte(temp[i]);
+        }
+
+        json from_bytes;
+        CHECK_NOTHROW(from_bytes = json::from_bon8(bon8_data));
+        CHECK(from_bytes == original);
+    }
+
+    SECTION("empty vector")
+    {
+        const std::vector<std::byte> empty_data;
+        CHECK_THROWS_WITH_AS([&]()
+        {
+            [[maybe_unused]] auto result = json::from_bon8(empty_data);
+            return true;
+        }
+        (),
+        "[json.exception.parse_error.110] parse error at byte 1: syntax error while parsing BON8 value: unexpected end of input",
+        json::parse_error&);
+    }
+}
+#endif

tests/src/unit-class_lexer.cpp

@@ -13,11 +13,15 @@
 using nlohmann::json;
 
 #include <array> // array
+#include <cctype> // toupper
 #include <cstdint> // uint32_t, uint64_t
 #include <cstdio> // snprintf
+#include <cmath> // isfinite
 #include <cstdlib> // strtod
 #include <cstring> // memcpy
 #include <limits> // numeric_limits
+#include <initializer_list> // initializer_list
+#include <list> // list
 #include <map> // map
 #include <random> // mt19937
 #include <sstream> // stringstream
@@ -332,6 +336,112 @@ TEST_CASE("lexer number fast path")
         }
     }
 
+#if !defined(JSON_NOEXCEPTION)
+    // this section reports parse errors, which abort when exceptions are off
+    SECTION("digits accumulated while scanning")
+    {
+        // The fast path accumulates the digits while it validates them, eight
+        // at a time where possible, and converts tokens with at most 19
+        // digits (floats) or 18 digits (integers) from that value. Every digit
+        // count from 1 to 25, in the integer and in the fraction part, with
+        // and without sign and exponent, must give the byte path's result. A
+        // std::list has no contiguous storage, so parsing it takes the byte
+        // path.
+        // type and value, or the error (values beyond the range of double
+        // are rejected with out_of_range.406 on both paths)
+        const auto outcome = [](const std::string & doc, bool byte_path) -> std::string
+        {
+            JSON_TRY
+            {
+                const std::list<char> chars(doc.begin(), doc.end());
+                const json j = byte_path ? json::parse(chars.begin(), chars.end()) : json::parse(doc);
+                return std::string(j[0].type_name()) + '|' + j.dump();
+            }
+            JSON_CATCH (const json::exception & e)
+            {
+                return e.what();
+            }
+        };
+
+        // the concatenation of @a parts
+        const auto join = [](std::initializer_list<std::string> parts)
+        {
+            std::string result;
+            for (const auto& part : parts)
+            {
+                result += part;
+            }
+            return result;
+        };
+
+        std::vector<std::string> numbers;
+        for (std::size_t digits = 1; digits <= 25; ++digits)
+        {
+            std::string run;
+            for (std::size_t i = 0; i < digits; ++i)
+            {
+                run += static_cast<char>('1' + static_cast<char>((i * 7) % 9));
+            }
+            const std::string nines(digits, '9');
+            for (const char* sign_text :
+                    {"", "-"
+                    })
+            {
+                const std::string sign = sign_text;
+                numbers.push_back(join({sign, run}));
+                numbers.push_back(join({sign, nines}));
+                numbers.push_back(join({sign, "1", std::string(digits - 1, '0')}));
+                numbers.push_back(join({sign, "0.", run}));
+                numbers.push_back(join({sign, "0.", std::string(digits, '0'), "1"}));
+                numbers.push_back(join({sign, run, ".", run}));
+                numbers.push_back(join({sign, run, "e-", std::to_string(digits)}));
+                numbers.push_back(join({sign, "1.", run, "E+", std::to_string(digits * 13)}));
+            }
+        }
+        // exponents beyond every range, and zeros
+        numbers.insert(numbers.end(), {"1e400", "1e-400", "-1e99999999999999999999", "1e-99999999999999999999",
+                                       "0e99999999999999999999", "0.0e-5", "-0.000", "123456789e-0000000000000000000000330"
+                                      });
+
+        for (const auto& n : numbers)
+        {
+            CAPTURE(n)
+            const std::string doc = "[" + n + "]";
+            const std::string a = outcome(doc, false);
+            CHECK(a == outcome(doc, true));
+            const double expected = std::strtod(n.c_str(), nullptr);
+            if (a.compare(0, 6, "number") == 0 && std::isfinite(expected) && n.find_first_of(".eE") != std::string::npos)
+            {
+                CHECK(json::parse(doc)[0].get<double>() == expected);
+            }
+        }
+    }
+#endif
+
+    SECTION("integers that do not fit a narrower type become floats")
+    {
+        // up to 18 digits, the fast path stores the accumulated value without
+        // an overflow check; a narrower number_integer_t/number_unsigned_t
+        // must still see the value rejected and converted as a float
+        using json32 = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int32_t, std::uint32_t, float>;
+        for (const char* n :
+                {"4294967295", "4294967296", "2147483647", "-2147483648", "-2147483649", "99999999999", "-99999999999"
+                })
+        {
+            CAPTURE(n)
+            const std::string doc = std::string("[") + n + "]";
+            const std::list<char> chars(doc.begin(), doc.end());
+            const json32 a = json32::parse(doc);
+            const json32 b = json32::parse(chars.begin(), chars.end());
+            CHECK(a[0].type() == b[0].type());
+            CHECK(a == b);
+        }
+        CHECK(json32::parse("[4294967295]")[0].is_number_unsigned());
+        CHECK(json32::parse("[4294967296]")[0].is_number_float());
+        CHECK(json32::parse("[-2147483648]")[0].is_number_integer());
+        CHECK(json32::parse("[-2147483649]")[0].is_number_float());
+    }
+
     SECTION("token type classification")
     {
         CHECK((scan_string("0") == json::lexer::token_type::value_unsigned));
@@ -490,6 +600,67 @@ TEST_CASE("lexer number fast path")
 #endif
 }
 
+#if !defined(JSON_NOEXCEPTION)
+// this test case compares the errors of both lexer paths, which abort when
+// exceptions are off
+TEST_CASE("lexer literal fast path")
+{
+    // For contiguous input, the rest of a literal is compared at once, and a
+    // mismatch is left to the byte path, which reports the error at the
+    // character that differs. Every truncation and every wrong character of
+    // each literal, at the end of the input or followed by more text, must
+    // give the byte path's result (a std::list is read one character at a
+    // time).
+    const auto outcome = [](const std::string & doc, bool byte_path) -> std::string
+    {
+        JSON_TRY
+        {
+            const std::list<char> chars(doc.begin(), doc.end());
+            return (byte_path ? json::parse(chars.begin(), chars.end()) : json::parse(doc)).dump();
+        }
+        JSON_CATCH (const json::exception & e)
+        {
+            return e.what();
+        }
+    };
+
+    std::vector<std::string> mismatches;
+    for (const std::string literal :
+            {"true", "false", "null"
+            })
+    {
+        std::vector<std::string> variants;
+        for (std::size_t length = 1; length <= literal.size(); ++length)
+        {
+            variants.push_back(literal.substr(0, length));
+        }
+        for (std::size_t i = 1; i < literal.size(); ++i)
+        {
+            std::string changed = literal;
+            changed[i] = 'X';
+            variants.push_back(changed);
+            changed[i] = static_cast<char>(std::toupper(static_cast<unsigned char>(literal[i])));
+            variants.push_back(changed);
+        }
+        for (const auto& variant : variants)
+        {
+            for (const std::string& doc :
+                    {
+                        variant, "[" + variant + "]", "[" + variant, variant + " ", variant + "1", "{\"k\":" + variant + "}"
+                    })
+            {
+                if (outcome(doc, false) != outcome(doc, true))
+                {
+                    mismatches.push_back(doc);
+                }
+            }
+        }
+    }
+    CAPTURE(mismatches)
+    CHECK(mismatches.empty());
+}
+#endif
+
 TEST_CASE("lexer string fast path")
 {
     // Build a byte string from explicit values: a hex escape in a string
@@ -610,6 +781,73 @@ TEST_CASE("lexer string fast path")
         CAPTURE(mismatches)
         CHECK(mismatches.empty());
     }
+
+    SECTION("special bytes at every offset of the vector blocks")
+    {
+        // With SSE2 or NEON, runs are scanned 16 bytes at a time (after one
+        // SWAR word, or four with NEON), and runs of non-ASCII text are
+        // checked 16 bytes at a time as well. Place every kind of byte that
+        // ends a run at each offset across several blocks, after ASCII and
+        // after CJK text, so sequences also straddle the block boundaries.
+        // The reference is a std::list, which has no contiguous storage and
+        // is therefore read one character at a time.
+        const auto byte_path = [](const std::string & doc) -> std::string
+        {
+            const std::list<char> chars(doc.begin(), doc.end());
+            JSON_TRY
+            {
+                return json::parse(chars.begin(), chars.end()).dump();
+            }
+            JSON_CATCH (const json::exception & e)
+            {
+                return e.what();
+            }
+        };
+        const std::vector<std::string> specials =
+        {
+            "\"", "\\", "\\u00e9", bytes({0x01}), bytes({0x1F}), bytes({0x7F}),
+            bytes({0xC3, 0xA9}), bytes({0xE4, 0xB8, 0xAD}), bytes({0xF0, 0x9F, 0x98, 0x80}),
+            bytes({0xFF}), bytes({0xC3}), bytes({0xE4, 0xB8}), bytes({0xED, 0xA0, 0x80}), bytes({0xC0, 0x80})
+        };
+        const std::string cjk = bytes({0xE4, 0xB8, 0xAD}); // U+4E2D
+
+        std::vector<std::string> mismatches;
+        for (std::size_t offset = 0; offset <= 80; ++offset)
+        {
+            std::string text;
+            while (text.size() < offset)
+            {
+                text += cjk;
+            }
+            for (const auto& prefix :
+                    {
+                        std::string(offset, 'a'), text
+                    })
+            {
+                for (const auto& special : specials)
+                {
+                    // the closing quote right behind, or in a later block
+                    for (const int tail :
+                            {
+                                0, 1, 3, 20
+                            })
+                    {
+                        std::string doc = "[\"";
+                        doc += prefix;
+                        doc += special;
+                        doc.append(static_cast<std::size_t>(tail), 'b');
+                        doc += "\"]";
+                        if (outcome(doc, false) != byte_path(doc))
+                        {
+                            mismatches.push_back(doc);
+                        }
+                    }
+                }
+            }
+        }
+        CAPTURE(mismatches)
+        CHECK(mismatches.empty());
+    }
 #endif
 
     // json::accept() never throws, so the ranges stay covered without exceptions
@@ -1804,3 +2042,118 @@ TEST_CASE("string scanning kernels")
     CHECK(nlohmann::detail::read_eight_bytes(bytes.data() + 8) == 0xFF0F0E0D0C0B0A09u);
     CHECK(nlohmann::detail::read_eight_bytes(reinterpret_cast<const char*>(bytes.data()) + 3) == 0x0B0A090807060504u);
 }
+
+TEST_CASE("find_ascii_copyable_run agrees with is_ascii_copyable for every byte")
+{
+    // the SWAR mask in find_ascii_copyable_run() encodes the predicate a
+    // second time; check every byte value at every position of a 24-byte buffer
+    // (three words) and for several lengths, with the byte at the end or inside
+    for (unsigned int value = 0; value < 256; ++value)
+    {
+        for (std::size_t position = 0; position < 24; ++position)
+        {
+            std::array<unsigned char, 24> buffer{};
+            buffer.fill(static_cast<unsigned char>('a'));
+            buffer[position] = static_cast<unsigned char>(value);
+            const bool copyable = nlohmann::detail::is_ascii_copyable(static_cast<unsigned char>(value));
+            for (const std::size_t n :
+                    {
+                        position, position + 1, std::size_t{24}
+                    })
+            {
+                if (n > 24)
+                {
+                    continue;
+                }
+                const std::size_t expected = (copyable || n <= position) ? n : position;
+                CAPTURE(value)
+                CAPTURE(position)
+                CAPTURE(n)
+                CHECK(nlohmann::detail::find_ascii_copyable_run(buffer.data(), n) == expected);
+            }
+        }
+    }
+}
+
+TEST_CASE("UTF-8 validators accept the same sequences")
+{
+    // The library checks UTF-8 in several places: detail::decode (serializer),
+    // the per-lead-byte switch of the lexer (json::accept), validate_one_utf8
+    // (bulk string scan), utf8_shape, and the byte path of the BON8 reader.
+    // They must accept exactly the same sequences (RFC 3629, section 4).
+    using nlohmann::json;
+
+    // bytes for the third and fourth position: the first two pairs are checked
+    // against all validators, the others only against the cheap ones
+    const std::array<std::array<unsigned char, 2>, 6> tails =
+    {
+        {
+            {{0x80, 0x80}}, {{0xBF, 0xBF}}, {{0x7F, 0x80}}, {{0xC0, 0x80}}, {{0x80, 0x7F}}, {{0x80, 0xC0}}
+        }
+    };
+
+    for (unsigned lead = 0x80; lead <= 0xFF; ++lead)
+    {
+        const auto shape = nlohmann::detail::utf8_shape(static_cast<std::uint8_t>(lead));
+        for (unsigned second = 0; second <= 0xFF; ++second)
+        {
+            for (std::size_t t = 0; t < tails.size(); ++t)
+            {
+                const std::array<unsigned char, 4> bytes = {{static_cast<unsigned char>(lead), static_cast<unsigned char>(second), tails[t][0], tails[t][1]}};
+
+                // expectation from the shape: the sequence is bytes[0..length)
+                const std::size_t length = shape.length;
+                bool expected = length >= 2 && second >= shape.second_lo && second <= shape.second_hi;
+                for (std::size_t i = 2; expected && i < length; ++i)
+                {
+                    expected = bytes[i] >= 0x80 && bytes[i] <= 0xBF;
+                }
+
+                // the DFA of the serializer
+                bool dfa = length >= 2;
+                if (dfa)
+                {
+                    std::uint8_t state = nlohmann::detail::UTF8_ACCEPT;
+                    std::uint32_t codep = 0;
+                    for (std::size_t i = 0; i < length; ++i)
+                    {
+                        nlohmann::detail::decode(state, codep, bytes[i]);
+                    }
+                    dfa = state == nlohmann::detail::UTF8_ACCEPT;
+                }
+
+                // the bulk path: exactly the sequence, and one byte short
+                const std::size_t bulk = nlohmann::detail::validate_one_utf8(bytes.data(), length);
+                const std::size_t bulk_short = length > 0 ? nlohmann::detail::validate_one_utf8(bytes.data(), length - 1) : 0;
+
+                CAPTURE(lead)
+                CAPTURE(second)
+                CAPTURE(t)
+                CHECK((dfa == expected && bulk == (expected ? length : 0) && bulk_short == 0));
+
+                if (t < 2 && length >= 2)
+                {
+                    // the lexer's byte path
+                    const std::string sequence(reinterpret_cast<const char*>(bytes.data()), length); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+                    CHECK(json::accept("\"" + sequence + "\"") == expected);
+
+                    // the byte path of the BON8 reader (a string ends at 0xFF)
+                    if (lead >= 0xC2 && lead <= 0xF7)
+                    {
+                        std::vector<std::uint8_t> packed(bytes.begin(), bytes.begin() + static_cast<std::ptrdiff_t>(length));
+                        packed.push_back(0xFF);
+                        const json j = json::from_bon8(packed, true, false);
+                        if (expected)
+                        {
+                            CHECK(j == json(sequence));
+                        }
+                        else
+                        {
+                            CHECK_FALSE((j.is_string() && j.get<std::string>() == sequence));
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

tests/src/unit-class_parser.cpp

@@ -30,7 +30,9 @@ using nlohmann::json;
 #include <valarray>
 #include <algorithm>
 #include <cstdio>
+#include <cstdint>
 #include <fstream>
+#include <iterator>
 #include <list>
 #include <sstream>
 #include <string>
@@ -2450,6 +2452,109 @@ std::string parse_error_message_range(IteratorType first, IteratorType last)
 }
 } // namespace
 
+TEST_CASE("object keys are moved into the value")
+{
+    // json_sax_dom_parser::key() moves the key out of the lexer's buffer into
+    // the object, and the lexer starts the next token with an empty buffer.
+    // Keys of every length (inline and allocated strings), keys with escapes,
+    // and duplicate keys must give the same objects as reading the input one
+    // character at a time, and as ordered_json, whose map copies the key.
+    const std::string long_key(100, 'k');
+    const std::string doc = R"({"a": 1, ")" + long_key + R"(": {"b": [2, 3], "sixteen_chars_xx": 4}, )"
+                            R"("esc\"apedé": 5, "a": 6, ")" + long_key + R"(x": 7, "": 8, "dup": 9, "dup": 10})";
+
+    const json j = json::parse(doc);
+    const std::list<char> chars(doc.begin(), doc.end());
+    CHECK(j == json::parse(chars.begin(), chars.end()));
+
+    CHECK(j.size() == 6);
+    CHECK(j["a"] == 6);
+    CHECK(j[long_key]["b"] == json({2, 3}));
+    CHECK(j[long_key]["sixteen_chars_xx"] == 4);
+    CHECK(j["esc\"aped\xc3\xa9"] == 5);
+    CHECK(j[long_key + "x"] == 7);
+    CHECK(j[""] == 8);
+    CHECK(j["dup"] == 10);
+
+    const auto o = nlohmann::ordered_json::parse(doc);
+    CHECK(o.size() == 6);
+    CHECK(o[long_key + "x"] == 7);
+    CHECK(json(o) == j);
+}
+
+TEST_CASE("text of float tokens")
+{
+    // For contiguous input, the lexer copies the text of a float token into
+    // its buffer only when a SAX handler asks for it (the library's own
+    // handlers do not). A user handler must still see the exact text, for
+    // every input adapter and in every position of a document.
+    const std::string doc = R"([1.5, -0.0, 0.1, 1e5, -2.5E-4, 12345678901234567890.5, 0.12345678901234567890123,
+                              {"a": 3.25, "b": [6.02e23, 1]}, "x", true, 7e-1])";
+    const std::vector<std::string> expected_floats =
+    {
+        "number_float(1.5)", "number_float(-0.0)", "number_float(0.1)", "number_float(1e5)", "number_float(-2.5E-4)",
+        "number_float(12345678901234567890.5)", "number_float(0.12345678901234567890123)", "number_float(3.25)",
+        "number_float(6.02e23)", "number_float(7e-1)"
+    };
+
+    const auto floats = [](const std::vector<std::string>& events)
+    {
+        std::vector<std::string> result;
+        std::copy_if(events.begin(), events.end(), std::back_inserter(result), [](const std::string & e)
+        {
+            return e.compare(0, 13, "number_float(") == 0;
+        });
+        return result;
+    };
+
+    SECTION("contiguous input")
+    {
+        SaxEventLogger l;
+        CHECK(json::sax_parse(doc, &l));
+        CHECK(floats(l.events) == expected_floats);
+    }
+
+    SECTION("byte input")
+    {
+        const std::vector<std::uint8_t> bytes(doc.begin(), doc.end());
+        SaxEventLogger l;
+        CHECK(json::sax_parse(bytes, &l));
+        CHECK(floats(l.events) == expected_floats);
+    }
+
+    SECTION("stream input")
+    {
+        std::istringstream is(doc);
+        SaxEventLogger l;
+        CHECK(json::sax_parse(is, &l));
+        CHECK(floats(l.events) == expected_floats);
+    }
+
+    SECTION("non-contiguous iterators")
+    {
+        const std::list<char> chars(doc.begin(), doc.end());
+        SaxEventLogger l;
+        CHECK(json::sax_parse(chars.begin(), chars.end(), &l));
+        CHECK(floats(l.events) == expected_floats);
+    }
+
+    SECTION("the library's own handlers do not need the text")
+    {
+        using lexer_adapter = nlohmann::detail::iterator_input_adapter<const char*>;
+        CHECK(nlohmann::detail::sax_ignores_number_text<nlohmann::detail::json_sax_dom_parser<json, lexer_adapter>>::value);
+        CHECK(nlohmann::detail::sax_ignores_number_text<nlohmann::detail::json_sax_dom_callback_parser<json, lexer_adapter>>::value);
+        CHECK(nlohmann::detail::sax_ignores_number_text<nlohmann::detail::json_sax_acceptor<json>>::value);
+        CHECK_FALSE(nlohmann::detail::sax_ignores_number_text<SaxEventLogger>::value);
+
+        // and the values are the same as when the text is read
+        const json j = json::parse(doc);
+        CHECK(j[0] == 1.5);
+        CHECK(j[5].get<double>() == 12345678901234567890.5);
+        CHECK(j[7]["b"][0] == 6.02e23);
+        CHECK(json::accept(doc));
+    }
+}
+
 TEST_CASE("last-read diagnostics are identical across input adapters")
 {
     // The lexer reconstructs the "last read" token lazily for seekable adapters

tests/src/unit-comparison-cpp20.cpp

@@ -1,526 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++ (supporting code)
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-License-Identifier: MIT
-
-// This file contains the C++20-only part of unit-comparison.cpp (tests of operator<=> and
-// other three-way comparison specific behavior). It is kept in a separate translation unit
-// so the (much larger) unit-comparison.cpp is built for C++11 only and not rebuilt for
-// every C++ standard.
-
-#include "doctest_compatibility.h"
-
-#include <nlohmann/json.hpp>
-using nlohmann::json;
-
-#ifdef JSON_HAS_CPP_20
-#if JSON_HAS_THREE_WAY_COMPARISON
-#include <cmath>
-#include <compare>
-#include <cstddef>
-#include <limits>
-#include <string>
-#include <utility>
-#include <vector>
-
-// this can be replaced with the doctest stl extension header in version 2.5
-namespace doctest
-{
-template<> struct StringMaker<std::partial_ordering>
-{
-    static String convert(const std::partial_ordering& order)
-    {
-        if (order == std::partial_ordering::less)
-        {
-            return "std::partial_ordering::less";
-        }
-        if (order == std::partial_ordering::equivalent)
-        {
-            return "std::partial_ordering::equivalent";
-        }
-        if (order == std::partial_ordering::greater)
-        {
-            return "std::partial_ordering::greater";
-        }
-        if (order == std::partial_ordering::unordered)
-        {
-            return "std::partial_ordering::unordered";
-        }
-        return "{?}";
-    }
-};
-} // namespace doctest
-
-TEST_CASE("lexicographical comparison operators (C++20)")
-{
-    constexpr auto f_ = false;
-    constexpr auto _t = true;
-    constexpr auto nan = std::numeric_limits<json::number_float_t>::quiet_NaN();
-    constexpr auto lt = std::partial_ordering::less;
-    constexpr auto gt = std::partial_ordering::greater;
-    constexpr auto eq = std::partial_ordering::equivalent;
-    constexpr auto un = std::partial_ordering::unordered;
-
-    INFO("using 3-way comparison");
-
-#if JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON
-    INFO("using legacy comparison");
-#endif
-
-    SECTION("types")
-    {
-        std::vector<json::value_t> j_types =
-        {
-            json::value_t::null,
-            json::value_t::boolean,
-            json::value_t::number_integer,
-            json::value_t::number_unsigned,
-            json::value_t::number_float,
-            json::value_t::object,
-            json::value_t::array,
-            json::value_t::string,
-            json::value_t::binary,
-            json::value_t::discarded
-        };
-
-        std::vector<std::vector<bool>> expected_lt =
-        {
-            //0   1   2   3   4   5   6   7   8   9
-            {f_, _t, _t, _t, _t, _t, _t, _t, _t, f_}, //  0
-            {f_, f_, _t, _t, _t, _t, _t, _t, _t, f_}, //  1
-            {f_, f_, f_, f_, f_, _t, _t, _t, _t, f_}, //  2
-            {f_, f_, f_, f_, f_, _t, _t, _t, _t, f_}, //  3
-            {f_, f_, f_, f_, f_, _t, _t, _t, _t, f_}, //  4
-            {f_, f_, f_, f_, f_, f_, _t, _t, _t, f_}, //  5
-            {f_, f_, f_, f_, f_, f_, f_, _t, _t, f_}, //  6
-            {f_, f_, f_, f_, f_, f_, f_, f_, _t, f_}, //  7
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_}, //  8
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_}, //  9
-        };
-
-        SECTION("comparison: less")
-        {
-            for (size_t i = 0; i < j_types.size(); ++i)
-            {
-                for (size_t j = 0; j < j_types.size(); ++j)
-                {
-                    CAPTURE(i)
-                    CAPTURE(j)
-                    // check precomputed values
-                    CHECK((j_types[i] < j_types[j]) == expected_lt[i][j]);
-                }
-            }
-        }
-
-        SECTION("comparison: 3-way")
-        {
-            // doctest runs the REQUIRE in the test case body once per leaf section; keep it
-            // here to run it as often as before the 3-way sections moved from unit-comparison.cpp
-            REQUIRE(std::isnan(nan));
-
-            std::vector<std::vector<std::partial_ordering>> expected =
-            {
-                //0   1   2   3   4   5   6   7   8   9
-                {eq, lt, lt, lt, lt, lt, lt, lt, lt, un}, //  0
-                {gt, eq, lt, lt, lt, lt, lt, lt, lt, un}, //  1
-                {gt, gt, eq, eq, eq, lt, lt, lt, lt, un}, //  2
-                {gt, gt, eq, eq, eq, lt, lt, lt, lt, un}, //  3
-                {gt, gt, eq, eq, eq, lt, lt, lt, lt, un}, //  4
-                {gt, gt, gt, gt, gt, eq, lt, lt, lt, un}, //  5
-                {gt, gt, gt, gt, gt, gt, eq, lt, lt, un}, //  6
-                {gt, gt, gt, gt, gt, gt, gt, eq, lt, un}, //  7
-                {gt, gt, gt, gt, gt, gt, gt, gt, eq, un}, //  8
-                {un, un, un, un, un, un, un, un, un, un}, //  9
-            };
-
-            // check expected partial_ordering against expected boolean
-            REQUIRE(expected.size() == expected_lt.size());
-            for (size_t i = 0; i < expected.size(); ++i)
-            {
-                REQUIRE(expected[i].size() == expected_lt[i].size());
-                for (size_t j = 0; j < expected[i].size(); ++j)
-                {
-                    CAPTURE(i)
-                    CAPTURE(j)
-                    CHECK(std::is_lt(expected[i][j]) == expected_lt[i][j]);
-                }
-            }
-
-            // check 3-way comparison against expected partial_ordering
-            REQUIRE(expected.size() == j_types.size());
-            for (size_t i = 0; i < j_types.size(); ++i)
-            {
-                REQUIRE(expected[i].size() == j_types.size());
-                for (size_t j = 0; j < j_types.size(); ++j)
-                {
-                    CAPTURE(i)
-                    CAPTURE(j)
-                    CHECK((j_types[i] <=> j_types[j]) == expected[i][j]); // *NOPAD*
-                }
-            }
-        }
-    }
-
-    SECTION("values")
-    {
-        json j_values =
-        {
-            nullptr, nullptr,                                              // 0 1
-            -17, 42,                                                       // 2 3
-            8u, 13u,                                                       // 4 5
-            3.14159, 23.42,                                                // 6 7
-            nan, nan,                                                      // 8 9
-            "foo", "bar",                                                  // 10 11
-            true, false,                                                   // 12 13
-            {1, 2, 3}, {"one", "two", "three"},                            // 14 15
-            {{"first", 1}, {"second", 2}}, {{"a", "A"}, {"b", {"B"}}},     // 16 17
-            json::binary({1, 2, 3}), json::binary({1, 2, 4}),              // 18 19
-            json(json::value_t::discarded), json(json::value_t::discarded) // 20 21
-        };
-
-        std::vector<std::vector<bool>> expected_eq =
-        {
-            //0   1   2   3   4   5   6   7   8   9  10  11  12  13  14  15  16  17  18  19  20  21
-            {_t, _t, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_}, //  0
-            {_t, _t, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_}, //  1
-            {f_, f_, _t, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_}, //  2
-            {f_, f_, f_, _t, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_}, //  3
-            {f_, f_, f_, f_, _t, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_}, //  4
-            {f_, f_, f_, f_, f_, _t, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_}, //  5
-            {f_, f_, f_, f_, f_, f_, _t, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_}, //  6
-            {f_, f_, f_, f_, f_, f_, f_, _t, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_}, //  7
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_}, //  8
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_}, //  9
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, _t, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_}, // 10
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, _t, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_}, // 11
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, _t, f_, f_, f_, f_, f_, f_, f_, f_, f_}, // 12
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, _t, f_, f_, f_, f_, f_, f_, f_, f_}, // 13
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, _t, f_, f_, f_, f_, f_, f_, f_}, // 14
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, _t, f_, f_, f_, f_, f_, f_}, // 15
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, _t, f_, f_, f_, f_, f_}, // 16
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, _t, f_, f_, f_, f_}, // 17
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, _t, f_, f_, f_}, // 18
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, _t, f_, f_}, // 19
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_}, // 20
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_}, // 21
-        };
-
-        std::vector<std::vector<bool>> expected_lt =
-        {
-            //0   1   2   3   4   5   6   7   8   9  10  11  12  13  14  15  16  17  18  19  20  21
-            {f_, f_, _t, _t, _t, _t, _t, _t, _t, _t, _t, _t, _t, _t, _t, _t, _t, _t, _t, _t, f_, f_}, //  0
-            {f_, f_, _t, _t, _t, _t, _t, _t, _t, _t, _t, _t, _t, _t, _t, _t, _t, _t, _t, _t, f_, f_}, //  1
-            {f_, f_, f_, _t, _t, _t, _t, _t, f_, f_, _t, _t, f_, f_, _t, _t, _t, _t, _t, _t, f_, f_}, //  2
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, _t, _t, f_, f_, _t, _t, _t, _t, _t, _t, f_, f_}, //  3
-            {f_, f_, f_, _t, f_, _t, f_, _t, f_, f_, _t, _t, f_, f_, _t, _t, _t, _t, _t, _t, f_, f_}, //  4
-            {f_, f_, f_, _t, f_, f_, f_, _t, f_, f_, _t, _t, f_, f_, _t, _t, _t, _t, _t, _t, f_, f_}, //  5
-            {f_, f_, f_, _t, _t, _t, f_, _t, f_, f_, _t, _t, f_, f_, _t, _t, _t, _t, _t, _t, f_, f_}, //  6
-            {f_, f_, f_, _t, f_, f_, f_, f_, f_, f_, _t, _t, f_, f_, _t, _t, _t, _t, _t, _t, f_, f_}, //  7
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, _t, _t, f_, f_, _t, _t, _t, _t, _t, _t, f_, f_}, //  8
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, _t, _t, f_, f_, _t, _t, _t, _t, _t, _t, f_, f_}, //  9
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, _t, _t, f_, f_}, // 10
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, _t, f_, f_, f_, f_, f_, f_, f_, _t, _t, f_, f_}, // 11
-            {f_, f_, _t, _t, _t, _t, _t, _t, _t, _t, _t, _t, f_, f_, _t, _t, _t, _t, _t, _t, f_, f_}, // 12
-            {f_, f_, _t, _t, _t, _t, _t, _t, _t, _t, _t, _t, _t, f_, _t, _t, _t, _t, _t, _t, f_, f_}, // 13
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, _t, _t, f_, f_, f_, _t, f_, f_, _t, _t, f_, f_}, // 14
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, _t, _t, f_, f_, f_, f_, f_, f_, _t, _t, f_, f_}, // 15
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, _t, _t, f_, f_, _t, _t, f_, f_, _t, _t, f_, f_}, // 16
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, _t, _t, f_, f_, _t, _t, _t, f_, _t, _t, f_, f_}, // 17
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, _t, f_, f_}, // 18
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_}, // 19
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_}, // 20
-            {f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_, f_}, // 21
-        };
-
-        SECTION("signed/unsigned mixed comparison above INT64_MAX")
-        {
-            const json above_int64_max = static_cast<std::uint64_t>((std::numeric_limits<std::int64_t>::max)()) + 1ULL;
-            const json max_uint64 = (std::numeric_limits<std::uint64_t>::max)();
-            const json negative_one = -1;
-            const json one = 1;
-            const json max_int64 = (std::numeric_limits<std::int64_t>::max)();
-
-            CHECK((negative_one <=> above_int64_max) == std::partial_ordering::less); // *NOPAD*
-            CHECK((above_int64_max <=> negative_one) == std::partial_ordering::greater); // *NOPAD*
-            CHECK((negative_one <=> max_uint64) == std::partial_ordering::less); // *NOPAD*
-            CHECK((max_uint64 <=> negative_one) == std::partial_ordering::greater); // *NOPAD*
-            CHECK((one <=> above_int64_max) == std::partial_ordering::less); // *NOPAD*
-            CHECK((above_int64_max <=> one) == std::partial_ordering::greater); // *NOPAD*
-            CHECK((max_int64 <=> above_int64_max) == std::partial_ordering::less); // *NOPAD*
-            CHECK((above_int64_max <=> max_int64) == std::partial_ordering::greater); // *NOPAD*
-        }
-
-        SECTION("integer/float mixed comparison is exact")
-        {
-            // Widening the integer to a double loses precision past the
-            // mantissa, so 2^63-2 and 2^63-1 both used to compare equal to the
-            // double 2^63 while differing from each other. That makes equality
-            // intransitive and the ordering not a strict weak ordering.
-            const json below_two_63 = static_cast<std::int64_t>(9223372036854775806LL);
-            const json max_int64 = (std::numeric_limits<std::int64_t>::max)();
-            const json two_63 = 9223372036854775808.0;
-
-            // the same past the unsigned range
-            const json max_uint64 = (std::numeric_limits<std::uint64_t>::max)();
-            const json two_64 = 18446744073709551616.0;
-
-            CHECK((max_int64 <=> two_63) == std::partial_ordering::less); // *NOPAD*
-            CHECK((two_63 <=> max_int64) == std::partial_ordering::greater); // *NOPAD*
-            CHECK((below_two_63 <=> max_int64) == std::partial_ordering::less); // *NOPAD*
-            CHECK((max_uint64 <=> two_64) == std::partial_ordering::less); // *NOPAD*
-            CHECK((json(1) <=> json(1.0)) == std::partial_ordering::equivalent); // *NOPAD*
-            CHECK((json(1) <=> json(nan)) == std::partial_ordering::unordered); // *NOPAD*
-        }
-
-        SECTION("comparison: 3-way")
-        {
-            // doctest runs the REQUIRE in the test case body once per leaf section; keep it
-            // here to run it as often as before the 3-way sections moved from unit-comparison.cpp
-            REQUIRE(std::isnan(nan));
-
-            std::vector<std::vector<std::partial_ordering>> expected =
-            {
-                //0   1   2   3   4   5   6   7   8   9  10  11  12  13  14  15  16  17  18  19  20  21
-                {eq, eq, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, un, un}, //  0
-                {eq, eq, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, un, un}, //  1
-                {gt, gt, eq, lt, lt, lt, lt, lt, un, un, lt, lt, gt, gt, lt, lt, lt, lt, lt, lt, un, un}, //  2
-                {gt, gt, gt, eq, gt, gt, gt, gt, un, un, lt, lt, gt, gt, lt, lt, lt, lt, lt, lt, un, un}, //  3
-                {gt, gt, gt, lt, eq, lt, gt, lt, un, un, lt, lt, gt, gt, lt, lt, lt, lt, lt, lt, un, un}, //  4
-                {gt, gt, gt, lt, gt, eq, gt, lt, un, un, lt, lt, gt, gt, lt, lt, lt, lt, lt, lt, un, un}, //  5
-                {gt, gt, gt, lt, lt, lt, eq, lt, un, un, lt, lt, gt, gt, lt, lt, lt, lt, lt, lt, un, un}, //  6
-                {gt, gt, gt, lt, gt, gt, gt, eq, un, un, lt, lt, gt, gt, lt, lt, lt, lt, lt, lt, un, un}, //  7
-                {gt, gt, un, un, un, un, un, un, un, un, lt, lt, gt, gt, lt, lt, lt, lt, lt, lt, un, un}, //  8
-                {gt, gt, un, un, un, un, un, un, un, un, lt, lt, gt, gt, lt, lt, lt, lt, lt, lt, un, un}, //  9
-                {gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, eq, gt, gt, gt, gt, gt, gt, gt, lt, lt, un, un}, // 10
-                {gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, lt, eq, gt, gt, gt, gt, gt, gt, lt, lt, un, un}, // 11
-                {gt, gt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, eq, gt, lt, lt, lt, lt, lt, lt, un, un}, // 12
-                {gt, gt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, eq, lt, lt, lt, lt, lt, lt, un, un}, // 13
-                {gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, lt, lt, gt, gt, eq, lt, gt, gt, lt, lt, un, un}, // 14
-                {gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, lt, lt, gt, gt, gt, eq, gt, gt, lt, lt, un, un}, // 15
-                {gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, lt, lt, gt, gt, lt, lt, eq, gt, lt, lt, un, un}, // 16
-                {gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, lt, lt, gt, gt, lt, lt, lt, eq, lt, lt, un, un}, // 17
-                {gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, eq, lt, un, un}, // 18
-                {gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, eq, un, un}, // 19
-                {un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un}, // 20
-                {un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un}, // 21
-            };
-
-            // check expected partial_ordering against expected booleans
-            REQUIRE(expected.size() == expected_eq.size());
-            REQUIRE(expected.size() == expected_lt.size());
-            for (size_t i = 0; i < expected.size(); ++i)
-            {
-                REQUIRE(expected[i].size() == expected_eq[i].size());
-                REQUIRE(expected[i].size() == expected_lt[i].size());
-                for (size_t j = 0; j < expected[i].size(); ++j)
-                {
-                    CAPTURE(i)
-                    CAPTURE(j)
-                    CHECK(std::is_eq(expected[i][j]) == expected_eq[i][j]);
-                    CHECK(std::is_lt(expected[i][j]) == expected_lt[i][j]);
-                    if (std::is_gt(expected[i][j]))
-                    {
-                        CHECK((!expected_eq[i][j] && !expected_lt[i][j]));
-                    }
-                }
-            }
-
-            // check that two values compare according to their expected ordering
-            REQUIRE(expected.size() == j_values.size());
-            for (size_t i = 0; i < j_values.size(); ++i)
-            {
-                REQUIRE(expected[i].size() == j_values.size());
-                for (size_t j = 0; j < j_values.size(); ++j)
-                {
-                    CAPTURE(i)
-                    CAPTURE(j)
-                    CHECK((j_values[i] <=> j_values[j]) == expected[i][j]); // *NOPAD*
-                }
-            }
-        }
-    }
-
-}
-
-TEST_CASE("regression #3868 - heterogeneous comparisons compile under C++20 (P2468R2)")
-{
-    // Issue #3868: operator!= was preventing compiler from synthesizing reversed
-    // operator== candidates under C++20's P2468R2 rewritten candidate rules.
-    // Verify that heterogeneous comparisons now work.
-
-    SECTION("string vs json")
-    {
-        std::string s = "string";
-        json j = "string";
-        CHECK(s == j);
-        CHECK(j == s);
-        CHECK_FALSE(s != j);
-        CHECK_FALSE(j != s);
-    }
-
-    SECTION("other heterogeneous types")
-    {
-        int i = 42;
-        json j = 42;
-        CHECK(i == j);
-        CHECK(j == i);
-        CHECK_FALSE(i != j);
-        CHECK_FALSE(j != i);
-    }
-}
-
-#if JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON
-TEST_CASE("regression #5665 - scalar <= discarded and scalar >= discarded in C++20 legacy mode")
-{
-    // Issue #5665: with a scalar on the left-hand side, <= and >= only had the
-    // candidate rewritten from operator<=>, which does not emulate the legacy
-    // discarded-value behavior. Check that scalar-on-the-left now matches the
-    // other three operand orders.
-    const json discarded(json::value_t::discarded);
-    const json one = 1;
-
-    CHECK(discarded <= 1);
-    CHECK(discarded >= 1);
-    CHECK(one <= discarded);
-    CHECK(one >= discarded);
-    CHECK(1 <= discarded);
-    CHECK(1 >= discarded);
-    CHECK(1.5 <= discarded);
-    CHECK(1.5 >= discarded);
-}
-
-#endif
-
-TEST_CASE("containers are compared element by element (C++20)")
-{
-    // Containers nested deeper than a bound are compared without the call
-    // stack, by code of their own; every relation is checked both at the top
-    // level and below that bound.
-    const auto deep = [](const json & j, const std::size_t depth)
-    {
-        json result = j;
-        for (std::size_t i = 0; i < depth; ++i)
-        {
-            result = json::array({std::move(result)});
-        }
-        return result;
-    };
-
-    for (const std::size_t depth : std::vector<std::size_t> {0, 200})
-    {
-        CAPTURE(depth)
-
-        // objects with different keys
-        {
-            const json a = deep({{"a", 1}}, depth);
-            const json b = deep({{"b", 1}}, depth);
-            CHECK((a <=> b) == std::partial_ordering::less); // *NOPAD*
-            CHECK((b <=> a) == std::partial_ordering::greater); // *NOPAD*
-            CHECK((a <=> a) == std::partial_ordering::equivalent); // *NOPAD*
-        }
-
-        // a container that is a prefix of the other one
-        {
-            // the one that runs out of elements first is the smaller one
-            const json shorter = deep({1}, depth);
-            const json longer = deep({1, 2}, depth);
-
-            const json smaller_object = deep({{"a", 1}}, depth);
-            const json larger_object = deep({{"a", 1}, {"b", 2}}, depth);
-            CHECK((shorter <=> longer) == std::partial_ordering::less); // *NOPAD*
-            CHECK((longer <=> shorter) == std::partial_ordering::greater); // *NOPAD*
-        }
-
-        // elements that cannot be ordered
-        {
-            const double nan = std::numeric_limits<double>::quiet_NaN();
-            const json lhs = deep({nan, 1}, depth);
-            const json rhs = deep({nan, 2}, depth);
-            // operator<=> stops there, as std::lexicographical_compare_three_way
-            // does, and operator< is derived from it
-            CHECK((lhs <=> rhs) == std::partial_ordering::unordered); // *NOPAD*
-            CHECK_FALSE(lhs < rhs);
-        }
-    }
-}
-
-TEST_CASE("operator<=> of binary values with a different subtype does not depend on nesting depth")
-{
-    // #5654: std::vector<std::uint8_t>::operator<=>, which the binary type's
-    // own operator<=> uses, ignores the subtype that operator== checks. So a
-    // pair of binary values with the same bytes but a different subtype is
-    // unequal, yet <=>-equivalent - the same inconsistency between == and <=>
-    // that a NaN has. Within the nesting bound, an array compares itself
-    // with std::vector's own operator<=>, which treats an equivalent pair as
-    // undecided and lets the next element decide, same as
-    // std::lexicographical_compare_three_way does. Past the bound,
-    // compare_iteratively<true>() takes over and must classify the pair the
-    // same way, or the result of operator<=> - and of <, which C++20 derives
-    // from it - depends on how deeply the values are nested.
-    const json a = json::array({json::binary({1}, 1), 1});
-    const json b = json::array({json::binary({1}, 2), 2});
-
-    // the root inconsistency: unequal, yet <=>-equivalent
-    CHECK_FALSE(a[0] == b[0]);
-    CHECK((a[0] <=> b[0]) == std::partial_ordering::equivalent); // *NOPAD*
-
-    const auto deep = [](const json & j, const std::size_t depth)
-    {
-        json result = j;
-        for (std::size_t i = 0; i < depth; ++i)
-        {
-            result = json::array({std::move(result)});
-        }
-        return result;
-    };
-
-    // 127 levels stay within nesting_depth_limit() (128); 128 and 200 do not,
-    // and must still agree with the levels that do
-    for (const std::size_t depth : std::vector<std::size_t> {0, 127, 128, 200})
-    {
-        CAPTURE(depth)
-        const json x = deep(a, depth);
-        const json y = deep(b, depth);
-        CHECK((x <=> y) == std::partial_ordering::less); // *NOPAD*
-        CHECK((y <=> x) == std::partial_ordering::greater); // *NOPAD*
-        CHECK(x < y);
-        CHECK(y > x);
-        CHECK_FALSE(y < x);
-    }
-}
-
-TEST_CASE("comparison of scalars (inline fast path): operator<=>")
-{
-    // the three-way part of "comparison of scalars (inline fast path)" in
-    // unit-comparison.cpp, which is built for C++11 only
-    const json::number_integer_t neg = -1;
-
-    SECTION("NaN")
-    {
-        const json nan = std::numeric_limits<json::number_float_t>::quiet_NaN();
-        const json one = 1.0;
-        CHECK((nan <=> nan) == std::partial_ordering::unordered); // *NOPAD*
-        CHECK((nan <=> one) == std::partial_ordering::unordered); // *NOPAD*
-        CHECK((one <=> nan) == std::partial_ordering::unordered); // *NOPAD*
-        CHECK((one <=> json(2.0)) == std::partial_ordering::less); // *NOPAD*
-        CHECK((json(2.0) <=> one) == std::partial_ordering::greater); // *NOPAD*
-        CHECK((one <=> one) == std::partial_ordering::equivalent); // *NOPAD*
-        CHECK((json(neg) <=> json(1u)) == std::partial_ordering::less); // *NOPAD*
-        CHECK((json(nullptr) <=> json(nullptr)) == std::partial_ordering::equivalent); // *NOPAD*
-        CHECK((json(true) <=> json(false)) == std::partial_ordering::greater); // *NOPAD*
-    }
-
-    SECTION("discarded")
-    {
-        const json d(json::value_t::discarded);
-        CHECK((d <=> d) == std::partial_ordering::unordered); // *NOPAD*
-        CHECK((d <=> json(1)) == std::partial_ordering::unordered); // *NOPAD*
-        CHECK((json(1) <=> d) == std::partial_ordering::unordered); // *NOPAD*
-    }
-}
-
-#endif // JSON_HAS_THREE_WAY_COMPARISON
-#endif

tests/src/unit-comparison.cpp

@@ -6,11 +6,12 @@
 // SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
 // SPDX-License-Identifier: MIT
 
-// cmake/test.cmake builds a unit test with C++ standards beyond C++11 only if the
+// cmake/test.cmake selects the C++ standard versions with which to build a
-// source file mentions the corresponding version macro. To avoid rebuilding this
+// unit test based on the presence of JSON_HAS_CPP_<VERSION> macros.
-// large file for every standard, tests that depend on the standard version (e.g.,
+// When using macros that are only defined for particular versions of the standard
-// those using JSON_HAS_FILESYSTEM, JSON_HAS_RANGES, or JSON_HAS_THREE_WAY_COMPARISON)
+// (e.g., JSON_HAS_FILESYSTEM for C++17 and up), please mention the corresponding
-// go into a separate file unit-comparison-cpp<NN>.cpp. This file stays C++11-only.
+// version macro in a comment close by, like this:
+// JSON_HAS_CPP_<VERSION> (do not remove; see note at top of file)
 
 #include "doctest_compatibility.h"
 
@@ -28,6 +29,37 @@
 #include <nlohmann/json.hpp>
 using nlohmann::json;
 
+#if JSON_HAS_THREE_WAY_COMPARISON
+// this can be replaced with the doctest stl extension header in version 2.5
+namespace doctest
+{
+template<> struct StringMaker<std::partial_ordering>
+{
+    static String convert(const std::partial_ordering& order)
+    {
+        if (order == std::partial_ordering::less)
+        {
+            return "std::partial_ordering::less";
+        }
+        if (order == std::partial_ordering::equivalent)
+        {
+            return "std::partial_ordering::equivalent";
+        }
+        if (order == std::partial_ordering::greater)
+        {
+            return "std::partial_ordering::greater";
+        }
+        if (order == std::partial_ordering::unordered)
+        {
+            return "std::partial_ordering::unordered";
+        }
+        return "{?}";
+    }
+};
+} // namespace doctest
+
+#endif
+
 namespace
 {
 // helper function to check std::less<json::value_t>
@@ -44,6 +76,16 @@ TEST_CASE("lexicographical comparison operators")
     constexpr auto f_ = false;
     constexpr auto _t = true;
     constexpr auto nan = std::numeric_limits<json::number_float_t>::quiet_NaN();
+#if JSON_HAS_THREE_WAY_COMPARISON
+    constexpr auto lt = std::partial_ordering::less;
+    constexpr auto gt = std::partial_ordering::greater;
+    constexpr auto eq = std::partial_ordering::equivalent;
+    constexpr auto un = std::partial_ordering::unordered;
+#endif
+
+#if JSON_HAS_THREE_WAY_COMPARISON
+    INFO("using 3-way comparison");
+#endif
 
 #if JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON
     INFO("using legacy comparison");
@@ -94,13 +136,62 @@ TEST_CASE("lexicographical comparison operators")
                     CAPTURE(i)
                     CAPTURE(j)
                     // check precomputed values
-#if !JSON_HAS_THREE_WAY_COMPARISON
+#if JSON_HAS_THREE_WAY_COMPARISON
+                    // JSON_HAS_CPP_20 (do not remove; see note at top of file)
+                    CHECK((j_types[i] < j_types[j]) == expected_lt[i][j]);
+#else
                     CHECK(operator<(j_types[i], j_types[j]) == expected_lt[i][j]);
 #endif
                     CHECK(f(j_types[i], j_types[j]) == expected_lt[i][j]);
                 }
             }
         }
+#if JSON_HAS_THREE_WAY_COMPARISON
+        // JSON_HAS_CPP_20 (do not remove; see note at top of file)
+        SECTION("comparison: 3-way")
+        {
+            std::vector<std::vector<std::partial_ordering>> expected =
+            {
+                //0   1   2   3   4   5   6   7   8   9
+                {eq, lt, lt, lt, lt, lt, lt, lt, lt, un}, //  0
+                {gt, eq, lt, lt, lt, lt, lt, lt, lt, un}, //  1
+                {gt, gt, eq, eq, eq, lt, lt, lt, lt, un}, //  2
+                {gt, gt, eq, eq, eq, lt, lt, lt, lt, un}, //  3
+                {gt, gt, eq, eq, eq, lt, lt, lt, lt, un}, //  4
+                {gt, gt, gt, gt, gt, eq, lt, lt, lt, un}, //  5
+                {gt, gt, gt, gt, gt, gt, eq, lt, lt, un}, //  6
+                {gt, gt, gt, gt, gt, gt, gt, eq, lt, un}, //  7
+                {gt, gt, gt, gt, gt, gt, gt, gt, eq, un}, //  8
+                {un, un, un, un, un, un, un, un, un, un}, //  9
+            };
+
+            // check expected partial_ordering against expected boolean
+            REQUIRE(expected.size() == expected_lt.size());
+            for (size_t i = 0; i < expected.size(); ++i)
+            {
+                REQUIRE(expected[i].size() == expected_lt[i].size());
+                for (size_t j = 0; j < expected[i].size(); ++j)
+                {
+                    CAPTURE(i)
+                    CAPTURE(j)
+                    CHECK(std::is_lt(expected[i][j]) == expected_lt[i][j]);
+                }
+            }
+
+            // check 3-way comparison against expected partial_ordering
+            REQUIRE(expected.size() == j_types.size());
+            for (size_t i = 0; i < j_types.size(); ++i)
+            {
+                REQUIRE(expected[i].size() == j_types.size());
+                for (size_t j = 0; j < j_types.size(); ++j)
+                {
+                    CAPTURE(i)
+                    CAPTURE(j)
+                    CHECK((j_types[i] <=> j_types[j]) == expected[i][j]); // *NOPAD*
+                }
+            }
+        }
+#endif
     }
 
     SECTION("values")
@@ -229,6 +320,18 @@ TEST_CASE("lexicographical comparison operators")
             CHECK_FALSE(above_int64_max <= max_int64);
             CHECK(above_int64_max > max_int64);
             CHECK(above_int64_max >= max_int64);
+
+#if JSON_HAS_THREE_WAY_COMPARISON
+            // JSON_HAS_CPP_20 (do not remove; see note at top of file)
+            CHECK((negative_one <=> above_int64_max) == std::partial_ordering::less); // *NOPAD*
+            CHECK((above_int64_max <=> negative_one) == std::partial_ordering::greater); // *NOPAD*
+            CHECK((negative_one <=> max_uint64) == std::partial_ordering::less); // *NOPAD*
+            CHECK((max_uint64 <=> negative_one) == std::partial_ordering::greater); // *NOPAD*
+            CHECK((one <=> above_int64_max) == std::partial_ordering::less); // *NOPAD*
+            CHECK((above_int64_max <=> one) == std::partial_ordering::greater); // *NOPAD*
+            CHECK((max_int64 <=> above_int64_max) == std::partial_ordering::less); // *NOPAD*
+            CHECK((above_int64_max <=> max_int64) == std::partial_ordering::greater); // *NOPAD*
+#endif
         }
 
         SECTION("integer/float mixed comparison is exact")
@@ -279,6 +382,16 @@ TEST_CASE("lexicographical comparison operators")
             CHECK_FALSE(json(1) < json(nan));
             CHECK_FALSE(json(nan) < json(1));
             CHECK_FALSE(json(1u) == json(nan));
+
+#if JSON_HAS_THREE_WAY_COMPARISON
+            // JSON_HAS_CPP_20 (do not remove; see note at top of file)
+            CHECK((max_int64 <=> two_63) == std::partial_ordering::less); // *NOPAD*
+            CHECK((two_63 <=> max_int64) == std::partial_ordering::greater); // *NOPAD*
+            CHECK((below_two_63 <=> max_int64) == std::partial_ordering::less); // *NOPAD*
+            CHECK((max_uint64 <=> two_64) == std::partial_ordering::less); // *NOPAD*
+            CHECK((json(1) <=> json(1.0)) == std::partial_ordering::equivalent); // *NOPAD*
+            CHECK((json(1) <=> json(nan)) == std::partial_ordering::unordered); // *NOPAD*
+#endif
         }
 
         SECTION("compares unordered")
@@ -505,6 +618,72 @@ TEST_CASE("lexicographical comparison operators")
                 }
             }
         }
+
+#if JSON_HAS_THREE_WAY_COMPARISON
+        // JSON_HAS_CPP_20 (do not remove; see note at top of file)
+        SECTION("comparison: 3-way")
+        {
+            std::vector<std::vector<std::partial_ordering>> expected =
+            {
+                //0   1   2   3   4   5   6   7   8   9  10  11  12  13  14  15  16  17  18  19  20  21
+                {eq, eq, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, un, un}, //  0
+                {eq, eq, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, un, un}, //  1
+                {gt, gt, eq, lt, lt, lt, lt, lt, un, un, lt, lt, gt, gt, lt, lt, lt, lt, lt, lt, un, un}, //  2
+                {gt, gt, gt, eq, gt, gt, gt, gt, un, un, lt, lt, gt, gt, lt, lt, lt, lt, lt, lt, un, un}, //  3
+                {gt, gt, gt, lt, eq, lt, gt, lt, un, un, lt, lt, gt, gt, lt, lt, lt, lt, lt, lt, un, un}, //  4
+                {gt, gt, gt, lt, gt, eq, gt, lt, un, un, lt, lt, gt, gt, lt, lt, lt, lt, lt, lt, un, un}, //  5
+                {gt, gt, gt, lt, lt, lt, eq, lt, un, un, lt, lt, gt, gt, lt, lt, lt, lt, lt, lt, un, un}, //  6
+                {gt, gt, gt, lt, gt, gt, gt, eq, un, un, lt, lt, gt, gt, lt, lt, lt, lt, lt, lt, un, un}, //  7
+                {gt, gt, un, un, un, un, un, un, un, un, lt, lt, gt, gt, lt, lt, lt, lt, lt, lt, un, un}, //  8
+                {gt, gt, un, un, un, un, un, un, un, un, lt, lt, gt, gt, lt, lt, lt, lt, lt, lt, un, un}, //  9
+                {gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, eq, gt, gt, gt, gt, gt, gt, gt, lt, lt, un, un}, // 10
+                {gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, lt, eq, gt, gt, gt, gt, gt, gt, lt, lt, un, un}, // 11
+                {gt, gt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, eq, gt, lt, lt, lt, lt, lt, lt, un, un}, // 12
+                {gt, gt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, lt, eq, lt, lt, lt, lt, lt, lt, un, un}, // 13
+                {gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, lt, lt, gt, gt, eq, lt, gt, gt, lt, lt, un, un}, // 14
+                {gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, lt, lt, gt, gt, gt, eq, gt, gt, lt, lt, un, un}, // 15
+                {gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, lt, lt, gt, gt, lt, lt, eq, gt, lt, lt, un, un}, // 16
+                {gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, lt, lt, gt, gt, lt, lt, lt, eq, lt, lt, un, un}, // 17
+                {gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, eq, lt, un, un}, // 18
+                {gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, gt, eq, un, un}, // 19
+                {un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un}, // 20
+                {un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un, un}, // 21
+            };
+
+            // check expected partial_ordering against expected booleans
+            REQUIRE(expected.size() == expected_eq.size());
+            REQUIRE(expected.size() == expected_lt.size());
+            for (size_t i = 0; i < expected.size(); ++i)
+            {
+                REQUIRE(expected[i].size() == expected_eq[i].size());
+                REQUIRE(expected[i].size() == expected_lt[i].size());
+                for (size_t j = 0; j < expected[i].size(); ++j)
+                {
+                    CAPTURE(i)
+                    CAPTURE(j)
+                    CHECK(std::is_eq(expected[i][j]) == expected_eq[i][j]);
+                    CHECK(std::is_lt(expected[i][j]) == expected_lt[i][j]);
+                    if (std::is_gt(expected[i][j]))
+                    {
+                        CHECK((!expected_eq[i][j] && !expected_lt[i][j]));
+                    }
+                }
+            }
+
+            // check that two values compare according to their expected ordering
+            REQUIRE(expected.size() == j_values.size());
+            for (size_t i = 0; i < j_values.size(); ++i)
+            {
+                REQUIRE(expected[i].size() == j_values.size());
+                for (size_t j = 0; j < j_values.size(); ++j)
+                {
+                    CAPTURE(i)
+                    CAPTURE(j)
+                    CHECK((j_values[i] <=> j_values[j]) == expected[i][j]); // *NOPAD*
+                }
+            }
+        }
+#endif
     }
 
 #if JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON
@@ -543,7 +722,60 @@ TEST_CASE("lexicographical comparison operators")
 #endif
 }
 
-namespace unit_comparison_detail
+#if JSON_HAS_THREE_WAY_COMPARISON
+// JSON_HAS_CPP_20 (do not remove; see note at top of file)
+
+TEST_CASE("regression #3868 - heterogeneous comparisons compile under C++20 (P2468R2)")
+{
+    // Issue #3868: operator!= was preventing compiler from synthesizing reversed
+    // operator== candidates under C++20's P2468R2 rewritten candidate rules.
+    // Verify that heterogeneous comparisons now work.
+
+    SECTION("string vs json")
+    {
+        std::string s = "string";
+        json j = "string";
+        CHECK(s == j);
+        CHECK(j == s);
+        CHECK_FALSE(s != j);
+        CHECK_FALSE(j != s);
+    }
+
+    SECTION("other heterogeneous types")
+    {
+        int i = 42;
+        json j = 42;
+        CHECK(i == j);
+        CHECK(j == i);
+        CHECK_FALSE(i != j);
+        CHECK_FALSE(j != i);
+    }
+}
+
+#if JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON
+TEST_CASE("regression #5665 - scalar <= discarded and scalar >= discarded in C++20 legacy mode")
+{
+    // Issue #5665: with a scalar on the left-hand side, <= and >= only had the
+    // candidate rewritten from operator<=>, which does not emulate the legacy
+    // discarded-value behavior. Check that scalar-on-the-left now matches the
+    // other three operand orders.
+    const json discarded(json::value_t::discarded);
+    const json one = 1;
+
+    CHECK(discarded <= 1);
+    CHECK(discarded >= 1);
+    CHECK(one <= discarded);
+    CHECK(one >= discarded);
+    CHECK(1 <= discarded);
+    CHECK(1 >= discarded);
+    CHECK(1.5 <= discarded);
+    CHECK(1.5 >= discarded);
+}
+#endif
+
+#endif
+
+namespace
 {
 // orders keys ascending or descending, as chosen when a map is created
 template<class Key>
@@ -595,6 +827,29 @@ struct unordered_object_t : std::map<Key, Value, directed_less<Key>, Allocator>
 };
 using unordered_json = nlohmann::json::with_object_t<unordered_object_t>;
 
+// the entries "0" to "9", enumerated in ascending or in descending order
+unordered_json make_unordered_object(const bool descending)
+{
+    unordered_json j = unordered_json::object_t(directed_less<std::string>(descending));
+    for (int i = 0; i < 10; ++i)
+    {
+        j[std::to_string(i)] = i;
+    }
+    return j;
+}
+
+template<typename Json>
+Json nest(Json j, const std::size_t depth)
+{
+    for (std::size_t i = 0; i < depth; ++i)
+    {
+        Json outer = Json::object();
+        outer["x"] = std::move(j);
+        j = std::move(outer);
+    }
+    return j;
+}
+
 // a std::map comparator with state: case-insensitive, unless constructed
 // case-sensitive. Used to check that copying an object copies the original's
 // comparator rather than default-constructing a new one (see #5649).
@@ -623,6 +878,18 @@ template<class Key, class Value, class /*Compare*/, class Allocator>
 using key_case_map = std::map<Key, Value, key_case_less, Allocator>;
 using key_case_json = nlohmann::json::with_object_t<key_case_map>;
 
+// the innermost value of a chain of single-element arrays
+template<typename Json>
+const Json& innermost(const Json& j)
+{
+    const Json* p = &j;
+    while (p->is_array())
+    {
+        p = &(*p)[0];
+    }
+    return *p;
+}
+
 // orders keys case-insensitively, so "key" and "KEY" compare equivalent
 // (neither less than the other) although they are not equal
 struct case_insensitive_less
@@ -640,58 +907,7 @@ struct case_insensitive_less
 template<class Key, class Value, class /*Compare*/, class Allocator>
 using case_insensitive_map = std::map<Key, Value, case_insensitive_less, Allocator>;
 using ci_json = nlohmann::json::with_object_t<case_insensitive_map>;
-
-// the types above keep external linkage: a basic_json specialized with a type
-// of an anonymous namespace has internal linkage, which GCC reports in a file
-// #include-d into a batch (-Wsubobject-linkage); the functions need none
-namespace
-{
-// the entries "0" to "9", enumerated in ascending or in descending order
-unordered_json make_unordered_object(const bool descending)
-{
-    unordered_json j = unordered_json::object_t(directed_less<std::string>(descending));
-    for (int i = 0; i < 10; ++i)
-    {
-        j[std::to_string(i)] = i;
-    }
-    return j;
-}
-
-template<typename Json>
-Json nest(Json j, const std::size_t depth)
-{
-    for (std::size_t i = 0; i < depth; ++i)
-    {
-        Json outer = Json::object();
-        outer["x"] = std::move(j);
-        j = std::move(outer);
-    }
-    return j;
-}
-
-// the innermost value of a chain of single-element arrays
-template<typename Json>
-const Json& innermost(const Json& j)
-{
-    const Json* p = &j;
-    while (p->is_array())
-    {
-        p = &(*p)[0];
-    }
-    return *p;
-}
 } // namespace
-} // namespace unit_comparison_detail
-
-// using-declarations rather than a using-directive, as this file may be
-// #include-d into a batch with other test files (JSON_TestUnityBuild)
-using unit_comparison_detail::ci_json;
-using unit_comparison_detail::innermost;
-using unit_comparison_detail::key_case_json;
-using unit_comparison_detail::key_case_less;
-using unit_comparison_detail::make_unordered_object;
-using unit_comparison_detail::nest;
-using unit_comparison_detail::unordered_json;
 
 TEST_CASE("equality of objects whose entries have no fixed order")
 {
@@ -834,6 +1050,12 @@ TEST_CASE("containers are compared element by element")
             CHECK(a < b);
             CHECK(b > a);
             CHECK_FALSE(b < a);
+#if JSON_HAS_THREE_WAY_COMPARISON
+            // JSON_HAS_CPP_20 (do not remove; see note at top of file)
+            CHECK((a <=> b) == std::partial_ordering::less); // *NOPAD*
+            CHECK((b <=> a) == std::partial_ordering::greater); // *NOPAD*
+            CHECK((a <=> a) == std::partial_ordering::equivalent); // *NOPAD*
+#endif
         }
 
         // a container that is a prefix of the other one
@@ -851,6 +1073,11 @@ TEST_CASE("containers are compared element by element")
             CHECK(smaller_object < larger_object);
             CHECK(larger_object > smaller_object);
             CHECK_FALSE(smaller_object == larger_object);
+#if JSON_HAS_THREE_WAY_COMPARISON
+            // JSON_HAS_CPP_20 (do not remove; see note at top of file)
+            CHECK((shorter <=> longer) == std::partial_ordering::less); // *NOPAD*
+            CHECK((longer <=> shorter) == std::partial_ordering::greater); // *NOPAD*
+#endif
         }
 
         // elements that cannot be ordered
@@ -861,7 +1088,13 @@ TEST_CASE("containers are compared element by element")
 
             CHECK_FALSE(lhs == lhs);
             CHECK_FALSE(rhs < lhs);
-#if !JSON_HAS_THREE_WAY_COMPARISON
+#if JSON_HAS_THREE_WAY_COMPARISON
+            // JSON_HAS_CPP_20 (do not remove; see note at top of file)
+            // operator<=> stops there, as std::lexicographical_compare_three_way
+            // does, and operator< is derived from it
+            CHECK((lhs <=> rhs) == std::partial_ordering::unordered); // *NOPAD*
+            CHECK_FALSE(lhs < rhs);
+#else
             // operator< skips a pair of elements that cannot be ordered, as
             // std::lexicographical_compare does, and the next pair decides
             CHECK(lhs < rhs);
@@ -870,6 +1103,54 @@ TEST_CASE("containers are compared element by element")
     }
 }
 
+#if JSON_HAS_THREE_WAY_COMPARISON
+// JSON_HAS_CPP_20 (do not remove; see note at top of file)
+TEST_CASE("operator<=> of binary values with a different subtype does not depend on nesting depth")
+{
+    // #5654: std::vector<std::uint8_t>::operator<=>, which the binary type's
+    // own operator<=> uses, ignores the subtype that operator== checks. So a
+    // pair of binary values with the same bytes but a different subtype is
+    // unequal, yet <=>-equivalent - the same inconsistency between == and <=>
+    // that a NaN has. Within the nesting bound, an array compares itself
+    // with std::vector's own operator<=>, which treats an equivalent pair as
+    // undecided and lets the next element decide, same as
+    // std::lexicographical_compare_three_way does. Past the bound,
+    // compare_iteratively<true>() takes over and must classify the pair the
+    // same way, or the result of operator<=> - and of <, which C++20 derives
+    // from it - depends on how deeply the values are nested.
+    const json a = json::array({json::binary({1}, 1), 1});
+    const json b = json::array({json::binary({1}, 2), 2});
+
+    // the root inconsistency: unequal, yet <=>-equivalent
+    CHECK_FALSE(a[0] == b[0]);
+    CHECK((a[0] <=> b[0]) == std::partial_ordering::equivalent); // *NOPAD*
+
+    const auto deep = [](const json & j, const std::size_t depth)
+    {
+        json result = j;
+        for (std::size_t i = 0; i < depth; ++i)
+        {
+            result = json::array({std::move(result)});
+        }
+        return result;
+    };
+
+    // 127 levels stay within nesting_depth_limit() (128); 128 and 200 do not,
+    // and must still agree with the levels that do
+    for (const std::size_t depth : std::vector<std::size_t> {0, 127, 128, 200})
+    {
+        CAPTURE(depth)
+        const json x = deep(a, depth);
+        const json y = deep(b, depth);
+        CHECK((x <=> y) == std::partial_ordering::less); // *NOPAD*
+        CHECK((y <=> x) == std::partial_ordering::greater); // *NOPAD*
+        CHECK(x < y);
+        CHECK(y > x);
+        CHECK_FALSE(y < x);
+    }
+}
+#endif
+
 TEST_CASE("comparison of scalars (inline fast path)")
 {
     const json::number_integer_t neg = -1;
@@ -968,6 +1249,17 @@ TEST_CASE("comparison of scalars (inline fast path)")
         CHECK_FALSE(nan < json(1u));
         CHECK_FALSE(json(1u) < nan);
 
+#if JSON_HAS_THREE_WAY_COMPARISON
+        CHECK((nan <=> nan) == std::partial_ordering::unordered); // *NOPAD*
+        CHECK((nan <=> one) == std::partial_ordering::unordered); // *NOPAD*
+        CHECK((one <=> nan) == std::partial_ordering::unordered); // *NOPAD*
+        CHECK((one <=> json(2.0)) == std::partial_ordering::less); // *NOPAD*
+        CHECK((json(2.0) <=> one) == std::partial_ordering::greater); // *NOPAD*
+        CHECK((one <=> one) == std::partial_ordering::equivalent); // *NOPAD*
+        CHECK((json(neg) <=> json(1u)) == std::partial_ordering::less); // *NOPAD*
+        CHECK((json(nullptr) <=> json(nullptr)) == std::partial_ordering::equivalent); // *NOPAD*
+        CHECK((json(true) <=> json(false)) == std::partial_ordering::greater); // *NOPAD*
+#endif
     }
 
     SECTION("discarded")
@@ -983,6 +1275,11 @@ TEST_CASE("comparison of scalars (inline fast path)")
         CHECK_FALSE(d == json(nullptr));
         CHECK_FALSE(json(nullptr) == d);
 
+#if JSON_HAS_THREE_WAY_COMPARISON
+        CHECK((d <=> d) == std::partial_ordering::unordered); // *NOPAD*
+        CHECK((d <=> json(1)) == std::partial_ordering::unordered); // *NOPAD*
+        CHECK((json(1) <=> d) == std::partial_ordering::unordered); // *NOPAD*
+#endif
     }
 
     SECTION("scalar overloads")

tests/src/unit-conversions1-cpp17.cpp

@@ -1,95 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++ (supporting code)
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-License-Identifier: MIT
-
-// This file contains the C++17-only part of unit-conversions1.cpp (conversions to and from
-// std::string_view). It is kept in a separate translation unit so the (much larger) unit-
-// conversions1.cpp is built for C++11 only and not rebuilt for every C++ standard.
-
-#include "doctest_compatibility.h"
-
-#include <nlohmann/json.hpp>
-using nlohmann::json;
-
-// workaround for MSVC, which does not set __cplusplus to the language version (#464)
-#if (defined(__cplusplus) && __cplusplus >= 201703L) || (defined(_HAS_CXX17) && _HAS_CXX17 == 1) // fix for issue #464
-    #define JSON_HAS_CPP_17
-#endif
-
-#ifdef JSON_HAS_CPP_17
-#include <string>
-#include <string_view>
-
-#if __has_include(<optional>)
-    #include <optional>
-#elif __has_include(<experimental/optional>)
-    #include <experimental/optional>
-#endif
-
-TEST_CASE("value conversion (C++17)")
-{
-    SECTION("get a string (explicit)")
-    {
-        const json::string_t s_reference{"Hello world"};
-        json j(s_reference);
-
-        SECTION("std::string_view")
-        {
-            std::string_view const s = j.get<std::string_view>();
-            CHECK(json(s) == j);
-        }
-
-        SECTION("exception in case of a non-string type using string_view")
-        {
-            CHECK_THROWS_WITH_AS(json(json::value_t::null).get<std::string_view>(),
-                                 "[json.exception.type_error.302] type must be string, but is null", json::type_error&);
-            CHECK_THROWS_WITH_AS(json(json::value_t::object).get<std::string_view>(),
-                                 "[json.exception.type_error.302] type must be string, but is object", json::type_error&);
-            CHECK_THROWS_WITH_AS(json(json::value_t::array).get<std::string_view>(),
-                                 "[json.exception.type_error.302] type must be string, but is array", json::type_error&);
-            CHECK_THROWS_WITH_AS(json(json::value_t::boolean).get<std::string_view>(),
-                                 "[json.exception.type_error.302] type must be string, but is boolean", json::type_error&);
-            CHECK_THROWS_WITH_AS(json(json::value_t::number_integer).get<std::string_view>(),
-                                 "[json.exception.type_error.302] type must be string, but is number", json::type_error&);
-            CHECK_THROWS_WITH_AS(json(json::value_t::number_unsigned).get<std::string_view>(),
-                                 "[json.exception.type_error.302] type must be string, but is number", json::type_error&);
-            CHECK_THROWS_WITH_AS(json(json::value_t::number_float).get<std::string_view>(),
-                                 "[json.exception.type_error.302] type must be string, but is number", json::type_error&);
-        }
-    }
-
-    SECTION("get a string (explicit, get_to)")
-    {
-        const json::string_t s_reference{"Hello world"};
-        json j(s_reference);
-
-        SECTION("std::string_view")
-        {
-            std::string const s = "previous value";
-            std::string_view sv = s;
-            j.get_to(sv);
-            CHECK(json(sv) == j);
-        }
-    }
-
-#if JSON_USE_IMPLICIT_CONVERSIONS
-    SECTION("get a string (implicit)")
-    {
-        const json::string_t s_reference{"Hello world"};
-        json j(s_reference);
-
-        SECTION("std::string_view")
-        {
-            std::string_view const s = j.get<std::string_view>();
-            CHECK(json(s) == j);
-        }
-    }
-#endif
-
-}
-
-#endif

tests/src/unit-conversions1.cpp

@@ -6,11 +6,12 @@
 // SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
 // SPDX-License-Identifier: MIT
 
-// cmake/test.cmake builds a unit test with C++ standards beyond C++11 only if the
+// cmake/test.cmake selects the C++ standard versions with which to build a
-// source file mentions the corresponding version macro. To avoid rebuilding this
+// unit test based on the presence of JSON_HAS_CPP_<VERSION> macros.
-// large file for every standard, tests that depend on the standard version (e.g.,
+// When using macros that are only defined for particular versions of the standard
-// those using JSON_HAS_FILESYSTEM, JSON_HAS_RANGES, or JSON_HAS_THREE_WAY_COMPARISON)
+// (e.g., JSON_HAS_FILESYSTEM for C++17 and up), please mention the corresponding
-// go into a separate file unit-conversions1-cpp<NN>.cpp. This file stays C++11-only.
+// version macro in a comment close by, like this:
+// JSON_HAS_CPP_<VERSION> (do not remove; see note at top of file)
 
 #include "doctest_compatibility.h"
 
@@ -30,6 +31,25 @@ using nlohmann::json;
 DOCTEST_CLANG_SUPPRESS_WARNING_PUSH
 DOCTEST_CLANG_SUPPRESS_WARNING("-Wexit-time-destructors")
 
+#if (defined(__cplusplus) && __cplusplus >= 201703L) || (defined(_HAS_CXX17) && _HAS_CXX17 == 1) // fix for issue #464
+    #define JSON_HAS_CPP_17
+    #define JSON_HAS_CPP_14
+#elif (defined(__cplusplus) && __cplusplus >= 201402L) || (defined(_HAS_CXX14) && _HAS_CXX14 == 1)
+    #define JSON_HAS_CPP_14
+#endif
+
+#ifdef JSON_HAS_CPP_17
+    #if __has_include(<optional>)
+        #include <optional>
+    #elif __has_include(<experimental/optional>)
+        #include <experimental/optional>
+    #endif
+#endif
+
+#if defined(JSON_HAS_CPP_17)
+    #include <string_view>
+#endif
+
 TEST_CASE("value conversion")
 {
     SECTION("get an object (explicit)")
@@ -499,6 +519,13 @@ TEST_CASE("value conversion")
             const std::string s = j.get<std::string>();
             CHECK(json(s) == j);
         }
+#if defined(JSON_HAS_CPP_17)
+        SECTION("std::string_view")
+        {
+            std::string_view const s = j.get<std::string_view>();
+            CHECK(json(s) == j);
+        }
+#endif
 
         SECTION("exception in case of a non-string type")
         {
@@ -524,6 +551,26 @@ TEST_CASE("value conversion")
                 json(json::value_t::number_float).get<json::string_t>(),
                 "[json.exception.type_error.302] type must be string, but is number", json::type_error&);
         }
+
+#if defined(JSON_HAS_CPP_17)
+        SECTION("exception in case of a non-string type using string_view")
+        {
+            CHECK_THROWS_WITH_AS(json(json::value_t::null).get<std::string_view>(),
+                                 "[json.exception.type_error.302] type must be string, but is null", json::type_error&);
+            CHECK_THROWS_WITH_AS(json(json::value_t::object).get<std::string_view>(),
+                                 "[json.exception.type_error.302] type must be string, but is object", json::type_error&);
+            CHECK_THROWS_WITH_AS(json(json::value_t::array).get<std::string_view>(),
+                                 "[json.exception.type_error.302] type must be string, but is array", json::type_error&);
+            CHECK_THROWS_WITH_AS(json(json::value_t::boolean).get<std::string_view>(),
+                                 "[json.exception.type_error.302] type must be string, but is boolean", json::type_error&);
+            CHECK_THROWS_WITH_AS(json(json::value_t::number_integer).get<std::string_view>(),
+                                 "[json.exception.type_error.302] type must be string, but is number", json::type_error&);
+            CHECK_THROWS_WITH_AS(json(json::value_t::number_unsigned).get<std::string_view>(),
+                                 "[json.exception.type_error.302] type must be string, but is number", json::type_error&);
+            CHECK_THROWS_WITH_AS(json(json::value_t::number_float).get<std::string_view>(),
+                                 "[json.exception.type_error.302] type must be string, but is number", json::type_error&);
+        }
+#endif
     }
 
     SECTION("get a string (explicit, get_to)")
@@ -544,6 +591,15 @@ TEST_CASE("value conversion")
             j.get_to(s);
             CHECK(json(s) == j);
         }
+#if defined(JSON_HAS_CPP_17)
+        SECTION("std::string_view")
+        {
+            std::string const s = "previous value";
+            std::string_view sv = s;
+            j.get_to(sv);
+            CHECK(json(sv) == j);
+        }
+#endif
     }
 
     SECTION("get null (explicit)")
@@ -582,6 +638,14 @@ TEST_CASE("value conversion")
             CHECK(json(s) == j);
         }
 
+#if defined(JSON_HAS_CPP_17)
+        SECTION("std::string_view")
+        {
+            std::string_view const s = j.get<std::string_view>();
+            CHECK(json(s) == j);
+        }
+#endif
+
         SECTION("std::string")
         {
             const std::string s = j;
@@ -1192,4 +1256,11 @@ TEST_CASE("value conversion")
 #endif
 }
 
+#ifdef JSON_HAS_CPP_17
+    #undef JSON_HAS_CPP_17
+#endif
+
+#ifdef JSON_HAS_CPP_14
+    #undef JSON_HAS_CPP_14
+#endif
 DOCTEST_CLANG_SUPPRESS_WARNING_POP

tests/src/unit-conversions2-cpp17.cpp

@@ -1,225 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++ (supporting code)
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-License-Identifier: MIT
-
-// This file contains the C++17-only part of unit-conversions2.cpp (conversions of
-// std::filesystem::path, std::u8string and std::optional). It is kept in a separate
-// translation unit so the (much larger) unit-conversions2.cpp is built for C++11 only and
-// not rebuilt for every C++ standard.
-
-#include "doctest_compatibility.h"
-
-#include <nlohmann/json.hpp>
-using nlohmann::json;
-
-// workaround for MSVC, which does not set __cplusplus to the language version (#464)
-#if (defined(__cplusplus) && __cplusplus >= 201703L) || (defined(_HAS_CXX17) && _HAS_CXX17 == 1) // fix for issue #464
-    #define JSON_HAS_CPP_17
-#endif
-
-// NLOHMANN_JSON_SERIALIZE_ENUM uses a static std::pair
-DOCTEST_CLANG_SUPPRESS_WARNING_PUSH
-DOCTEST_CLANG_SUPPRESS_WARNING("-Wexit-time-destructors")
-
-#ifdef JSON_HAS_CPP_17
-#include <map>
-#include <stdexcept>
-#include <string>
-#include <string_view>
-#include <type_traits>
-#include <vector>
-
-#if __has_include(<optional>)
-    #include <optional>
-#elif __has_include(<experimental/optional>)
-    #include <experimental/optional>
-#endif
-
-#if JSON_HAS_FILESYSTEM || JSON_HAS_EXPERIMENTAL_FILESYSTEM
-TEST_CASE("std::filesystem::path")
-{
-    SECTION("ascii")
-    {
-        json const j_string = "Path";
-        auto p = j_string.template get<nlohmann::detail::std_fs::path>();
-        json const j_path = p;
-
-        CHECK(j_path.template get<std::string>() ==
-              j_string.template get<std::string>());
-    }
-
-    SECTION("utf-8")
-    {
-        json const j_string = "P\xc4\x9b\xc5\xa1ina";
-        auto p = j_string.template get<nlohmann::detail::std_fs::path>();
-        json const j_path = p;
-
-        CHECK(j_path.template get<std::string>() ==
-              j_string.template get<std::string>());
-    }
-}
-
-#endif
-
-// the ADL to_json overload for std::u8string only exists under the same guard
-// as std::filesystem::path support (it is otherwise only reached indirectly,
-// via std::filesystem::path::u8string()) -- mirror both #if conditions from
-// include/nlohmann/detail/conversions/to_json.hpp exactly
-#if JSON_HAS_FILESYSTEM || JSON_HAS_EXPERIMENTAL_FILESYSTEM
-#if defined(__cpp_lib_char8_t)
-TEST_CASE("std::u8string")
-{
-    SECTION("ascii")
-    {
-        const std::u8string s = u8"Path";
-        json const j = s;
-
-        CHECK(j.template get<std::string>() == "Path");
-    }
-
-    SECTION("utf-8")
-    {
-        // use \u universal-character-names (rather than raw \x byte escapes
-        // or literal non-ASCII source bytes) to compose the multi-byte UTF-8
-        // encoding -- MSVC treats \x escapes used that way inside a u8
-        // literal as a nonstandard extension (warning C5321), which some of
-        // our CI configs promote to an error; \u is portable and produces
-        // the exact same encoded bytes without depending on the source
-        // file's encoding
-        const std::u8string s = u8"P\u011B\u0161ina";
-        json const j = s;
-
-        CHECK(j.template get<std::string>() == "P\xc4\x9b\xc5\xa1ina");
-    }
-}
-
-#endif
-#endif
-
-#if !defined(JSON_NOEXCEPTION)
-namespace
-{
-// a type whose to_json reports an error by throwing, used below to check that
-// converting a std::optional<T> to JSON propagates an exception thrown while
-// converting its contained value instead of calling std::terminate (#5642)
-struct throwing_to_json_type {};
-
-[[noreturn]] void to_json(json& /*unused*/, const throwing_to_json_type& /*unused*/)
-{
-    throw std::runtime_error("cannot serialize throwing_to_json_type");
-}
-}  // namespace
-#endif
-
-TEST_CASE("std::optional")
-{
-    SECTION("null")
-    {
-        const json j_null;
-        const std::optional<std::string> opt_null;
-
-        CHECK(json(opt_null) == j_null);
-        CHECK(j_null.get<std::optional<std::string>>() == std::nullopt);
-
-        // Constructing std::optional<T> directly from JSON null throws because
-        // std::optional's own converting constructor is chosen over basic_json's
-        // operator T(). This is a language-level limitation (std::optional<T> is
-        // constructible from T, and T is constructible from basic_json via the
-        // operator); there is no SFINAE path that distinguishes "call from inside
-        // std::optional's constructor" from "direct call". Use get<std::optional<T>>()
-        // or get_to() instead for correct null handling. See #4864 and #5246.
-        CHECK_THROWS_WITH_AS(std::optional<std::string>(j_null),
-                             "[json.exception.type_error.302] type must be string, but is null", json::type_error&);
-        CHECK_THROWS_WITH_AS(std::optional<int>(j_null),
-                             "[json.exception.type_error.302] type must be number, but is null", json::type_error&);
-
-        // Assignment goes through the same overload resolution as direct
-        // construction, so it throws for the same reason. This relies on
-        // basic_json's implicit conversion operator, so it only applies
-        // when JSON_USE_IMPLICIT_CONVERSIONS is enabled (the default).
-#if JSON_USE_IMPLICIT_CONVERSIONS
-        std::optional<std::string> opt_assign;
-        CHECK_THROWS_WITH_AS(opt_assign = j_null,
-                             "[json.exception.type_error.302] type must be string, but is null", json::type_error&);
-#endif
-
-        // get_to() is the correct way to obtain std::nullopt from a JSON null.
-        std::optional<std::string> opt_get_to = "placeholder";
-        j_null.get_to(opt_get_to);
-        CHECK(opt_get_to == std::nullopt);
-    }
-
-    SECTION("string")
-    {
-        json j_string = "string";
-        std::optional<std::string> opt_string = "string";
-
-        CHECK(json(opt_string) == j_string);
-        CHECK(std::optional<std::string>(j_string) == opt_string);
-        // false positive: Infer attributes the destruction of the temporaries above to opt_string
-        // @infer-ignore USE_AFTER_DELETE
-    }
-
-    SECTION("bool")
-    {
-        json j_bool = true;
-        std::optional<bool> opt_bool = true;
-
-        CHECK(json(opt_bool) == j_bool);
-        CHECK(std::optional<bool>(j_bool) == opt_bool);
-    }
-
-    SECTION("number")
-    {
-        json j_number = 1;
-        std::optional<int> opt_int = 1;
-
-        CHECK(json(opt_int) == j_number);
-        CHECK(j_number.get<std::optional<int>>() == opt_int);
-    }
-
-    SECTION("array")
-    {
-        json j_array = {1, 2, nullptr};
-        std::vector<std::optional<int>> opt_array = {{1, 2, std::nullopt}};
-
-        CHECK(json(opt_array) == j_array);
-        CHECK(j_array.get<std::vector<std::optional<int>>>() == opt_array);
-    }
-
-    SECTION("object")
-    {
-        json j_object = {{"one", 1}, {"two", 2}, {"zero", nullptr}};
-        std::map<std::string, std::optional<int>> opt_object {{"one", 1}, {"two", 2}, {"zero", std::nullopt}};
-
-        CHECK(json(opt_object) == j_object);
-        CHECK(std::map<std::string, std::optional<int>>(j_object) == opt_object);
-    }
-
-#if !defined(JSON_NOEXCEPTION)
-    SECTION("exception from contained value's to_json propagates (#5642)")
-    {
-        // to_json(BasicJsonType&, const std::optional<T>&) must not be
-        // noexcept: it calls T's to_json, which may throw (a user-defined
-        // to_json that reports an error, or std::bad_alloc for T =
-        // std::string/vector/json). Before the fix, this called
-        // std::terminate() instead of letting the exception propagate.
-        const std::optional<throwing_to_json_type> opt = throwing_to_json_type{};
-        CHECK_THROWS_WITH_AS(json(opt), "cannot serialize throwing_to_json_type", std::runtime_error&);
-
-        // the conversion is noexcept exactly when converting the contained value is
-        // (except with MSVC 2017, where it is never noexcept, see to_json.hpp)
-#if !defined(_MSC_VER) || defined(__clang__) || _MSC_VER >= 1920
-        static_assert(!std::is_nothrow_constructible<json, const std::optional<throwing_to_json_type>&>::value);
-        static_assert(std::is_nothrow_constructible<json, const std::optional<int>&>::value);
-#endif
-    }
-#endif
-}
-
-DOCTEST_CLANG_SUPPRESS_WARNING_POP
-#endif

tests/src/unit-conversions2.cpp

@@ -6,11 +6,12 @@
 // SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
 // SPDX-License-Identifier: MIT
 
-// cmake/test.cmake builds a unit test with C++ standards beyond C++11 only if the
+// cmake/test.cmake selects the C++ standard versions with which to build a
-// source file mentions the corresponding version macro. To avoid rebuilding this
+// unit test based on the presence of JSON_HAS_CPP_<VERSION> macros.
-// large file for every standard, tests that depend on the standard version (e.g.,
+// When using macros that are only defined for particular versions of the standard
-// those using JSON_HAS_FILESYSTEM, JSON_HAS_RANGES, or JSON_HAS_THREE_WAY_COMPARISON)
+// (e.g., JSON_HAS_FILESYSTEM for C++17 and up), please mention the corresponding
-// go into a separate file unit-conversions2-cpp<NN>.cpp. This file stays C++11-only.
+// version macro in a comment close by, like this:
+// JSON_HAS_CPP_<VERSION> (do not remove; see note at top of file)
 
 #include "doctest_compatibility.h"
 
@@ -35,6 +36,25 @@ using nlohmann::json;
 DOCTEST_CLANG_SUPPRESS_WARNING_PUSH
 DOCTEST_CLANG_SUPPRESS_WARNING("-Wexit-time-destructors")
 
+#if (defined(__cplusplus) && __cplusplus >= 201703L) || (defined(_HAS_CXX17) && _HAS_CXX17 == 1) // fix for issue #464
+    #define JSON_HAS_CPP_17
+    #define JSON_HAS_CPP_14
+#elif (defined(__cplusplus) && __cplusplus >= 201402L) || (defined(_HAS_CXX14) && _HAS_CXX14 == 1)
+    #define JSON_HAS_CPP_14
+#endif
+
+#ifdef JSON_HAS_CPP_17
+    #if __has_include(<optional>)
+        #include <optional>
+    #elif __has_include(<experimental/optional>)
+        #include <experimental/optional>
+    #endif
+#endif
+
+#if defined(JSON_HAS_CPP_17)
+    #include <string_view>
+#endif
+
 TEST_CASE("value conversion")
 {
     SECTION("get a binary value (explicit)")
@@ -660,4 +680,194 @@ TEST_CASE("Strict JSON to enum mapping")
     }
 }
 
+
+#ifdef JSON_HAS_CPP_17
+#if JSON_HAS_FILESYSTEM || JSON_HAS_EXPERIMENTAL_FILESYSTEM
+TEST_CASE("std::filesystem::path")
+{
+    SECTION("ascii")
+    {
+        json const j_string = "Path";
+        auto p = j_string.template get<nlohmann::detail::std_fs::path>();
+        json const j_path = p;
+
+        CHECK(j_path.template get<std::string>() ==
+              j_string.template get<std::string>());
+    }
+
+    SECTION("utf-8")
+    {
+        json const j_string = "P\xc4\x9b\xc5\xa1ina";
+        auto p = j_string.template get<nlohmann::detail::std_fs::path>();
+        json const j_path = p;
+
+        CHECK(j_path.template get<std::string>() ==
+              j_string.template get<std::string>());
+    }
+}
+#endif
+
+// the ADL to_json overload for std::u8string only exists under the same guard
+// as std::filesystem::path support (it is otherwise only reached indirectly,
+// via std::filesystem::path::u8string()) -- mirror both #if conditions from
+// include/nlohmann/detail/conversions/to_json.hpp exactly
+#if JSON_HAS_FILESYSTEM || JSON_HAS_EXPERIMENTAL_FILESYSTEM
+#if defined(__cpp_lib_char8_t)
+TEST_CASE("std::u8string")
+{
+    SECTION("ascii")
+    {
+        const std::u8string s = u8"Path";
+        json const j = s;
+
+        CHECK(j.template get<std::string>() == "Path");
+    }
+
+    SECTION("utf-8")
+    {
+        // use \u universal-character-names (rather than raw \x byte escapes
+        // or literal non-ASCII source bytes) to compose the multi-byte UTF-8
+        // encoding -- MSVC treats \x escapes used that way inside a u8
+        // literal as a nonstandard extension (warning C5321), which some of
+        // our CI configs promote to an error; \u is portable and produces
+        // the exact same encoded bytes without depending on the source
+        // file's encoding
+        const std::u8string s = u8"P\u011B\u0161ina";
+        json const j = s;
+
+        CHECK(j.template get<std::string>() == "P\xc4\x9b\xc5\xa1ina");
+    }
+}
+#endif
+#endif
+
+#if !defined(JSON_NOEXCEPTION)
+namespace
+{
+// a type whose to_json reports an error by throwing, used below to check that
+// converting a std::optional<T> to JSON propagates an exception thrown while
+// converting its contained value instead of calling std::terminate (#5642)
+struct throwing_to_json_type {};
+
+[[noreturn]] void to_json(json& /*unused*/, const throwing_to_json_type& /*unused*/)
+{
+    throw std::runtime_error("cannot serialize throwing_to_json_type");
+}
+}  // namespace
+#endif
+
+TEST_CASE("std::optional")
+{
+    SECTION("null")
+    {
+        const json j_null;
+        const std::optional<std::string> opt_null;
+
+        CHECK(json(opt_null) == j_null);
+        CHECK(j_null.get<std::optional<std::string>>() == std::nullopt);
+
+        // Constructing std::optional<T> directly from JSON null throws because
+        // std::optional's own converting constructor is chosen over basic_json's
+        // operator T(). This is a language-level limitation (std::optional<T> is
+        // constructible from T, and T is constructible from basic_json via the
+        // operator); there is no SFINAE path that distinguishes "call from inside
+        // std::optional's constructor" from "direct call". Use get<std::optional<T>>()
+        // or get_to() instead for correct null handling. See #4864 and #5246.
+        CHECK_THROWS_WITH_AS(std::optional<std::string>(j_null),
+                             "[json.exception.type_error.302] type must be string, but is null", json::type_error&);
+        CHECK_THROWS_WITH_AS(std::optional<int>(j_null),
+                             "[json.exception.type_error.302] type must be number, but is null", json::type_error&);
+
+        // Assignment goes through the same overload resolution as direct
+        // construction, so it throws for the same reason. This relies on
+        // basic_json's implicit conversion operator, so it only applies
+        // when JSON_USE_IMPLICIT_CONVERSIONS is enabled (the default).
+#if JSON_USE_IMPLICIT_CONVERSIONS
+        std::optional<std::string> opt_assign;
+        CHECK_THROWS_WITH_AS(opt_assign = j_null,
+                             "[json.exception.type_error.302] type must be string, but is null", json::type_error&);
+#endif
+
+        // get_to() is the correct way to obtain std::nullopt from a JSON null.
+        std::optional<std::string> opt_get_to = "placeholder";
+        j_null.get_to(opt_get_to);
+        CHECK(opt_get_to == std::nullopt);
+    }
+
+    SECTION("string")
+    {
+        json j_string = "string";
+        std::optional<std::string> opt_string = "string";
+
+        CHECK(json(opt_string) == j_string);
+        CHECK(std::optional<std::string>(j_string) == opt_string);
+        // false positive: Infer attributes the destruction of the temporaries above to opt_string
+        // @infer-ignore USE_AFTER_DELETE
+    }
+
+    SECTION("bool")
+    {
+        json j_bool = true;
+        std::optional<bool> opt_bool = true;
+
+        CHECK(json(opt_bool) == j_bool);
+        CHECK(std::optional<bool>(j_bool) == opt_bool);
+    }
+
+    SECTION("number")
+    {
+        json j_number = 1;
+        std::optional<int> opt_int = 1;
+
+        CHECK(json(opt_int) == j_number);
+        CHECK(j_number.get<std::optional<int>>() == opt_int);
+    }
+
+    SECTION("array")
+    {
+        json j_array = {1, 2, nullptr};
+        std::vector<std::optional<int>> opt_array = {{1, 2, std::nullopt}};
+
+        CHECK(json(opt_array) == j_array);
+        CHECK(j_array.get<std::vector<std::optional<int>>>() == opt_array);
+    }
+
+    SECTION("object")
+    {
+        json j_object = {{"one", 1}, {"two", 2}, {"zero", nullptr}};
+        std::map<std::string, std::optional<int>> opt_object {{"one", 1}, {"two", 2}, {"zero", std::nullopt}};
+
+        CHECK(json(opt_object) == j_object);
+        CHECK(std::map<std::string, std::optional<int>>(j_object) == opt_object);
+    }
+
+#if !defined(JSON_NOEXCEPTION)
+    SECTION("exception from contained value's to_json propagates (#5642)")
+    {
+        // to_json(BasicJsonType&, const std::optional<T>&) must not be
+        // noexcept: it calls T's to_json, which may throw (a user-defined
+        // to_json that reports an error, or std::bad_alloc for T =
+        // std::string/vector/json). Before the fix, this called
+        // std::terminate() instead of letting the exception propagate.
+        const std::optional<throwing_to_json_type> opt = throwing_to_json_type{};
+        CHECK_THROWS_WITH_AS(json(opt), "cannot serialize throwing_to_json_type", std::runtime_error&);
+
+        // the conversion is noexcept exactly when converting the contained value is
+        // (except with MSVC 2017, where it is never noexcept, see to_json.hpp)
+#if !defined(_MSC_VER) || defined(__clang__) || _MSC_VER >= 1920
+        static_assert(!std::is_nothrow_constructible<json, const std::optional<throwing_to_json_type>&>::value);
+        static_assert(std::is_nothrow_constructible<json, const std::optional<int>&>::value);
+#endif
+    }
+#endif
+}
+#endif
+
+#ifdef JSON_HAS_CPP_17
+    #undef JSON_HAS_CPP_17
+#endif
+
+#ifdef JSON_HAS_CPP_14
+    #undef JSON_HAS_CPP_14
+#endif
 DOCTEST_CLANG_SUPPRESS_WARNING_POP

tests/src/unit-custom-base-class.cpp

@@ -44,10 +44,10 @@ TEST_CASE("JSON Node Metadata")
 {
     SECTION("type int")
     {
-        using json_t = json_with_metadata<int>;
+        using json = json_with_metadata<int>;
-        json_t null;
+        json null;
-        auto obj   = json_t::object();
+        auto obj   = json::object();
-        auto array = json_t::array();
+        auto array = json::array();
 
         null.metadata()  = 1;
         obj.metadata()   = 2;
@@ -61,8 +61,8 @@ TEST_CASE("JSON Node Metadata")
     }
     SECTION("type vector<int>")
     {
-        using json_t = json_with_metadata<std::vector<int>>;
+        using json = json_with_metadata<std::vector<int>>;
-        json_t value;
+        json value;
         value.metadata().emplace_back(1);
         auto copy = value;
         value.metadata().emplace_back(2);
@@ -75,12 +75,12 @@ TEST_CASE("JSON Node Metadata")
     }
     SECTION("copy ctor")
     {
-        using json_t = json_with_metadata<std::vector<int>>;
+        using json = json_with_metadata<std::vector<int>>;
-        json_t value;
+        json value;
         value.metadata().emplace_back(1);
         value.metadata().emplace_back(2);
 
-        json_t copy = value;
+        json copy = value;
 
         CHECK(copy.metadata().size()  == 2);
         CHECK(copy.metadata().at(0)   == 1);
@@ -95,12 +95,12 @@ TEST_CASE("JSON Node Metadata")
     }
     SECTION("move ctor")
     {
-        using json_t = json_with_metadata<std::vector<int>>;
+        using json = json_with_metadata<std::vector<int>>;
-        json_t value;
+        json value;
         value.metadata().emplace_back(1);
         value.metadata().emplace_back(2);
 
-        const json_t moved = std::move(value);
+        const json moved = std::move(value);
 
         CHECK(moved.metadata().size()  == 2);
         CHECK(moved.metadata().at(0)   == 1);
@@ -108,12 +108,12 @@ TEST_CASE("JSON Node Metadata")
     }
     SECTION("move assign")
     {
-        using json_t = json_with_metadata<std::vector<int>>;
+        using json = json_with_metadata<std::vector<int>>;
-        json_t value;
+        json value;
         value.metadata().emplace_back(1);
         value.metadata().emplace_back(2);
 
-        json_t moved;
+        json moved;
         moved = std::move(value);
 
         CHECK(moved.metadata().size()  == 2);
@@ -122,12 +122,12 @@ TEST_CASE("JSON Node Metadata")
     }
     SECTION("copy assign")
     {
-        using json_t = json_with_metadata<std::vector<int>>;
+        using json = json_with_metadata<std::vector<int>>;
-        json_t value;
+        json value;
         value.metadata().emplace_back(1);
         value.metadata().emplace_back(2);
 
-        json_t copy;
+        json copy;
         copy = value;
 
         CHECK(copy.metadata().size()  == 2);
@@ -143,8 +143,8 @@ TEST_CASE("JSON Node Metadata")
     }
     SECTION("type unique_ptr<int>")
     {
-        using json_t = json_with_metadata<std::unique_ptr<int>>;
+        using json = json_with_metadata<std::unique_ptr<int>>;
-        json_t value;
+        json value;
         value.metadata().reset(new int(42)); // NOLINT(cppcoreguidelines-owning-memory)
         auto moved = std::move(value);
 
@@ -153,12 +153,12 @@ TEST_CASE("JSON Node Metadata")
     }
     SECTION("type vector<int> in json array")
     {
-        using json_t = json_with_metadata<std::vector<int>>;
+        using json = json_with_metadata<std::vector<int>>;
-        json_t value;
+        json value;
         value.metadata().emplace_back(1);
         value.metadata().emplace_back(2);
 
-        json_t const array(10, value);
+        json const array(10, value);
 
         CHECK(value.metadata().size() == 2);
         CHECK(value.metadata().at(0)  == 1);
@@ -173,10 +173,10 @@ TEST_CASE("JSON Node Metadata")
     }
     SECTION("member swap")
     {
-        using json_t = json_with_metadata<int>;
+        using json = json_with_metadata<int>;
-        json_t a = 1;
+        json a = 1;
         a.metadata() = 100;
-        json_t b = 2;
+        json b = 2;
         b.metadata() = 200;
 
         a.swap(b);
@@ -188,10 +188,10 @@ TEST_CASE("JSON Node Metadata")
     }
     SECTION("nonmember swap")
     {
-        using json_t = json_with_metadata<int>;
+        using json = json_with_metadata<int>;
-        json_t a = 1;
+        json a = 1;
         a.metadata() = 100;
-        json_t b = 2;
+        json b = 2;
         b.metadata() = 200;
 
         using std::swap;
@@ -204,10 +204,10 @@ TEST_CASE("JSON Node Metadata")
     }
     SECTION("std::swap")
     {
-        using json_t = json_with_metadata<int>;
+        using json = json_with_metadata<int>;
-        json_t a = 1;
+        json a = 1;
         a.metadata() = 100;
-        json_t b = 2;
+        json b = 2;
         b.metadata() = 200;
 
         std::swap(a, b);
@@ -221,15 +221,15 @@ TEST_CASE("JSON Node Metadata")
     {
         // std::sort mixes swap() with moves; each value's metadata must
         // travel with it, just as it does for copy, move, and assignment
-        using json_t = json_with_metadata<int>;
+        using json = json_with_metadata<int>;
-        std::vector<json_t> values;
+        std::vector<json> values;
         for (const int v :
                 {
                     5, 3, 9, 1, 7, 2, 8, 4, 6, 0, 15, 13, 19, 11, 17, 12, 18, 14, 16, 10,
                     25, 23, 29, 21, 27, 22, 28, 24, 26, 20, 35, 33
                 })
         {
-            json_t value = v;
+            json value = v;
             value.metadata() = v;
             values.push_back(value);
         }
@@ -267,19 +267,19 @@ template <class Ptr, class Fnc>
 void visitor_adaptor::do_visit(const Ptr& ptr, const Fnc& fnc) const
 {
     using value_t = nlohmann::detail::value_t;
-    const json_with_visitor_t& self = *static_cast<const json_with_visitor_t*>(this); // NOLINT(cppcoreguidelines-pro-type-static-cast-downcast)
+    const json_with_visitor_t& json = *static_cast<const json_with_visitor_t*>(this); // NOLINT(cppcoreguidelines-pro-type-static-cast-downcast)
-    switch (self.type())
+    switch (json.type())
     {
         case value_t::object:
-            for (const auto& entry : self.items())
+            for (const auto& entry : json.items())
             {
                 entry.value().do_visit(ptr / entry.key(), fnc);
             }
             break;
         case value_t::array:
-            for (std::size_t i = 0; i < self.size(); ++i)
+            for (std::size_t i = 0; i < json.size(); ++i)
             {
-                self.at(i).do_visit(ptr / std::to_string(i), fnc);
+                json.at(i).do_visit(ptr / std::to_string(i), fnc);
             }
             break;
         case value_t::discarded:
@@ -292,22 +292,22 @@ void visitor_adaptor::do_visit(const Ptr& ptr, const Fnc& fnc) const
         case value_t::number_float:
         case value_t::binary:
         default:
-            fnc(ptr, self);
+            fnc(ptr, json);
     }
 }
 
 TEST_CASE("JSON Visit Node")
 {
-    json_with_visitor_t root;
+    json_with_visitor_t json;
-    root["null"];
+    json["null"];
-    root["int"]  = -1;
+    json["int"]  = -1;
-    root["uint"] = 1U;
+    json["uint"] = 1U;
-    root["float"] = 1.0;
+    json["float"] = 1.0;
-    root["boolean"] = true;
+    json["boolean"] = true;
-    root["string"] = "string";
+    json["string"] = "string";
-    root["array"].push_back(0);
+    json["array"].push_back(0);
-    root["array"].push_back(1);
+    json["array"].push_back(1);
-    root["array"].push_back(root);
+    json["array"].push_back(json);
 
     std::set<std::string> expected
     {
@@ -330,7 +330,7 @@ TEST_CASE("JSON Visit Node")
         "/array/2/array/1 - number_integer - 1"
     };
 
-    root.visit(
+    json.visit(
             [&](const json_with_visitor_t::json_pointer & p,
                 const json_with_visitor_t& j)
     {
@@ -374,7 +374,7 @@ TEST_CASE("JSON Visit Node")
                 break;
         }
         str << " - "  << j.dump();
-        CHECK(root.at(p) == j);
+        CHECK(json.at(p) == j);
         INFO(str.str());
         CHECK(expected.count(str.str()) == 1);
         expected.erase(str.str());
@@ -404,22 +404,22 @@ using json_with_hidden_base_members = nlohmann::json::with_base_class_t<base_cla
 
 TEST_CASE("JSON Node as_base_class")
 {
-    using json_t = json_with_hidden_base_members;
+    using json = json_with_hidden_base_members;
 
-    static_assert(std::is_same<decltype(std::declval<json_t&>().as_base_class()), json_t::json_base_class_t&>::value, "");
+    static_assert(std::is_same<decltype(std::declval<json&>().as_base_class()), json::json_base_class_t&>::value, "");
-    static_assert(std::is_same<decltype(std::declval<const json_t&>().as_base_class()), const json_t::json_base_class_t&>::value, "");
+    static_assert(std::is_same<decltype(std::declval<const json&>().as_base_class()), const json::json_base_class_t&>::value, "");
-    static_assert(noexcept(std::declval<json_t&>().as_base_class()), "");
+    static_assert(noexcept(std::declval<json&>().as_base_class()), "");
-    static_assert(noexcept(std::declval<const json_t&>().as_base_class()), "");
+    static_assert(noexcept(std::declval<const json&>().as_base_class()), "");
 
     SECTION("non-const")
     {
-        json_t j = {1, 2, 3};
+        json j = {1, 2, 3};
 
         CHECK(std::string(j.type_name()) == "array");
         CHECK(j.size() == 3);
         CHECK(std::string(j.as_base_class().type_name()) == "custom type_name");
         CHECK(j.as_base_class().size() == 42);
-        CHECK(&j.as_base_class() == &static_cast<json_t::json_base_class_t&>(j));
+        CHECK(&j.as_base_class() == &static_cast<json::json_base_class_t&>(j));
 
         j.as_base_class().m_size = 7;
         CHECK(j.as_base_class().size() == 7);
@@ -428,13 +428,13 @@ TEST_CASE("JSON Node as_base_class")
 
     SECTION("const")
     {
-        const json_t j = {1, 2, 3};
+        const json j = {1, 2, 3};
 
         CHECK(std::string(j.type_name()) == "array");
         CHECK(j.size() == 3);
         CHECK(std::string(j.as_base_class().type_name()) == "custom type_name");
         CHECK(j.as_base_class().size() == 42);
-        CHECK(&j.as_base_class() == &static_cast<const json_t::json_base_class_t&>(j));
+        CHECK(&j.as_base_class() == &static_cast<const json::json_base_class_t&>(j));
     }
 }
 

tests/src/unit-custom-binary-type-cpp17.cpp

@@ -1,111 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++ (supporting code)
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-License-Identifier: MIT
-
-// This file contains the C++17-only part of unit-custom-binary-type.cpp (binary types
-// whose value type is std::byte). It is kept in a separate translation unit so the (much
-// larger) unit-custom-binary-type.cpp is built for C++11 only and not rebuilt for every
-// C++ standard.
-
-#include "doctest_compatibility.h"
-
-// capture whether JSON_DISABLE_ENUM_SERIALIZATION was enabled on the command
-// line before including json.hpp, which #undefs it; std::byte is an enum, so
-// converting std::vector<std::byte> needs enum serialization
-#if defined(JSON_DISABLE_ENUM_SERIALIZATION) && (JSON_DISABLE_ENUM_SERIALIZATION == 1)
-    #define SKIP_TESTS_FOR_ENUM_SERIALIZATION
-#endif
-
-#include <nlohmann/json.hpp>
-
-#ifdef JSON_HAS_CPP_17
-#include <cstddef>
-#include <cstdint>
-#include <functional>
-#include <map>
-#include <memory>
-#include <string>
-#include <vector>
-
-// a BinaryType whose value type is not an integer type at all
-using byte_binary_json = nlohmann::json::with_binary_t<std::vector<std::byte>>;
-
-TEST_CASE("binary type whose value type is not std::uint8_t (C++17)")
-{
-    SECTION("dumping a value type that is not an integer")
-    {
-        const std::vector<std::byte> bytes{std::byte{0}, std::byte{1}, std::byte{0xFF}};
-        CHECK(byte_binary_json::binary(bytes).dump() == R"({"bytes":[0,1,255],"subtype":null})");
-        CHECK(byte_binary_json::binary(bytes, 42).dump() == R"({"bytes":[0,1,255],"subtype":42})");
-        CHECK(byte_binary_json::binary({}).dump() == R"({"bytes":[],"subtype":null})");
-    }
-
-    SECTION("hashing and the binary formats")
-    {
-        const std::vector<std::byte> bytes{std::byte{0}, std::byte{1}, std::byte{0xFF}};
-        const auto j = byte_binary_json::binary(bytes);
-
-        CHECK(std::hash<byte_binary_json> {}(j) == std::hash<byte_binary_json> {}(j));
-        CHECK(byte_binary_json::from_cbor(byte_binary_json::to_cbor(j)) == j);
-        CHECK(byte_binary_json::from_msgpack(byte_binary_json::to_msgpack(j)) == j);
-
-        // UBJSON has no binary type, so binary values are written as an array
-        CHECK(byte_binary_json::from_ubjson(byte_binary_json::to_ubjson(j)) == byte_binary_json({0, 1, 255}));
-        // the same holds for BON8
-        CHECK(byte_binary_json::from_bon8(byte_binary_json::to_bon8(j)) == byte_binary_json({0, 1, 255}));
-    }
-}
-
-// moved from unit-regression3.cpp, so that file does not instantiate a second
-// basic_json specialization (MinGW section limit, see windows.yml)
-TEST_CASE("std::vector<std::byte> as binary type")
-{
-    SECTION("issue #4804: from_cbor incompatible with std::vector<std::byte> as binary_t")
-    {
-        const std::vector<std::uint8_t> data = {0x80};
-        const auto decoded = byte_binary_json::from_cbor(data);
-        CHECK((decoded == byte_binary_json::array()));
-    }
-
-#ifndef SKIP_TESTS_FOR_ENUM_SERIALIZATION
-    SECTION("discussion #4209 - custom BinaryType direct assignment and round-tripping")
-    {
-        // Test that assigning a custom BinaryType directly creates a binary value, not an array
-        const std::vector<std::byte> original{std::byte{1}, std::byte{2}, std::byte{3}};
-        const byte_binary_json j = original;
-        CHECK(j.is_binary());
-        CHECK(!j.is_array());
-
-        // Test round-tripping: extracting the binary value back as the custom container type
-        const auto extracted = j.get<std::vector<std::byte>>();
-        CHECK(extracted == original);
-
-        // Test that the default json alias behavior is unchanged: std::vector<uint8_t> -> array
-        const nlohmann::json default_json = std::vector<std::uint8_t> {1, 2, 3};
-        CHECK(default_json.is_array());
-        CHECK(!default_json.is_binary());
-    }
-
-    SECTION("discussion #4209 - custom BinaryType extraction from parsed array")
-    {
-        // Test that extracting a custom BinaryType from a parsed JSON array still works
-        // (not just from a binary-typed node)
-        const auto j = byte_binary_json::parse("[1,2,3]");
-        CHECK(j.is_array());
-        CHECK(!j.is_binary());
-
-        // Extracting as custom BinaryType should work from arrays
-        const auto extracted = j.get<std::vector<std::byte>>();
-        CHECK(extracted.size() == 3);
-        CHECK(extracted[0] == std::byte{1});
-        CHECK(extracted[1] == std::byte{2});
-        CHECK(extracted[2] == std::byte{3});
-    }
-#endif
-}
-
-#endif