Read MessagePack containers without recursing per nesting level

get_msgpack_array() and get_msgpack_object() read their elements by calling
back into parse_msgpack_internal(), which calls them again for a nested
container. The native call stack therefore grew with the nesting depth of the
input, and each level costs only one byte to encode: 0x91 is a one-element
array, so a few hundred thousand of them crash the process before any of the
input is rejected (#5104).

Keep the open containers on a heap stack instead, the way
parser::sax_parse_internal() has always done for JSON text. A frame records
how many elements are left and whether to close with end_object() or
end_array(); parse_msgpack_value() reads a single value and, for a container,
only opens it; and parse_msgpack_internal() loops, resuming the innermost
container after each element and closing it when its count runs out. Whether
the value that was begun is complete is answered by the stack being empty, so
no separate bookkeeping is needed.

The switch that decodes a value is untouched apart from the six container
cases, which now call enter_container() rather than a reader that loops. That
keeps this diff to the control flow and leaves the decoding of every other
type byte-identical.

enter_container() is the only place a binary reader emits start_object() or
start_array(), so a check that rejects a container can be added there once and
is guaranteed to run before the start event. The frame type and the stack are
shared, ready for the other three formats.

Verified against develop over empty, nested, counted (array 16/32, map 16/32)
and truncated inputs: identical values, error codes, messages and byte
offsets. 300,000 levels now report parse_error.110 instead of crashing, and a
well-formed 300,000-level value is read to completion through the SAX
interface, where develop crashes.

Reading such a value into a basic_json needs the return-by-move change as
well, without which the recursive copy constructor overflows on the way out;
that is the parent commit, and the test for the value path covers the two
together. Timing is unchanged: parsing 60,000 small objects and one array of
a million integers is within run-to-run noise of develop either way.

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

.github/CONTRIBUTING.md

@@ -108,7 +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-regression2.cpp` and add a section referencing the fixed issue.
+When fixing a bug, edit `unit-regression3.cpp` and add a section referencing the fixed issue.
+`unit-regression2.cpp` holds the older tests; the two files exist because a single one grew large enough for the
+MinGW linker to fail relocating it, so please keep adding to the smaller file rather than growing one of them.
 
 #### Exceptions
 

.github/workflows/check_amalgamation.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@bf7454d06d71f1098171f2acdf0cd4708d7b5920 # v2.20.0
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 
@@ -34,7 +34,7 @@ jobs:
 
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@bf7454d06d71f1098171f2acdf0cd4708d7b5920 # v2.20.0
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 
@@ -67,8 +67,18 @@ jobs:
           ${{ github.workspace }}/venv/bin/astyle --project=tools/astyle/.astylerc --suffix=none --quiet \
             $INCLUDE_DIR/json.hpp $INCLUDE_DIR/json_fwd.hpp
 
+          # fail loudly if a directory is renamed or removed: find would only warn
+          # about the missing path and silently drop its files from the check
+          SOURCE_DIRS="docs/mkdocs/docs/examples include tests"
+          for DIR in $SOURCE_DIRS; do
+            if [ ! -d "$DIR" ]; then
+              echo "::error::source directory '$DIR' does not exist"
+              exit 1
+            fi
+          done
+
           ${{ github.workspace }}/venv/bin/astyle --project=tools/astyle/.astylerc --suffix=none --quiet \
-            $(find docs/examples include tests -type f \( -name '*.hpp' -o -name '*.cpp' -o -name '*.cu' \) -not -path 'tests/thirdparty/*' -not -path 'tests/abi/include/nlohmann/*' | sort)
+            $(find $SOURCE_DIRS -type f \( -name '*.hpp' -o -name '*.cpp' -o -name '*.cu' \) -not -path 'tests/thirdparty/*' -not -path 'tests/abi/include/nlohmann/*' | sort)
 
       - name: Build patch and check for differences
         id: diff

.github/workflows/cifuzz.yml

@@ -9,7 +9,7 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
     - name: Harden Runner
-      uses: step-security/harden-runner@bf7454d06d71f1098171f2acdf0cd4708d7b5920 # v2.20.0
+      uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
       with:
         egress-policy: audit
 

.github/workflows/codeql-analysis.yml

@@ -27,7 +27,7 @@ jobs:
 
     steps:
     - name: Harden Runner
-      uses: step-security/harden-runner@bf7454d06d71f1098171f2acdf0cd4708d7b5920 # v2.20.0
+      uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
       with:
         egress-policy: audit
 
@@ -38,14 +38,14 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@e0647621c2984b5ed2f768cb892365bf2a616ad1 # v4.37.2
+      uses: github/codeql-action/init@cdf488f595d80d6e07e03d4674febd5ab45fa938 # v4.37.9
       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@e0647621c2984b5ed2f768cb892365bf2a616ad1 # v4.37.2
+      uses: github/codeql-action/autobuild@cdf488f595d80d6e07e03d4674febd5ab45fa938 # v4.37.9
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@e0647621c2984b5ed2f768cb892365bf2a616ad1 # v4.37.2
+      uses: github/codeql-action/analyze@cdf488f595d80d6e07e03d4674febd5ab45fa938 # v4.37.9

.github/workflows/comment_check_amalgamation.yml

@@ -19,7 +19,7 @@ jobs:
       pull-requests: write
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@bf7454d06d71f1098171f2acdf0cd4708d7b5920 # v2.20.0
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 

.github/workflows/dependency-review.yml

@@ -17,7 +17,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@bf7454d06d71f1098171f2acdf0cd4708d7b5920 # v2.20.0
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 

.github/workflows/flawfinder.yml

@@ -27,7 +27,7 @@ jobs:
       security-events: write
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@bf7454d06d71f1098171f2acdf0cd4708d7b5920 # v2.20.0
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 
@@ -43,6 +43,6 @@ jobs:
           output: 'flawfinder_results.sarif'
 
       - name: Upload analysis results to GitHub Security tab
-        uses: github/codeql-action/upload-sarif@e0647621c2984b5ed2f768cb892365bf2a616ad1 # v4.37.2
+        uses: github/codeql-action/upload-sarif@cdf488f595d80d6e07e03d4674febd5ab45fa938 # v4.37.9
         with:
           sarif_file: ${{github.workspace}}/flawfinder_results.sarif

.github/workflows/labeler.yml

@@ -17,7 +17,7 @@ jobs:
 
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@bf7454d06d71f1098171f2acdf0cd4708d7b5920 # v2.20.0
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 

.github/workflows/publish_documentation.yml

@@ -7,7 +7,6 @@ on:
       - develop
     paths:
       - docs/mkdocs/**
-      - docs/examples/**
   workflow_dispatch:
 
 # we don't want to have concurrent jobs, and we don't want to cancel running jobs to avoid broken publications
@@ -27,7 +26,7 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@bf7454d06d71f1098171f2acdf0cd4708d7b5920 # v2.20.0
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 

.github/workflows/scorecards.yml

@@ -36,7 +36,7 @@ jobs:
 
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@bf7454d06d71f1098171f2acdf0cd4708d7b5920 # v2.20.0
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 
@@ -76,6 +76,6 @@ jobs:
 
       # Upload the results to GitHub's code scanning dashboard.
       - name: "Upload to code-scanning"
-        uses: github/codeql-action/upload-sarif@e0647621c2984b5ed2f768cb892365bf2a616ad1 # v4.37.2
+        uses: github/codeql-action/upload-sarif@cdf488f595d80d6e07e03d4674febd5ab45fa938 # v4.37.9
         with:
           sarif_file: results.sarif

.github/workflows/semgrep.yml

@@ -32,7 +32,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@bf7454d06d71f1098171f2acdf0cd4708d7b5920 # v2.20.0
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 
@@ -61,7 +61,7 @@ jobs:
 
       # Upload SARIF file generated in previous step
       - name: Upload SARIF file
-        uses: github/codeql-action/upload-sarif@e0647621c2984b5ed2f768cb892365bf2a616ad1 # v4.37.2
+        uses: github/codeql-action/upload-sarif@cdf488f595d80d6e07e03d4674febd5ab45fa938 # v4.37.9
         with:
           sarif_file: semgrep.sarif
         if: always()

.github/workflows/stale.yml

@@ -16,11 +16,11 @@ jobs:
 
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@bf7454d06d71f1098171f2acdf0cd4708d7b5920 # v2.20.0
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 
-      - uses: actions/stale@1e223db275d687790206a7acac4d1a11bd6fe629 # v10.4.0
+      - uses: actions/stale@4391f3da665fdf50b6810c1a66712fb9ba21aa93 # v11.0.0
         with:
           stale-issue-label: 'state: stale'
           stale-pr-label: 'state: stale'

.github/workflows/ubuntu.yml

@@ -25,7 +25,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@e6906078ebd1ccb8ce51ab4626ac46a1b5a517e3 # v4.4.0
+        uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -35,7 +35,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@bf7454d06d71f1098171f2acdf0cd4708d7b5920 # v2.20.0
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 
@@ -47,7 +47,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@e6906078ebd1ccb8ce51ab4626ac46a1b5a517e3 # v4.4.0
+        uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -60,7 +60,7 @@ jobs:
         target: [ci_test_amalgamation, ci_test_single_header, ci_cppcheck, ci_cpplint, ci_reproducible_tests, ci_non_git_tests, ci_offline_testdata, ci_reuse_compliance, ci_test_valgrind]
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@bf7454d06d71f1098171f2acdf0cd4708d7b5920 # v2.20.0
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 
@@ -70,7 +70,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@e6906078ebd1ccb8ce51ab4626ac46a1b5a517e3 # v4.4.0
+        uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -89,7 +89,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@e6906078ebd1ccb8ce51ab4626ac46a1b5a517e3 # v4.4.0
+        uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -108,7 +108,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@e6906078ebd1ccb8ce51ab4626ac46a1b5a517e3 # v4.4.0
+        uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -118,7 +118,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@bf7454d06d71f1098171f2acdf0cd4708d7b5920 # v2.20.0
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 
@@ -142,7 +142,7 @@ jobs:
           name: code-coverage-report
           path: ${{ github.workspace }}/build/html
       - name: Publish report to Coveralls
-        uses: coverallsapp/github-action@5cbfd81b66ca5d10c19b062c04de0199c215fb6e # v2.3.7
+        uses: coverallsapp/github-action@8d6379e14d29928660c4ba802d8e85393440b329 # v2.3.8
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
           path-to-lcov: ${{ github.workspace }}/build/json.info.filtered.noexcept
@@ -184,7 +184,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@e6906078ebd1ccb8ce51ab4626ac46a1b5a517e3 # v4.4.0
+        uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
       - name: Run CMake
         run: CXX=g++-${{ matrix.compiler }} cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -202,7 +202,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@e6906078ebd1ccb8ce51ab4626ac46a1b5a517e3 # v4.4.0
+        uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -212,14 +212,14 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        compiler: ['3.4', '3.5', '3.6', '3.7', '3.8', '3.9', '4', '5', '6', '7', '8', '9', '10', '11', '12', '13', '14', '15-bullseye', '16', '17', '18', '19', '20', 'latest']
+        compiler: ['3.4', '3.5', '3.6', '3.7', '3.8', '3.9', '4', '5', '6', '7', '8', '9', '10', '11', '12', '13', '14', '15-bullseye', '16', '17', '18', '19', '20', '21', '22', 'latest']
     container: silkeh/clang:${{ matrix.compiler }}
     steps:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@e6906078ebd1ccb8ce51ab4626ac46a1b5a517e3 # v4.4.0
+        uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
       - name: Set env FORCE_STDCPPFS_FLAG for clang 7 / 8 / 9 / 10
         run: echo "JSON_FORCED_GLOBAL_COMPILE_OPTIONS=-DJSON_HAS_FILESYSTEM=0;-DJSON_HAS_EXPERIMENTAL_FILESYSTEM=0" >> "$GITHUB_ENV"
         if: ${{ matrix.compiler == '7' || matrix.compiler == '8' || matrix.compiler == '9' || matrix.compiler == '10' }}
@@ -239,7 +239,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@e6906078ebd1ccb8ce51ab4626ac46a1b5a517e3 # v4.4.0
+        uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -259,7 +259,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@e6906078ebd1ccb8ce51ab4626ac46a1b5a517e3 # v4.4.0
+        uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build with libc++
@@ -286,7 +286,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@e6906078ebd1ccb8ce51ab4626ac46a1b5a517e3 # v4.4.0
+        uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -306,7 +306,7 @@ jobs:
       # import-std support. Its opt-in token is CMake-version-specific, so pin
       # CMake to the version whose token is set in tests/module_cpp20/CMakeLists.txt.
       - name: Get pinned CMake and ninja
-        uses: lukka/get-cmake@e6906078ebd1ccb8ce51ab4626ac46a1b5a517e3 # v4.4.0
+        uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
         with:
           cmakeVersion: 4.3.4
       # Clang: the std library module is provided by libc++ (the image's libstdc++
@@ -332,7 +332,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@e6906078ebd1ccb8ce51ab4626ac46a1b5a517e3 # v4.4.0
+        uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -347,7 +347,7 @@ jobs:
     steps:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@e6906078ebd1ccb8ce51ab4626ac46a1b5a517e3 # v4.4.0
+        uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -359,7 +359,7 @@ jobs:
     steps:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@e6906078ebd1ccb8ce51ab4626ac46a1b5a517e3 # v4.4.0
+        uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -369,7 +369,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@bf7454d06d71f1098171f2acdf0cd4708d7b5920 # v2.20.0
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 
@@ -379,7 +379,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@e6906078ebd1ccb8ce51ab4626ac46a1b5a517e3 # v4.4.0
+        uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
       - name: Run CMake
         run: cmake -S . -B build -DCMAKE_TOOLCHAIN_FILE=$EMSDK/upstream/emscripten/cmake/Modules/Platform/Emscripten.cmake -GNinja
       - name: Build
@@ -392,7 +392,7 @@ jobs:
         target: [ci_test_examples, ci_test_build_documentation]
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@bf7454d06d71f1098171f2acdf0cd4708d7b5920 # v2.20.0
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 

.github/workflows/windows.yml

@@ -88,7 +88,7 @@ jobs:
     steps:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@e6906078ebd1ccb8ce51ab4626ac46a1b5a517e3 # v4.4.0
+        uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
       - name: Set extra CXX_FLAGS for latest std_version
         # /wd5285 silences C5285 emitted by the bundled third-party doctest.h, which
         # specializes std::tuple (newly diagnosed by the VS2026 v145 toolset)
@@ -153,10 +153,16 @@ jobs:
         with:
           platform: x64
           version: 12.2.0 # https://github.com/egor-tensin/setup-mingw/issues/14
+      # CMAKE_CXX_FLAGS_DEBUG is overridden to drop the default -g: linking
+      # test-regression2_cpp20 intermittently fails with "relocation truncated
+      # to fit: IMAGE_REL_AMD64_SECREL against `.debug_line'" because the
+      # MinGW linker cannot relocate the debug sections this test produces.
+      # The tests are only built and run here, so the debug info is not used.
       - name: Run CMake
         run: cmake -S . -B build ^
              -DCMAKE_CXX_COMPILER="C:/Program Files/LLVM/bin/clang++.exe" ^
              -DCMAKE_CXX_FLAGS="--target=x86_64-w64-mingw32 -stdlib=libstdc++ -pthread" ^
+             -DCMAKE_CXX_FLAGS_DEBUG="-g0" ^
              -DCMAKE_EXE_LINKER_FLAGS="-lwinpthread" ^
              -G"MinGW Makefiles" ^
              -DCMAKE_BUILD_TYPE=Debug ^
@@ -193,7 +199,7 @@ jobs:
       # import-std support. Its opt-in token is CMake-version-specific, so pin
       # CMake to the version whose token is set in tests/module_cpp20/CMakeLists.txt.
       - name: Get pinned CMake and ninja
-        uses: lukka/get-cmake@e6906078ebd1ccb8ce51ab4626ac46a1b5a517e3 # v4.4.0
+        uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
         with:
           cmakeVersion: 4.3.4
       - name: Run CMake (Debug)

README.md

@@ -42,6 +42,7 @@
   - [Specializing enum conversion](#specializing-enum-conversion)
   - [Binary formats (BSON, CBOR, MessagePack, UBJSON, and BJData)](#binary-formats-bson-cbor-messagepack-ubjson-and-bjdata)
 - [Customers](#customers)
+- [Ecosystem](#ecosystem)
 - [Supported compilers](#supported-compilers)
 - [Integration](#integration)
   - [CMake](#cmake)
@@ -1186,6 +1187,11 @@ The library is used in multiple projects, applications, operating systems, etc.
 
 [![logos of customers using the library](docs/mkdocs/docs/images/customers.png)](https://json.nlohmann.me/home/customers/)
 
+## Ecosystem
+
+Beyond projects that use the library, there are third-party projects that build on top of it - schema validators,
+language bindings, format converters, and the like. See the curated [Ecosystem](https://json.nlohmann.me/community/ecosystem/) page.
+
 ## Supported compilers
 
 Though it's 2026 already, the support for C++11 is still a bit sparse. Currently, the following compilers are known to work:
@@ -1801,13 +1807,13 @@ The library itself consists of a single header file licensed under the MIT licen
 - [**amalgamate.py - Amalgamate C source and header files**](https://github.com/edlund/amalgamate) to create a single header file
 - [**American fuzzy lop**](https://lcamtuf.coredump.cx/afl/) for fuzz testing
 - [**AppVeyor**](https://www.appveyor.com) for [continuous integration](https://ci.appveyor.com/project/nlohmann/json) on Windows
-- [**Artistic Style**](http://astyle.sourceforge.net) for automatic source code indentation
+- [**Artistic Style**](https://astyle.sourceforge.net) for automatic source code indentation
 - [**Clang**](https://clang.llvm.org) for compilation with code sanitizers
 - [**CMake**](https://cmake.org) for build automation
 - [**Codacy**](https://www.codacy.com) for further [code analysis](https://app.codacy.com/gh/nlohmann/json/dashboard)
 - [**Coveralls**](https://coveralls.io) to measure [code coverage](https://coveralls.io/github/nlohmann/json)
 - [**Coverity Scan**](https://scan.coverity.com) for [static analysis](https://scan.coverity.com/projects/nlohmann-json)
-- [**cppcheck**](http://cppcheck.sourceforge.net) for static analysis
+- [**cppcheck**](https://cppcheck.sourceforge.io) for static analysis
 - [**doctest**](https://github.com/onqtam/doctest) for the unit tests
 - [**GitHub Changelog Generator**](https://github.com/skywinder/github-changelog-generator) to generate the [ChangeLog](https://github.com/nlohmann/json/blob/develop/ChangeLog.md)
 - [**Google Benchmark**](https://github.com/google/benchmark) to implement the benchmarks
@@ -1822,6 +1828,15 @@ The library itself consists of a single header file licensed under the MIT licen
 
 ## Notes
 
+### Standards compliance
+
+The library targets strict conformance with [RFC 8259](https://tools.ietf.org/html/rfc8259.html). Both the original [JSONTestSuite](https://github.com/nst/JSONTestSuite) and its updated revision are exercised in CI; their test data is downloaded from [`nlohmann/json_test_data`](https://github.com/nlohmann/json_test_data) at configure time rather than committed to this repository (see [`tests/src/unit-testsuites.cpp`](https://github.com/nlohmann/json/blob/develop/tests/src/unit-testsuites.cpp)):
+
+- The updated revision runs all mandatory `y_` (must-accept) and `n_` (must-reject) cases through the strict [`parse()`](https://json.nlohmann.me/api/basic_json/parse/) entry point; the original suite runs its `n_` cases through `parse()` and its `y_` cases through [`operator>>`](https://json.nlohmann.me/api/operator_gtgt/).
+- The `i_` (implementation-defined) cases are, by RFC 8259, free to be accepted *or* rejected, so "passing all `i_` cases" is not a meaningful conformance metric. The library makes deliberate, documented choices there: nesting depth is not artificially limited, a leading UTF-8 byte order mark is silently ignored, [Unicode noncharacters](https://www.unicode.org/faq/private_use.html#nonchar1) are forwarded unchanged, invalid UTF-8 and lone/unpaired UTF-16 surrogates are rejected (stricter than required), and a number that cannot be stored without becoming `NaN`/`INF` raises [`out_of_range.406`](https://json.nlohmann.me/home/exceptions/#jsonexceptionout_of_range406).
+
+One behavioral nuance is worth calling out, because a superficial test often misreads it as non-compliance: [`parse()`](https://json.nlohmann.me/api/basic_json/parse/) is strict and rejects trailing data after a value, whereas [`operator>>`](https://json.nlohmann.me/api/operator_gtgt/) follows relaxed iostream semantics — it parses a single value and leaves the stream positioned right after it. Feeding "a valid document followed by trailing bytes" through `operator>>` reports success; the same input through `parse()` is rejected. This is a documented two-API design, not a conformance gap. See [**parsing**](https://json.nlohmann.me/features/parsing/) for details.
+
 ### Character encoding
 
 The library supports **Unicode input** as follows:

cmake/ci.cmake

@@ -294,7 +294,7 @@ file(GLOB_RECURSE INDENT_FILES
         ${PROJECT_SOURCE_DIR}/tests/src/*.cpp
         ${PROJECT_SOURCE_DIR}/tests/src/*.hpp
         ${PROJECT_SOURCE_DIR}/tests/benchmarks/src/benchmarks.cpp
-    ${PROJECT_SOURCE_DIR}/docs/examples/*.cpp
+    ${PROJECT_SOURCE_DIR}/docs/mkdocs/docs/examples/*.cpp
 )
 
 set(include_dir ${PROJECT_SOURCE_DIR}/single_include/nlohmann)

cmake/clang_flags.cmake

@@ -5,6 +5,9 @@
 # -Wno-extra-semi-stmt            The library uses assert which triggers this warning.
 # -Wno-padded                     We do not care about padding warnings.
 # -Wno-covered-switch-default     All switches list all cases and a default case.
+# -Wno-c2y-extensions             Clang 22.1 diagnoses __COUNTER__ as a C2y extension, also in
+#                                 C++ mode. The library does not use __COUNTER__; the warnings
+#                                 all come from vendored Doctest (SECTION/TEST_CASE macros).
 # -Wno-unsafe-buffer-usage        Pervasive: the library's own low-level numeric/buffer code
 #                                 (to_chars, serializer, lexer, binary reader/writer, input
 #                                 adapters, json_pointer) plus vendored Doctest itself (~208
@@ -20,5 +23,6 @@ set(CLANG_CXXFLAGS
     -Wno-extra-semi-stmt
     -Wno-padded
     -Wno-covered-switch-default
+    -Wno-c2y-extensions
     -Wno-unsafe-buffer-usage
 )

docs/mkdocs/docs/api/basic_json/parser_callback_t.md

@@ -29,7 +29,14 @@ Discarding a value (i.e., returning `#!cpp false`) has different effects dependi
 called:
 
 - Discarded values in structured types are skipped. That is, the parser will behave as if the discarded value was never
-  read.
+  read. This holds for every value type and for both kinds of parent: a discarded element is removed from the
+  surrounding array, and a discarded member is removed from the surrounding object together with its key.
+- Arrays and objects can be discarded either at their `parse_event_t::array_start`/`parse_event_t::object_start` event
+  or at their `parse_event_t::array_end`/`parse_event_t::object_end` event, and both remove the whole value. Discarding
+  it at the start event also means the callback is called neither for the content of the value nor for its matching end
+  event.
+- Discarding a `parse_event_t::key` event discards the whole object member. The callback is still called for the
+  associated value, but its return value has no further effect.
 - In case a value outside a structured type is skipped, it is replaced with `null`. This case happens if the top-level
   element is skipped.
 
@@ -49,7 +56,7 @@ called:
 ## Return value
 
 Whether the JSON value which called the function during parsing should be kept (`#!cpp true`) or not (`#!cpp false`). In
-the latter case, it is either skipped completely or replaced by an empty discarded object.
+the latter case, it is skipped completely, or replaced by `null` if it is the top-level value.
 
 ## Examples
 
@@ -68,6 +75,21 @@ the latter case, it is either skipped completely or replaced by an empty discard
     --8<-- "examples/parse__string__parser_callback_t.output"
     ```
 
+??? example
+
+    The example below shows where discarded values are removed. The array and the number are discarded in different
+    ways, but in each case the parse result contains neither the value nor its key.
+
+    ```cpp
+    --8<-- "examples/parser_callback_t.cpp"
+    ```
+
+    Output:
+
+    ```json
+    --8<-- "examples/parser_callback_t.output"
+    ```
+
 ## See also
 
 - [parse](parse.md) deserialize from a compatible input
@@ -76,3 +98,5 @@ the latter case, it is either skipped completely or replaced by an empty discard
 ## Version history
 
 - Added in version 1.0.0.
+- Fixed in version 3.13.0 to also remove discarded values from a parent object; before, discarding an array or a value
+  stored under an object key left a discarded member behind, which made the parse result serialize to invalid JSON.

docs/mkdocs/docs/api/basic_json/to_bjdata.md

@@ -52,6 +52,11 @@ optional, `#!cpp bjdata_version_t::draft2` by default.
 
 Strong guarantee: if an exception is thrown, there are no changes in the JSON value.
 
+## Exceptions
+
+- Throws [`other_error.502`](../../home/exceptions.md#jsonexceptionother_error502) if `use_type` is true and `use_size`
+  is false.
+
 ## Complexity
 
 Linear in the size of the JSON value `j`.

docs/mkdocs/docs/api/basic_json/to_bson.md

@@ -46,7 +46,9 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
 
 ## Complexity
 
-Linear in the size of the JSON value `j`.
+Proportional to the size of the JSON value `j` multiplied by its maximum nesting
+depth, `O(n × d)`. BSON length prefixes are computed recursively before nested
+values are written.
 
 ## Examples
 

docs/mkdocs/docs/api/basic_json/to_ubjson.md

@@ -45,6 +45,11 @@ The exact mapping and its limitations are described on a [dedicated page](../../
 
 Strong guarantee: if an exception is thrown, there are no changes in the JSON value.
 
+## Exceptions
+
+- Throws [`other_error.502`](../../home/exceptions.md#jsonexceptionother_error502) if `use_type` is true and `use_size`
+  is false.
+
 ## Complexity
 
 Linear in the size of the JSON value `j`.

docs/mkdocs/docs/api/operator_gtgt.md

@@ -33,17 +33,44 @@ A UTF-8 byte order mark is silently ignored.
 Invalid Unicode escapes and unpaired surrogates in the input are reported as
 [`parse_error.101`](../home/exceptions.md#jsonexceptionparse_error101) with a detailed message.
 
-`operator>>` parses exactly one JSON value and leaves the stream positioned right after it, so it can be called
+`operator>>` parses exactly one JSON value, so it can be called repeatedly to read a sequence of concatenated JSON
-repeatedly to read a sequence of concatenated JSON values from the same stream:
+values from the same stream:
 
 ```cpp
 json j1, j2;
-input >> j1;  // parses the first value, stream now positioned right after it
+input >> j1;  // parses the first value
 input >> j2;  // parses the next value
 ```
 
-Note this does **not** work for [JSON Lines](../features/parsing/json_lines.md) (newline-delimited JSON) input --
+!!! warning "A number must be followed by whitespace"
-see that page for why and for the recommended alternative.
+
+    A number is only terminated by the character that follows it. That character is read from the stream to detect the
+    end of the number, and it is **not** put back. When a value that is a number is immediately followed by the next
+    value, the first character of that next value is lost:
+
+    ```cpp
+    std::istringstream input("1true");
+    json j1, j2;
+    input >> j1;  // j1 == 1
+    input >> j2;  // throws parse_error.101: the stream now starts at "rue"
+    ```
+
+    Separating the values with whitespace avoids this, because the character that is eaten is then the separator:
+
+    ```cpp
+    std::istringstream input("1 true");
+    json j1, j2;
+    input >> j1;  // j1 == 1
+    input >> j2;  // j2 == true
+    ```
+
+    Only numbers are affected. Values ending in a self-delimiting character do not read past themselves, so
+    `truefalse`, `[1][2]`, `{"a":1}{"b":2}`, and `"a""b"` can be read back to back without a separator.
+
+    This is tracked in [#5340](https://github.com/nlohmann/json/issues/5340).
+
+Note that reading concatenated values does **not** work for [JSON Lines](../features/parsing/json_lines.md)
+(newline-delimited JSON) input -- see that page for why and for the recommended alternative.
 
 !!! warning "Deprecation"
 

docs/mkdocs/docs/api/ordered_json.md

@@ -13,6 +13,12 @@ Therefore, adding object elements can yield a reallocation in which case all ite
 [`end()`](basic_json/end.md) iterator) and all references to the elements are invalidated. Also, any iterator or
 reference after the insertion point will point to the same index, which is now a different value.
 
+## Complexity
+
+[`ordered_map`](ordered_map.md) has no lookup index: every key-based object operation is a linear scan, so building or
+parsing an object of `n` keys costs O(n²) rather than O(n log n). See
+[`ordered_map` complexity](ordered_map.md#complexity) for the per-operation table and for measured numbers.
+
 ## Examples
 
 ??? example

docs/mkdocs/docs/api/ordered_map.md

@@ -56,6 +56,48 @@ std::equal_to<>     // since C++14
 - **find**
 - **insert**
 
+## Complexity
+
+Because the elements are stored in a `std::vector` in insertion order, there is no index to look a key up by. Every
+key-based operation performs a **linear scan** over the stored elements. With `n` denoting the number of elements in the
+container:
+
+| Operation                              | Complexity     | Note                                                     |
+|----------------------------------------|----------------|----------------------------------------------------------|
+| **emplace**                            | O(n)           | scans for an existing key, then appends (amortized O(1)) |
+| **operator\[\]**                       | O(n)           | delegates to **emplace** (non-const) or **at** (const)   |
+| **at**                                 | O(n)           | throws `#!cpp std::out_of_range` if the key is not found |
+| **find**                               | O(n)           |                                                          |
+| **count**                              | O(n)           | the result is always 0 or 1                              |
+| **erase(key)**                         | O(n)           | scan, then move the remaining elements one position down |
+| **erase(pos)**, **erase(first, last)** | O(n)           | moves all elements after the erased range                |
+| **insert(value)**                      | O(n)           | equivalent to **emplace**                                |
+| **insert(first, last)**                | O((n + m) * m) | for `m` inserted elements                                |
+
+This differs from `#!cpp std::map`, where the same operations are O(log n).
+
+!!! warning "Quadratic cost of building large objects"
+
+    Because every insertion scans all elements inserted so far, building an object of `n` distinct keys costs
+    **O(n²)** in total. This applies to filling an [`ordered_json`](ordered_json.md) object key by key as well as to
+    parsing one, since the parser inserts each key as it is read.
+
+    The cost is negligible for the object sizes typically found in configuration files or API payloads, but it grows
+    steeply for machine-generated objects with many thousands of keys. Measured with `-O2 -DNDEBUG` for parsing a flat
+    object of `n` keys, relative to `#!cpp nlohmann::json` (which uses `#!cpp std::map`):
+
+    | `n`    | `json` | `ordered_json` | factor |
+    |--------|--------|----------------|--------|
+    | 2000   | 0.7 ms | 3.6 ms         | 5×     |
+    | 4000   | 0.8 ms | 14.0 ms        | 19×    |
+    | 8000   | 1.6 ms | 67.8 ms        | 43×    |
+    | 16 000 | 3.3 ms | 181.6 ms       | 54×    |
+
+    If key order matters for objects of that size, consider a container with a lookup index, such as
+    [`tsl::ordered_map`](https://github.com/Tessil/ordered-map)
+    ([integration](https://github.com/nlohmann/json/issues/546#issuecomment-304447518)), as the object type -- see
+    [object order](../features/object_order.md).
+
 ## Examples
 
 ??? example

docs/mkdocs/docs/community/ecosystem.md

@@ -0,0 +1,40 @@
+# Ecosystem
+
+The projects below build on top of `nlohmann::json` rather than merely using it - schema validators, language
+bindings, format converters, and similar building blocks. The list is not exhaustive, and is curated rather than
+automatically generated. If you maintain or know of a project that belongs here,
+[please let me know](mailto:mail@nlohmann.me).
+
+For products, applications, and organizations that use the library, see [Customers](../home/customers.md) instead.
+
+## Schema validation
+
+- [**json-schema-validator**](https://github.com/pboettch/json-schema-validator), a JSON Schema (draft 7) validator
+  with human-readable error messages
+
+## Serialization and reflection
+
+- [**nlohmann_json_reflect**](https://github.com/1261385937/nlohmann_json_reflect), a reflection extension for
+  (de)serializing nested containers-in-structs-in-containers
+
+## Encodings
+
+- [**base-encode-decode**](https://github.com/saxonnicholls/base-encode-decode), a header-only Base64/32/16/8/4/2
+  (and DNA/RNA) encoding library, with an adapter that serializes binary data through `nlohmann::json`
+
+## Language bindings and interop
+
+- [**pybind11_json**](https://github.com/pybind/pybind11_json), a bidirectional type caster between
+  `nlohmann::json` and Python objects for [pybind11](https://github.com/pybind/pybind11) bindings
+- [**nanobind_json**](https://github.com/ianhbell/nanobind_json), the same idea for
+  [nanobind](https://github.com/wjakob/nanobind) bindings
+- [**nlohmann_json_qt**](https://github.com/dpurgin/nlohmann_json_qt), deserialization helpers for Qt types
+  (`QString`, `QUrl`, `QDateTime`, `QVector`, ...) from `nlohmann::json`
+- [**vulkan2json**](https://github.com/Fadis/vulkan2json), serialization and deserialization of Vulkan API structs
+
+## Format converters
+
+- [**tojson**](https://github.com/mircodz/tojson), a header-only converter between YAML/XML documents and
+  `nlohmann::json`
+- [**json2xml**](https://github.com/testillano/json2xml), a header-only converter from `nlohmann::json` to XML for
+  simple configuration documents

docs/mkdocs/docs/community/index.md

@@ -1,5 +1,6 @@
 # Community
 
+- [Ecosystem](ecosystem.md) - third-party projects built on top of this library
 - [Code of Conduct](code_of_conduct.md) - the rules and norms of this project
 - [Contribution Guidelines](contribution_guidelines.md) - guidelines how to contribute to this project
 - [Governance](governance.md) - the governance model of this project

docs/mkdocs/docs/community/quality_assurance.md

@@ -66,6 +66,7 @@ Note: Some modern features (like C++20 ranges or filesystem support) may be disa
         | Clang 20.1.1                                 | x86_64       | Ubuntu 22.04.1 LTS                | GitHub    |
         | Clang 20.1.8 with GNU-like command-line      | x86_64       | Windows Server 2022 (Build 20348) | GitHub    |
         | Clang 21.1.8                                 | x86_64       | Ubuntu 22.04.1 LTS                | GitHub    |
+        | Clang 22.1.8                                 | x86_64       | Ubuntu 22.04.1 LTS                | GitHub    |
         | CUDA 11.8.0 (nvcc)                           | x86_64       | Ubuntu 22.04 LTS                  | GitHub    |
         | CUDA 12.1.1 (nvcc)                           | x86_64       | Ubuntu 22.04 LTS                  | GitHub    |
         | CUDA 12.6.3 (nvcc)                           | x86_64       | Ubuntu 22.04 LTS                  | GitHub    |

docs/mkdocs/docs/examples/parser_callback_t.cpp

@@ -0,0 +1,47 @@
+#include <iostream>
+#include <nlohmann/json.hpp>
+
+using json = nlohmann::json;
+
+int main()
+{
+    // a JSON text with an array and a number inside an object
+    auto text = R"({"IDs": [116, 943], "Width": 800})";
+
+    // discard the array when the parser reads its opening bracket
+    json j_array_start = json::parse(text, [](int /*depth*/, json::parse_event_t event, json& /*parsed*/)
+    {
+        return event != json::parse_event_t::array_start;
+    });
+
+    // discard the same array when the parser reads its closing bracket
+    json j_array_end = json::parse(text, [](int /*depth*/, json::parse_event_t event, json& /*parsed*/)
+    {
+        return event != json::parse_event_t::array_end;
+    });
+
+    // discard the number, but keep its key
+    json j_value = json::parse(text, [](int /*depth*/, json::parse_event_t event, json & parsed)
+    {
+        return !(event == json::parse_event_t::value && parsed == json(800));
+    });
+
+    // discard the key of the number
+    json j_key = json::parse(text, [](int /*depth*/, json::parse_event_t event, json & parsed)
+    {
+        return !(event == json::parse_event_t::key && parsed == json("Width"));
+    });
+
+    // discard the top-level object
+    json j_root = json::parse(text, [](int /*depth*/, json::parse_event_t event, json& /*parsed*/)
+    {
+        return event != json::parse_event_t::object_end;
+    });
+
+    // in every case, the discarded value is removed together with its key
+    std::cout << j_array_start << '\n'
+              << j_array_end << '\n'
+              << j_value << '\n'
+              << j_key << '\n'
+              << j_root << '\n';
+}

docs/mkdocs/docs/examples/parser_callback_t.output

@@ -0,0 +1,5 @@
+{"Width":800}
+{"Width":800}
+{"IDs":[116,943]}
+{"IDs":[116,943]}
+null

docs/mkdocs/docs/features/binary_formats/bjdata.md

@@ -116,9 +116,20 @@ The library uses the following mapping from JSON values types to BJData types ac
     ```
 
     Likewise, when a JSON object in the above form is serialized using
-    [`to_bjdata`](../../api/basic_json/to_bjdata.md), it is automatically converted into a compact BJData ND-array. The
+    [`to_bjdata`](../../api/basic_json/to_bjdata.md), it is automatically converted into a compact BJData ND-array. When
-    only exception is, that when the 1-dimensional vector stored in `"_ArraySize_"` contains a single integer or two
+    the 1-dimensional vector stored in `"_ArraySize_"` contains a single integer or two integers with one being 1, a
-    integers with one being 1, a regular 1-D optimized array is generated.
+    regular 1-D optimized array is generated instead.
+
+    An object is only converted if the annotation actually describes a packed array; otherwise it is serialized as a
+    regular JSON object. This requires all of the following:
+
+    - `"_ArrayType_"` is one of `uint8`, `int8`, `uint16`, `int16`, `uint32`, `int32`, `uint64`, `int64`, `single`,
+      `double`, `char`, or `byte`,
+    - `"_ArraySize_"` is an array, since the dimensions are written as the ND-array header's length,
+    - every entry of `"_ArraySize_"` is a non-negative integer, and their product is representable as a `std::size_t`,
+    - `"_ArrayData_"` holds exactly that many elements, and
+    - every element of `"_ArrayData_"` is a number of the kind named by `"_ArrayType_"` (a floating-point number for
+      `single` and `double`, an integer otherwise).
 
     The current version of this library does not yet support automatic detection of and conversion from a nested JSON
     array input to a BJData ND-array.

docs/mkdocs/docs/features/binary_formats/bson.md

@@ -98,6 +98,17 @@ The library maps BSON record types to JSON value types as follows:
     This library deserializes BSON type `0x11` (Timestamp) as a `number_unsigned` value. The 64-bit value is preserved,
     but the Timestamp type information is not.
 
+!!! warning "Lenient BSON input handling"
+
+    The BSON reader is lenient in a few areas where the BSON specification is more restrictive:
+
+    - array element keys are not checked against the required decimal sequence (`0`, `1`, `2`, ...),
+    - any non-zero byte is accepted as `true` for the boolean type, and
+    - the payload for binary subtype `0x02` is returned as-is, including its inner length prefix.
+
+    If BSON input must be validated for strict specification compliance, validate it separately before passing it to
+    `from_bson()`.
+
 ??? example
 
     ```cpp

docs/mkdocs/docs/features/binary_formats/cbor.md

@@ -160,14 +160,11 @@ The library maps CBOR types to JSON value types as follows:
 
     The mapping is **incomplete** in the sense that not all CBOR types can be converted to a JSON value. The following CBOR types are not supported and will yield parse errors:
 
-     - date/time (0xC0..0xC1)
-     - bignum (0xC2..0xC3)
-     - decimal fraction (0xC4)
-     - bigfloat (0xC5)
-     - expected conversions (0xD5..0xD7)
      - simple values (0xE0..0xF3, 0xF8)
      - undefined (0xF7)
 
+    Tagged items (0xC0..0xDB) are not interpreted either; see the note on tagged items below.
+
 !!! warning "Negative integer overflow"
 
     CBOR negative integers (major type 1) are decoded as `-1 - n`. If the encoded magnitude `n` is too large for the
@@ -181,7 +178,7 @@ The library maps CBOR types to JSON value types as follows:
 
 !!! warning "Tagged items"
 
-    Tagged items will throw a parse error by default. They can be ignored by passing `cbor_tag_handler_t::ignore` to function `from_cbor`. They can be stored by passing `cbor_tag_handler_t::store` to function `from_cbor`.
+    Tagged items (0xC0..0xDB) will throw a parse error by default. They can be ignored by passing `cbor_tag_handler_t::ignore` to function `from_cbor`, in which case the tag is skipped and the enclosed data item is parsed on its own. They can be stored by passing `cbor_tag_handler_t::store` to function `from_cbor`. Note that no tag is ever interpreted: for instance, a text string tagged with tag 0 (date/time) stays a string.
 
 ??? example
 

docs/mkdocs/docs/features/binary_formats/ubjson.md

@@ -69,6 +69,12 @@ The library uses the following mapping from JSON values types to UBJSON types ac
     Note that `use_size = true` alone may result in larger representations - the benefit of this parameter is that the
     receiving side is immediately informed on the number of elements of the container.
 
+    An array whose type marker is `Z` (null), `T` (true) or `F` (false) stores no payload at all, because the marker
+    already is the value. Its declared count is therefore the only thing that decides how much memory the receiving side
+    allocates, and a handful of bytes can describe billions of elements. `from_ubjson` rejects such an array with
+    [`out_of_range.408`](../../home/exceptions.md#jsonexceptionout_of_range408) when the count exceeds 1,048,576, and
+    `to_ubjson` writes longer arrays of these types without the annotation, so any value it produces can be read back.
+
 !!! info "Binary values"
 
     If the JSON data contains the binary type, the value stored is a list of integers, as suggested by the UBJSON

docs/mkdocs/docs/features/conversions.md

@@ -54,6 +54,30 @@ json j = {1.0, "hello", 42};
 auto t = j.get<std::tuple<double, std::string, int>>();  // {1.0, "hello", 42}
 ```
 
+!!! warning "Serializing a `std::pair`/`std::tuple` whose every element is a string-keyed pair"
+
+    When *every* element of a `#!cpp std::pair` or `#!cpp std::tuple` is itself a two-element array whose first
+    element is a string (for example `#!cpp std::pair<std::string, int>`), serializing it produces a JSON **object**
+    instead of the expected array:
+
+    ```cpp
+    using kv = std::pair<std::string, int>;
+    json j = std::pair<kv, kv>{{"a", 1}, {"b", 2}};  // {"a":1,"b":2}, not [["a",1],["b",2]]
+    ```
+
+    This is a consequence of the [brace-initializer object-detection rule](creating_values.md): the same rule that
+    lets `#!cpp json{{"a", 1}, {"b", 2}}` create an object also fires here. The resulting object cannot be read back
+    into the original type (`#!cpp get<std::pair<kv, kv>>()` throws [`type_error.302`](../home/exceptions.md#jsonexceptiontype_error302)),
+    and duplicate keys collapse into one, losing elements. This only affects `#!cpp std::pair`/`#!cpp std::tuple`
+    themselves; a `#!cpp std::vector<std::pair<std::string, int>>`, or a pair/tuple with at least one element that is
+    not a string-keyed pair, serializes to an array as expected. To force an array, build one explicitly from the
+    elements with [`array`](../api/basic_json/array.md):
+
+    ```cpp
+    std::pair<kv, kv> p{{"a", 1}, {"b", 2}};
+    json a = json::array({p.first, p.second});  // [["a",1],["b",2]]
+    ```
+
 !!! info "Extracting references into a tuple"
 
     A tuple type may also hold references (e.g. `#!cpp std::tuple<double&, std::string&>`) to avoid copying: `get`
@@ -66,8 +90,14 @@ auto t = j.get<std::tuple<double, std::string, int>>();  // {1.0, "hello", 42}
     std::get<1>(refs) = "world";  // modifies j[1] in place
     ```
 
-    A referenced type must be one the library actually stores (or an arithmetic type it can convert to/from);
+    A referenced element must name the type the library actually *stores* — one of [`boolean_t`](../api/basic_json/boolean_t.md),
-    otherwise this is a compile error.
+    [`number_integer_t`](../api/basic_json/number_integer_t.md), [`number_unsigned_t`](../api/basic_json/number_unsigned_t.md),
+    [`number_float_t`](../api/basic_json/number_float_t.md), [`string_t`](../api/basic_json/string_t.md),
+    [`binary_t`](../api/basic_json/binary_t.md), [`array_t`](../api/basic_json/array_t.md), or
+    [`object_t`](../api/basic_json/object_t.md). There is nothing else to refer to, so a reference to any other type is a
+    compile error even when a conversion would exist: `#!cpp std::tuple<int&>` is rejected, because the library stores a
+    `#!cpp number_integer_t` (`#!cpp std::int64_t` by default) and not an `#!cpp int`. This restriction applies only to
+    reference elements — a plain `#!cpp std::tuple<int>` converts by value as usual.
 
 ## Implicit conversions
 
@@ -116,17 +146,34 @@ which forces the explicit `get` form and can catch unintended conversions at com
     with a custom `adl_serializer<std::optional<T>>` specialization. Prefer `get<std::optional<T>>()`/`get_to()`
     over `static_cast` for optional types.
 
-!!! warning "Converting to a fixed-size `std::array` does not check length"
+!!! warning "Converting to a fixed-size destination does not check the array size"
 
-    Converting a JSON array to `#!cpp std::array<T, N>` does not check that the JSON array's size matches `N`:
+    Some destination types have a size that is fixed by their C++ type rather than by the JSON value:
-    if the JSON array is longer, the extra elements are silently dropped; if it is shorter, the remaining
+    `#!cpp std::pair<A, B>`, `#!cpp std::tuple<Ts...>`, `#!cpp std::array<T, N>`, C arrays `#!cpp T[N]`, and
-    `std::array` elements are left default-constructed. No exception is thrown in either case.
+    `#!cpp std::map`/`#!cpp std::unordered_map` with a non-string key type (which is read from an array of
+    two-element arrays). All of them read exactly as many elements as they need via
+    [`at`](../api/basic_json/at.md) and **never compare the JSON array's size to that number**. The two
+    mismatch directions therefore behave differently:
+
+    - The JSON array has **too many** elements: the surplus is **silently discarded**, and no exception is
+      thrown.
+    - The JSON array has **too few** elements: `at` throws
+      [`out_of_range.401`](../home/exceptions.md#jsonexceptionout_of_range401) for the first missing index --
+      an out-of-range error, not a [`type_error`](../home/exceptions.md#type-errors), even though the cause
+      is a shape mismatch.
 
     ```cpp
     json j = {1, 2, 3, 4, 5};
-    auto a = j.get<std::array<int, 3>>();  // {1, 2, 3} -- elements 4 and 5 silently dropped
+
+    auto a = j.get<std::array<int, 3>>();       // {1, 2, 3} -- elements 4 and 5 silently dropped
+    auto p = j.get<std::pair<int, int>>();      // (1, 2)    -- elements 3, 4, and 5 silently dropped
+
+    json k = {1};
+    auto q = k.get<std::pair<int, int>>();      // ❌ throws out_of_range.401
     ```
 
+    If a size mismatch is an error in your application, check the size yourself before converting.
+
 ## Omitting a field when serializing `std::optional`
 
 By default, `to_json` for `std::optional<T>` writes either the value or `#!json null` -- there is no built-in way

docs/mkdocs/docs/features/object_order.md

@@ -53,6 +53,12 @@ If you do want to preserve the **insertion order**, you can use the type [`nlohm
 
 Alternatively, you can use a more sophisticated ordered map like [`tsl::ordered_map`](https://github.com/Tessil/ordered-map) ([integration](https://github.com/nlohmann/json/issues/546#issuecomment-304447518)) or [`nlohmann::fifo_map`](https://github.com/nlohmann/fifo_map) ([integration](https://github.com/nlohmann/json/issues/485#issuecomment-333652309)).
 
+The [`ordered_map`](../api/ordered_map.md) behind `nlohmann::ordered_json` is deliberately minimal and has no lookup
+index, so every key access is a linear scan and building an object of `n` keys costs O(n²). This is unnoticeable at
+typical object sizes but becomes significant for objects with many thousands of keys; see
+[`ordered_map` complexity](../api/ordered_map.md#complexity). The alternatives above keep a lookup index and do not
+have this cost.
+
 ### Notes on parsing
 
 Note that you also need to call the right [`parse`](../api/basic_json/parse.md) function when reading from a file.

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

@@ -28,6 +28,22 @@ Inputs consisting of multiple values separated by newlines are handled by the [J
 By default, the library rejects comments and trailing commas. Both can be enabled with parameters of the `parse`
 function — see [comments](../comments.md) and [trailing commas](../trailing_commas.md).
 
+## Strictness and trailing data
+
+[`parse`](../../api/basic_json/parse.md) reads a single JSON value and requires the whole input to be consumed: any
+non-whitespace data after the value is reported as a parse error. Use it when you want to guarantee that an input is
+exactly one complete JSON document.
+
+[`operator>>`](../../api/operator_gtgt.md) follows relaxed `#!cpp std::istream` semantics instead: it parses one JSON
+value and leaves the stream positioned right after it, without requiring the rest of the stream to be consumed. This is
+what makes it possible to read several concatenated values from the same stream, but it also means that "a valid
+document followed by trailing bytes" is accepted rather than rejected. If you are validating conformance, or need to
+reject any input that is not exactly one JSON document, prefer `parse`.
+
+When using `operator>>` to read several concatenated values this way, a value that is a number must be followed by
+whitespace, because `operator>>` consumes the character that terminates a number — see the
+[`operator>>` notes](../../api/operator_gtgt.md#notes) for details and examples.
+
 ## SAX vs. DOM parsing
 
 The library offers two parsing models:

docs/mkdocs/docs/features/parsing/json_lines.md

@@ -49,4 +49,5 @@ JSON Lines input with more than one value is treated as invalid JSON by the [`pa
     with a JSON Lines input does not work, because the parser will try to parse one value after the last one.
 
     This is different from parsing a stream of *concatenated* (non-newline-delimited) JSON values, for which
-    `operator>>` does work -- see its [notes](../../api/operator_gtgt.md#notes) for details.
+    `operator>>` does work, provided that a value that is a number is followed by whitespace -- see its
+    [notes](../../api/operator_gtgt.md#notes) for details.

docs/mkdocs/docs/home/customers.md

@@ -8,41 +8,72 @@ the result of an internet search. If you know further customers of the library,
 ## Space Exploration
 
 - [**Peregrine Lunar Lander Flight 01**](https://en.wikipedia.org/wiki/Peregrine_Mission_One) - The library was used for payload management in the **Peregrine Moon Lander**, developed by **Astrobotic Technology** and launched as part of NASA's **Commercial Lunar Payload Services (CLPS)** program. After six days in orbit, the spacecraft was intentionally redirected into Earth's atmosphere, where it burned up over the Pacific Ocean on **January 18, 2024**.
+- [**NASA Unsteady Pressure-Sensitive Paint Processing**](https://github.com/nasa/upsp-processing), NASA software for processing high-speed video recordings of wind tunnel tests on launch vehicle and aircraft models
+- [**Terma TEMU**](https://temu.terma.com/docs/public/temu-release-notes/latest/copying/json-for-modern-cpp.html), an emulator of spacecraft on-board computers used to develop and validate flight software for European space missions
 
 ## Automotive
 
 - [**Alexa Auto SDK**](https://github.com/alexa/alexa-auto-sdk), a software development kit enabling the integration of Alexa into automotive systems
 - [**Apollo**](https://github.com/ApolloAuto/apollo), a framework for building autonomous driving systems
 - [**Automotive Grade Linux (AGL)**](https://download.automotivelinux.org/AGL/release/jellyfish/latest/qemux86-64/deploy/licenses/nlohmann-json/), a collaborative open-source platform for automotive software development
+- [**Autoware**](https://github.com/autowarefoundation/autoware_universe), an open-source software stack for autonomous driving built on ROS 2
+- [**Eclipse S-CORE**](https://github.com/eclipse-score/nlohmann_json), an open-source software platform for the software-defined vehicle backed by major automotive manufacturers and suppliers
 - [**Genesis Motor** (infotainment)](http://webmanual.genesis.com/ccIC/AVNT/JW/KOR/English/reference010.html), a luxury automotive brand
 - [**Hyundai** (infotainment)](https://www.hyundai.com/wsvc/ww/download.file.do?id=/content/hyundai/ww/data/opensource/data/GN7-2022/licenseCode/info), a global automotive brand
 - [**Kia** (infotainment)](http://webmanual.kia.com/PREM_GEN6/AVNT/RJPE/KOR/Korean/reference010.html), a global automotive brand
 - [**Mercedes-Benz Operating System (MB.OS)**](https://group.mercedes-benz.com/careers/about-us/mercedes-benz-operating-system/), a core component of the vehicle software ecosystem from Mercedes-Benz
+- [**NVIDIA DRIVE OS**](https://developer.nvidia.com/docs/drive/drive-os/6.0.5/public/driveworks-nvcgf/dwx_open_source_attribution.html), the operating system and DriveWorks SDK powering NVIDIA's platform for autonomous vehicles
 - [**Rivian** (infotainment)](https://assets.ctfassets.net/2md5qhoeajym/3cwyo4eoufk4yingUwusFt/ded2c47da620fdfc99c88c7156d2c1d8/In-Vehicle_OSS_Attribution_2024__11-24_.pdf), an electric vehicle manufacturer
 - [**Suzuki** (infotainment)](https://www.globalsuzuki.com/motorcycle/ipc/oss/oss_48KA_00.pdf), a global automotive and motorcycle manufacturer
 
 ## Gaming and Entertainment
 
+- [**Anno 117: Pax Romana**](https://www.mobygames.com/person/1195889/niels-lohmann/credits/), a city-building strategy game set in the Roman Empire
 - [**Assassin's Creed: Mirage**](https://www.mobygames.com/person/1195889/niels-lohmann/credits/), a stealth-action game set in the Middle East, focusing on the journey of a young assassin with classic parkour and stealth mechanics
+- [**Battlefield 6**](https://www.mobygames.com/person/1195889/niels-lohmann/credits/), a military first-person shooter known for its large-scale multiplayer battles
+- [**Battlefield: REDSEC**](https://www.mobygames.com/person/1195889/niels-lohmann/credits/), a free-to-play battle royale experience set in the Battlefield universe
+- [**BioMenace: Remastered**](https://www.mobygames.com/person/1195889/niels-lohmann/credits/), a remaster of the classic side-scrolling platform shooter
 - [**Chasm: The Rift**](https://www.mobygames.com/person/1195889/niels-lohmann/credits/), a first-person shooter blending horror and adventure, where players navigate dark realms and battle monsters
 - [**College Football 25**](https://www.mobygames.com/person/1195889/niels-lohmann/credits/), a college football simulation game featuring gameplay that mimics real-life college teams and competitions
+- [**College Football 26**](https://www.mobygames.com/person/1195889/niels-lohmann/credits/), a college football simulation game featuring licensed teams and stadiums
+- [**College Football 27**](https://www.mobygames.com/person/1195889/niels-lohmann/credits/), the latest installment of the college football simulation series
 - [**Concepts**](https://concepts.app/en/licenses), a digital sketching app designed for creative professionals, offering flexible drawing tools for illustration, design, and brainstorming
 - [**Depthkit**](https://www.depthkit.tv/third-party-licenses), a tool for creating and capturing volumetric video, enabling immersive 3D experiences and interactive content
+- [**Dune: Awakening**](https://www.mobygames.com/person/1195889/niels-lohmann/credits/), an open-world survival MMO set on the desert planet Arrakis
+- [**EA Sports FC 25**](https://www.mobygames.com/person/1195889/niels-lohmann/credits/), an association football simulation with club, career, and online modes
+- [**EA Sports FC 26**](https://www.mobygames.com/person/1195889/niels-lohmann/credits/), the latest installment of the association football simulation series
+- [**EA Sports UFC 6**](https://www.mobygames.com/person/1195889/niels-lohmann/credits/), a mixed martial arts fighting simulation
+- [**FiveM**](https://github.com/citizenfx/fivem), a modification framework for Grand Theft Auto V that powers custom multiplayer servers
+- [**FLUX:: Immersive**](https://doc.flux.audio/syrah/Credits.html), a suite of professional audio processing and immersive mixing plugins used in music and post-production
 - [**IMG.LY**](https://img.ly/acknowledgements), a platform offering creative tools and SDKs for integrating advanced image and video editing in applications
+- [**immersivetech**](https://immersitech.io/open-source-third-party-software/), a technology company focused on immersive experiences, providing tools and solutions for virtual and augmented reality applications
+- [**Kodi**](https://github.com/xbmc/xbmc/blob/master/xbmc/utils/JSONVariantWriter.cpp), a home theater and media center application
 - [**LOOT**](https://loot.readthedocs.io/_/downloads/en/0.13.0/pdf/), a tool for optimizing the load order of game plugins, commonly used in The Elder Scrolls and Fallout series
+- [**LunaTranslator**](https://github.com/HIllya51/LunaTranslator/blob/main/src/NativeImpl/LunaSubprocess/aspatch.cpp), a real-time translation tool for visual novels
+- [**MaaAssistantArknights**](https://github.com/MaaAssistantArknights/MaaAssistantArknights/blob/dev-v2/src/MaaCore/Vision/Roguelike/BlackFlow/BlackFlowMapAnalyzer.cpp), an automation assistant for the mobile game Arknights
 - [**Madden NFL 25**](https://www.mobygames.com/person/1195889/niels-lohmann/credits/), a sports simulation game capturing the excitement of American football with realistic gameplay and team management features
+- [**Madden NFL 26**](https://www.mobygames.com/person/1195889/niels-lohmann/credits/), an American football simulation with franchise and team management modes
+- [**Madden NFL 27**](https://www.mobygames.com/person/1195889/niels-lohmann/credits/), the latest installment of the American football simulation series
 - [**Marne**](https://marne.io/licenses), an unofficial private server platform for hosting custom Battlefield 1 game experiences
 - [**Minecraft**](https://www.minecraft.net/zh-hant/attribution), a popular sandbox video game
+- [**Mumble**](https://github.com/mumble-voip/mumble), a low-latency, open-source voice chat application widely used by gaming communities
 - [**NHL 22**](https://www.mobygames.com/person/1195889/niels-lohmann/credits/), a hockey simulation game offering realistic gameplay, team management, and various modes to enhance the hockey experience
+- [**OBS Studio**](https://github.com/obsproject/obs-studio), a free and open-source suite for video recording and live streaming
+- [**OpenRCT2**](https://github.com/OpenRCT2/OpenRCT2/blob/develop/src/openrct2/core/JsonFwd.hpp), an open source re-implementation of RollerCoaster Tycoon 2
 - [**Pixelpart**](https://pixelpart.net/documentation/book/third-party.html), a 2D animation and video compositing software that allows users to create animated graphics and visual effects with a focus on simplicity and ease of use
 - [**Razer Cortex**](https://mysupport.razer.com/app/answers/detail/a_id/14146/~/open-source-software-for-razer-software), a gaming performance optimizer and system booster designed to enhance the gaming experience
 - [**Red Dead Redemption II**](https://www.mobygames.com/person/1195889/niels-lohmann/credits/), an open-world action-adventure game following an outlaw's story in the late 1800s, emphasizing deep storytelling and immersive gameplay
+- [**RetroArch**](https://github.com/libretro/RetroArch), a frontend for emulators, game engines, and media players built on the libretro API
+- [**shadPS4**](https://github.com/shadps4-emu/shadPS4/blob/main/src/core/user_manager.h), a PlayStation 4 emulator for Windows, Linux and macOS
+- [**skate.**](https://www.mobygames.com/person/1195889/niels-lohmann/credits/), a free-to-play skateboarding game set in an open world
 - [**Snapchat**](https://www.snap.com/terms/license-android), a multimedia messaging and augmented reality app for communication and entertainment
+- [**Steel Century Groove**](https://www.mobygames.com/person/1195889/niels-lohmann/credits/), an action game released in 2026
+- [**Sunshine**](https://github.com/LizardByte/Sunshine/blob/master/src/confighttp.h), a self-hosted game streaming host compatible with Moonlight clients
 - [**Tactics Ogre: Reborn**](https://www.square-enix-games.com/en_US/documents/tactics-ogre-reborn-pc-installer-software-and-associated-plug-ins-disclosure), a tactical role-playing game featuring strategic battles and deep storytelling elements
 - [**Throne and Liberty**](https://www.amazon.com/gp/help/customer/display.html?nodeId=T7fLNw5oAevCMtJFPj&pop-up=1), an MMORPG that offers an expansive fantasy world with dynamic gameplay and immersive storytelling
 - [**Unity Vivox**](https://docs.unity3d.com/Packages/com.unity.services.vivox@15.1/license/Third%20Party%20Notices.html), a communication service that enables voice and text chat functionality in multiplayer games developed with Unity
+- [**xemu**](https://github.com/xemu-project/xemu), an emulator of the original Xbox console
 - [**Zool: Redimensioned**](https://www.mobygames.com/person/1195889/niels-lohmann/credits/), a modern reimagining of the classic platformer featuring fast-paced gameplay and vibrant environments
-- [**immersivetech**](https://immersitech.io/open-source-third-party-software/), a technology company focused on immersive experiences, providing tools and solutions for virtual and augmented reality applications
 
 ## Consumer Electronics
 
@@ -50,109 +81,195 @@ the result of an internet search. If you know further customers of the library,
 - [**Canon CanoScan LIDE**](https://carolburo.com/wp-content/uploads/2024/06/LiDE400_OnlineManual_Win_FR_V02.pdf), a series of flatbed scanners offering high-resolution image scanning for home and office use
 - [**Canon PIXMA Printers**](https://www.mediaexpert.pl/products/files/73/7338196/Instrukcja-obslugi-CANON-Pixma-TS7450i.pdf), a line of all-in-one inkjet printers known for high-quality printing and wireless connectivity
 - [**Cisco Webex Desk Camera**](https://www.cisco.com/c/dam/en_us/about/doing_business/open_source/docs/CiscoWebexDeskCamera-23-1622100417.pdf), a video camera designed for professional-quality video conferencing and remote collaboration
+- [**DJI Edge SDK**](https://github.com/dji-sdk/Edge-SDK-V2-Demo), the reference applications for DJI's Edge SDK, used to build edge computing services on DJI drone docks
+- [**Elgato Stream Deck**](https://github.com/elgatosf/streamdeck-obs-plugin2), a family of programmable control surfaces for content creators and their plugin ecosystem
+- [**Instagrid**](https://instagrid.co/intellectual-property/foss), a manufacturer of portable, high-performance battery systems for professional mobile power supply
+- [**iRobot**](https://iot-content.irobot.com/iw/sfsites/c/cms/delivery/media/MCKRLTPDJSSJBNJKDA5SG5UVVIIQ), a manufacturer of autonomous home robots including the Roomba vacuum cleaner range
+- [**Logitech Logi Bolt**](https://opensource.logitech.com/wiki/Logi_BoltApp/), the management application for Logitech's secure wireless connectivity technology
+- [**Novitus**](https://novitus.pl/licencjepensource), a manufacturer of fiscal cash registers and point-of-sale devices
 - [**Philips Hue Personal Wireless Lighting**](http://2ak5ape.257.cz/), a smart lighting system for customizable and wireless home illumination
 - [**Ray-Ban Meta Smart glasses**](https://www.meta.com/de/en/legal/smart-glasses/third-party-notices-android/03/), a pair of smart glasses designed for capturing photos and videos with integrated connectivity and social features
 - [**Razer Synapse**](https://mysupport.razer.com/app/answers/detail/a_id/14146/~/open-source-software-for-razer-software), a unified configuration software enabling hardware customization for Razer devices
+- [**Sharp Professional Displays**](https://jp.sharp/restricted/business/lcd-display/cms/images/source_pnla862/PN-LA652_752_862_LicenseInformation.pdf), a range of large-format interactive displays for business and education
 - [**Siemens SINEMA Remote Connect**](https://cache.industry.siemens.com/dl/files/790/109793790/att_1054961/v2/OSS_SINEMA-RC_86.pdf), a remote connectivity solution for monitoring and managing industrial networks and devices securely
+- [**Skydio**](https://pages.skydio.com/rs/784-TUF-591/images/Open%20Source%20Software%20Notice%20v0.2.html), a manufacturer of autonomous drones for inspection, public safety, and defense applications
 - [**Sony PlayStation 4**](https://doc.dl.playstation.net/doc/ps4-oss/index.html), a gaming console developed by Sony that offers a wide range of games and multimedia entertainment features
+- [**Sony Spatial Reality Display**](https://www.sony.co.jp/en/Products/Developer-Spatial-Reality-display/download/dcc-tools/blender-plugin/SpatiaRealityDisplayPluginforPreviewBL_Manual.pdf), a glasses-free stereoscopic 3D display and its plugins for Blender, 3ds Max, and ZBrush
 - [**Sony Virtual Webcam Driver for Remote Camera**](https://helpguide.sony.net/rc/vwd/v1/zh-cn/print.pdf), a software driver that enables the use of Sony cameras as virtual webcams for video conferencing and streaming
+- [**Yamaha Clavinova**](https://usa.yamaha.com/files/download/other_assets/1/2298171/CLP-800_oss_license.pdf), a series of digital pianos combining acoustic piano feel with digital sound technology
 
-## Operating Systems
+## Operating Systems and Platforms
 
 - [**Apple iOS and macOS**](https://www.apple.com/macos), a family of operating systems developed by Apple, including iOS for mobile devices and macOS for desktop computers
+- [**Chromium**](https://chromium.googlesource.com/chromium/src/+/main/third_party/nlohmann_json/), the open-source browser project that Google Chrome, Microsoft Edge, and many other browsers are built on, where the library is used as data container for on-device model execution
 - [**Google Fuchsia**](https://fuchsia.googlesource.com/third_party/json/), an open-source operating system developed by Google, designed to be secure, updatable, and adaptable across various devices
+- [**LG webOS**](https://github.com/webosose/com.webos.service.camera), a Linux-based operating system used in LG smart TVs, signage, and embedded devices
+- [**Microsoft Azure Linux**](https://github.com/microsoft/azurelinux), a Linux distribution developed by Microsoft for Azure infrastructure and edge workloads
+- [**OpenHarmony**](https://github.com/openharmony/third_party_json), an open-source operating system for smart devices and the foundation of HarmonyOS
 - [**SerenityOS**](https://github.com/SerenityOS/serenity), an open-source operating system that aims to provide a simple and beautiful user experience with a focus on simplicity and elegance
+- [**Windows Subsystem for Linux**](https://github.com/microsoft/WSL), a compatibility layer that runs Linux environments natively on Windows
 - [**Yocto**](http://ftp.emacinc.com/openembedded-sw/kirkstone-icop-5.15-kirkstone-6.0/archive-2024-10/pn8m-090t-ppc/licenses/nlohmann-json/), a Linux-based build system for creating custom operating systems and software distributions, tailored for embedded devices and IoT applications
 
 ## Development Tools and IDEs
 
 - [**Accentize SpectralBalance**](https://www.accentize.com/products/SpectralBalanceManual.pdf), an adaptive speech analysis tool designed to enhance audio quality by optimizing frequency balance in recordings
+- [**Airbus Ghidralligator**](https://www.cyber.airbus.com/en/newsroom/stories/2025-06-ghidralligator), a Ghidra-based emulator from Airbus CyberSecurity used to fuzz and analyse embedded firmware
+- [**Apache brpc**](https://github.com/apache/brpc/blob/master/src/butil/iobuf.h), an industrial-grade remote procedure call framework for C++
 - [**Arm Compiler for Linux**](https://documentation-service.arm.com/static/66558e9d876c8d213b7843e4), a software development toolchain for compiling and optimizing applications on Arm-based Linux systems
 - [**BBEdit**](https://s3.amazonaws.com/BBSW-download/BBEdit_15.1.2_User_Manual.pdf), a professional text and code editor for macOS
 - [**CoderPad**](https://coderpad.io), a collaborative coding platform that enables real-time code interviews and assessments for developers; the library is included in every CoderPad instance and can be accessed with a simple `#include "json.hpp"`
+- [**Codon**](https://github.com/exaloop/codon/blob/develop/jupyter/jupyter.h), an ahead-of-time compiler for a Python-like language
 - [**Compiler Explorer**](https://godbolt.org), a web-based tool that allows users to write, compile, and visualize the assembly output of code in various programming languages; the library is readily available and accessible with the directive `#include <nlohmann/json.hpp>`.
-- [**GitHub CodeQL**](https://github.com/github/codeql), a code analysis tool used for identifying security vulnerabilities and bugs in software through semantic queries
+- [**Flutter**](https://github.com/flutter/flutter/blob/master/engine/src/flutter/impeller/compiler/reflector.cc), a UI toolkit for building natively compiled applications for mobile, web, and desktop from a single codebase
+- [**Fraunhofer VVenC**](https://github.com/fraunhoferhhi/vvenc), a fast and efficient encoder for the Versatile Video Coding (H.266/VVC) standard
+- [**GitHub CodeQL**](https://github.com/github/codeql/blob/main/shared/cpp/Diagnostics.h), a code analysis tool used for identifying security vulnerabilities and bugs in software through semantic queries
+- [**GoPro ngfx**](https://github.com/gopro/ngfx), a low-level graphics abstraction and profiling framework developed by GoPro
+- [**gRPC**](https://github.com/grpc/grpc/blob/master/tools/artifact_gen/utils.h), a high-performance universal remote procedure call framework
 - [**Hex-Rays**](https://docs.hex-rays.com/user-guide/user-interface/licenses), a reverse engineering toolset for analyzing and decompiling binaries, primarily used for security research and vulnerability analysis
 - [**ImHex**](https://github.com/WerWolv/ImHex), a hex editor designed for reverse engineering, providing advanced features for data analysis and manipulation
+- [**Intel GITS**](https://github.com/intel/gits), a tool for capturing and replaying graphics API calls for debugging and performance analysis
 - [**Intel GPA Framework**](https://intel.github.io/gpasdk-doc/src/licenses.html), a suite of cross-platform tools for capturing, analyzing, and optimizing graphics applications across different APIs
 - [**Intopix**](https://www.intopix.com/software-licensing), a provider of advanced image processing and compression solutions used in software development and AV workflows
 - [**Java SE**](https://www.oracle.com/a/tech/docs/jdk8-lium.pdf), the core Java platform that provides the libraries and runtime needed to build and run general-purpose Java applications
-- [**MKVToolNix**](https://mkvtoolnix.download/doc/README.md), a set of tools for creating, editing, and inspecting MKV (Matroska) multimedia container files
 - [**Meta Yoga**](https://github.com/facebook/yoga), a layout engine that facilitates flexible and efficient user interface design across multiple platforms
-- [**NVIDIA Nsight Compute**](https://docs.nvidia.com/nsight-compute/2022.2/pdf/CopyrightAndLicenses.pdf), a performance analysis tool for CUDA applications that provides detailed insights into GPU performance metrics
+- [**MKVToolNix**](https://mkvtoolnix.download/doc/README.md), a set of tools for creating, editing, and inspecting MKV (Matroska) multimedia container files
+- [**MRTech IFF SDK**](https://mr-technologies.com/pub/iff-sdk-manual-2-0-1/iff-sdk-manual-2-0-1.pdf), an image processing SDK for machine vision applications with GPU-accelerated pipelines
+- [**Nix**](https://github.com/NixOS/nix/blob/master/src/nix/build.cc), a purely functional package manager
 - [**Notepad++**](https://github.com/notepad-plus-plus/notepad-plus-plus), a free source code editor that supports various programming languages
+- [**NVIDIA Nsight Compute**](https://docs.nvidia.com/nsight-compute/2022.2/pdf/CopyrightAndLicenses.pdf), a performance analysis tool for CUDA applications that provides detailed insights into GPU performance metrics
+- [**openFrameworks**](https://github.com/openframeworks/openFrameworks/blob/master/libs/openFrameworks/utils/ofJson.h), a community-developed C++ toolkit for creative coding
 - [**OpenRGB**](https://gitlab.com/CalcProgrammer1/OpenRGB), an open source RGB lighting control that doesn't depend on manufacturer software
 - [**OpenTelemetry C++**](https://github.com/open-telemetry/opentelemetry-cpp), a library for collecting and exporting observability data in C++, enabling developers to implement distributed tracing and metrics in their application
+- [**Oracle GraalVM**](https://docs.oracle.com/en/graalvm/jdk/21/docs/licensing-information/), a high-performance JDK distribution with ahead-of-time compilation and polyglot runtime support
+- [**Philips amp-cucumber-cpp-runner**](https://github.com/philips-software/amp-cucumber-cpp-runner), a behaviour-driven development test runner for embedded C++ software developed at Philips
 - [**Qt Creator**](https://doc.qt.io/qtcreator/qtcreator-attribution-json-nlohmann.html), an IDE for developing applications using the Qt application framework
+- [**Qt for MCUs**](https://doc.qt.io/QtForMCUs/quickultralite-attribution-nlohmann-json.html), a graphics framework for building fluid user interfaces on microcontrollers
+- [**React Native**](https://github.com/react/react-native/blob/main/packages/react-native/ReactCxxPlatform/react/devsupport/PackagerConnection.cpp), a framework for building native mobile applications using React
 - [**Scanbot SDK**](https://docs.scanbot.io/barcode-scanner-sdk/web/third-party-libraries/), a software development kit (SDK) that provides tools for integrating advanced document scanning and barcode scanning capabilities into applications
+- [**STMicroelectronics TouchGFX**](https://www.st.com/resource/en/additional_license_terms/additional-license-terms-x-cube-touchgfx.html), a graphical user interface framework shipped with STM32 microcontrollers for building embedded HMIs
+- [**swagger-codegen**](https://github.com/swagger-api/swagger-codegen/blob/master/samples/server/petstore/pistache-server/model/Pet.h), a template-driven engine that generates API clients and server stubs from an OpenAPI specification
+- [**Swoole**](https://github.com/swoole/swoole-src/blob/master/ext-src/swoole_admin_server.cc), a coroutine-based concurrency engine for PHP
+- [**Tracy Profiler**](https://github.com/wolfpld/tracy/blob/master/profiler/src/profiler/TracyLlm.hpp), a real-time frame profiler for games and other applications
+- [**WasmEdge**](https://github.com/WasmEdge/WasmEdge/blob/master/plugins/wasi_nn/GGML/tts/tts_core.cpp), a lightweight WebAssembly runtime for edge and cloud workloads
+- [**x64dbg**](https://github.com/x64dbg/x64dbg/blob/development/src/cross/remote_table/TableRpcData.h), an open source user mode debugger for Windows, aimed at reverse engineering and malware analysis
 
 ## Machine Learning and AI
 
+- [**Alibaba MNN**](https://github.com/alibaba/MNN), a lightweight deep learning inference engine for mobile and embedded devices
+- [**AMD Gaia**](https://github.com/amd/gaia), an open-source framework for running generative AI applications locally on AMD hardware
+- [**AMD Vitis AI (VAIP)**](https://github.com/amd/vaip), the execution provider stack that runs AI models on AMD Ryzen AI and adaptive computing devices
 - [**Apple Core ML Tools**](https://github.com/apple/coremltools), a set of tools for converting and configuring machine learning models for deployment in Apple's Core ML framework
 - [**Avular Mobile Robotics**](https://www.avular.com/licenses/nlohmann-json-3.9.1.txt), a platform for developing and deploying mobile robotics solutions
+- [**FunASR**](https://github.com/modelscope/FunASR/blob/main/runtime/http/bin/asr_sessions.h), a speech recognition toolkit for training and deploying end-to-end models
 - [**Google gemma.cpp**](https://github.com/google/gemma.cpp), a lightweight C++ inference engine designed for running AI models from the Gemma family
+- [**Google Magenta The Infinite Crate**](https://github.com/magenta/the-infinite-crate), an open-source generative AI plugin for digital audio workstations from Google's Magenta research team
+- [**GPT4All**](https://github.com/nomic-ai/gpt4all/blob/main/gpt4all-chat/src/tool.h), a desktop application for running local large language models on consumer hardware
+- [**Huawei MindSpore**](https://github.com/mindspore-ai/mindspore/blob/master/Third_Party_Open_Source_Software_Notice), a deep learning framework for training and inference across device, edge, and cloud
+- [**KTransformers**](https://github.com/kvcache-ai/ktransformers/blob/main/archive/csrc/balance_serve/sched/model_config.h), a framework for heterogeneous large language model inference
 - [**llama.cpp**](https://github.com/ggerganov/llama.cpp), a C++ library designed for efficient inference of large language models (LLMs), enabling streamlined integration into applications
+- [**LocalAI**](https://github.com/mudler/LocalAI/blob/master/backend/cpp/ds4/dsml_renderer.cpp), a self-hosted inference engine that exposes local models through an OpenAI-compatible API
 - [**MLX**](https://github.com/ml-explore/mlx), an array framework for machine learning on Apple Silicon
 - [**Mozilla llamafile**](https://github.com/Mozilla-Ocho/llamafile), a tool designed for distributing and executing large language models (LLMs) efficiently using a single file format
 - [**NVIDIA ACE**](https://docs.nvidia.com/ace/latest/index.html), a suite of real-time AI solutions designed for the development of interactive avatars and digital human applications, enabling scalable and sophisticated user interactions
+- [**NVIDIA Instant NGP**](https://github.com/NVlabs/instant-ngp/blob/master/src/nerf_loader.cu), an implementation of instant neural graphics primitives for rapid scene reconstruction
+- [**NVIDIA TensorRT**](https://github.com/NVIDIA/TensorRT), an SDK for high-performance deep learning inference, including its TensorRT-LLM extension for large language models
+- [**NVIDIA TensorRT-LLM**](https://github.com/NVIDIA/TensorRT-LLM/blob/main/cpp/tensorrt_llm/common/safetensors.cpp), a toolkit for optimizing and serving large language model inference on GPUs
+- [**ONNX Runtime**](https://github.com/microsoft/onnxruntime), a cross-platform inference and training accelerator for machine learning models
+- [**OpenVINO**](https://github.com/openvinotoolkit/openvino), Intel's toolkit for optimizing and deploying deep learning inference across CPUs, GPUs, and NPUs
+- [**PaddleOCR**](https://github.com/PaddlePaddle/PaddleOCR/blob/main/deploy/cpp_infer/src/modules/text_detection/result.cc), an optical character recognition toolkit that turns documents and images into structured data
+- [**PaddlePaddle**](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/ap/src/axpr/anf_expr.cc), a deep learning framework for distributed training and inference
 - [**Peer**](https://support.peer.inc/hc/en-us/articles/17261335054235-Licenses), a platform offering personalized AI assistants for interactive learning and creative collaboration
+- [**PyTorch**](https://github.com/pytorch/pytorch), a machine learning framework for building and training neural networks, widely used in research and production
+- [**Qualcomm AI Engine Direct**](https://github.com/qualcomm/qai-appbuilder), a toolchain for building and running generative AI applications on Snapdragon devices
+- [**sherpa-onnx**](https://github.com/k2-fsa/sherpa-onnx/blob/master/sherpa-onnx/csrc/sentence-piece-tokenizer.cc), a speech toolkit for on-device recognition, synthesis and speaker diarization
 - [**stable-diffusion.cpp**](https://github.com/leejet/stable-diffusion.cpp), a C++ implementation of the Stable Diffusion image generation model
 - [**TanvasTouch**](https://tanvas.co/tanvastouch-sdk-third-party-acknowledgments), a software development kit (SDK) that enables developers to create tactile experiences on touchscreens, allowing users to feel textures and physical sensations in a digital environment
 - [**TensorFlow**](https://github.com/tensorflow/tensorflow), a machine learning framework that facilitates the development and training of models, supporting data serialization and efficient data exchange between components
+- [**whisper.cpp**](https://github.com/ggml-org/whisper.cpp), a C++ implementation of OpenAI's Whisper automatic speech recognition model
 
 ## Scientific Research and Analysis
 
 - [**BLACK**](https://www.black-sat.org/en/stable/installation/linux.html), a bounded linear temporal logic (LTL) satisfiability checker
+- [**CERN ALICE O2**](https://github.com/AliceO2Group/AliceO2), the online-offline computing framework of the ALICE heavy-ion experiment at the Large Hadron Collider
 - [**CERN Atlas Athena**](https://gitlab.cern.ch/atlas/athena/-/blob/main/Control/PerformanceMonitoring/PerfMonComps/src/PerfMonMTSvc.h), a software framework used in the ATLAS experiment at the Large Hadron Collider (LHC) for performance monitoring
+- [**CERN CMSSW**](https://github.com/cms-sw/cmssw), the offline software framework of the CMS experiment at the Large Hadron Collider
+- [**CERN Gaudi**](https://gitlab.cern.ch/gaudi/Gaudi), the event-processing framework used by the LHCb and ATLAS experiments at the Large Hadron Collider
 - [**ICU**](https://github.com/unicode-org/icu), the International Components for Unicode, a mature library for software globalization and multilingual support
 - [**KAMERA**](https://github.com/Kitware/kamera), a platform for synchronized data collection and real-time deep learning to map marine species like polar bears and seals, aiding Arctic ecosystem research
 - [**KiCad**](https://gitlab.com/kicad/code/kicad/-/tree/master/thirdparty/nlohmann_json), a free and open-source software suite for electronic design automation
+- [**LLNL ROSE**](https://github.com/llnl/rose), a compiler infrastructure from Lawrence Livermore National Laboratory for building source-to-source program analysis and transformation tools
 - [**Maple**](https://www.maplesoft.com/support/help/Maple/view.aspx?path=copyright), a symbolic and numeric computing environment for advanced mathematical modeling and analysis
 - [**MeVisLab**](https://mevislabdownloads.mevis.de/docs/current/MeVis/ThirdParty/Documentation/Publish/ThirdPartyReference/index.html), a software framework for medical image processing and visualization.
+- [**MITK**](https://github.com/MITK/MITK), the Medical Imaging Interaction Toolkit, a framework for developing interactive medical image processing software
 - [**OpenPMD API**](https://openpmd-api.readthedocs.io/en/0.8.0-alpha/backends/json.html), a versatile programming interface for accessing and managing scientific data, designed to facilitate the efficient storage, retrieval, and sharing of simulation data across various applications and platforms
+- [**ORNL DataFed**](https://github.com/ORNL/DataFed), a federated scientific data management system developed at Oak Ridge National Laboratory
 - [**ParaView**](https://github.com/Kitware/ParaView), an open-source tool for large-scale data visualization and analysis across various scientific domains
 - [**QGIS**](https://gitlab.b-data.ch/qgis/qgis/-/blob/backport-57658-to-release-3_34/external/nlohmann/json.hpp), a free and open-source geographic information system (GIS) application that allows users to create, edit, visualize, and analyze geospatial data across a variety of formats
-- [**VTK**](https://github.com/Kitware/VTK), a software library for 3D computer graphics, image processing, and visualization
+- [**Sandia InterSpec**](https://github.com/sandialabs/InterSpec), spectral radiation analysis software from Sandia National Laboratories for identifying radioactive isotopes
 - [**VolView**](https://github.com/Kitware/VolView), a lightweight application for interactive visualization and analysis of 3D medical imaging data.
+- [**VTK**](https://github.com/Kitware/VTK), a software library for 3D computer graphics, image processing, and visualization
 
 ## Business and Productivity Software
 
 - [**ArcGIS PRO**](https://www.esri.com/content/dam/esrisites/en-us/media/legal/open-source-acknowledgements/arcgis-pro-2-8-attribution-report.html), a desktop geographic information system (GIS) application developed by Esri for mapping and spatial analysis
 - [**Autodesk Desktop**](https://damassets.autodesk.net/content/dam/autodesk/www/Company/legal-notices-trademarks/autodesk-desktop-platform-components/internal-autodesk-components-web-page-2023.pdf), a software platform developed by Autodesk for creating and managing desktop applications and services
 - [**Check Point**](https://www.checkpoint.com/about-us/copyright-and-trademarks/), a cybersecurity company specializing in threat prevention and network security solutions, offering a range of products designed to protect enterprises from cyber threats and ensure data integrity
+- [**EasyEffects**](https://github.com/wwmm/easyeffects/blob/master/src/presets_manager.hpp), an audio effects processor for PipeWire offering limiting, compression and equalization
+- [**espanso**](https://github.com/espanso/espanso/blob/dev/espanso-ui/src/win32/native.cpp), a cross-platform text expander
+- [**Karabiner-Elements**](https://github.com/pqrs-org/Karabiner-Elements/blob/main/src/share/app_icon.hpp), a keyboard customizer for macOS
+- [**MacType**](https://github.com/snowie2000/mactype/blob/directwrite/settings.h), a font rendering engine for Windows
+- [**magicplan**](https://help.magicplan.app/acknowledgments), a mobile application for creating floor plans and interior designs using augmented reality
 - [**Microsoft Office for Mac**](https://officecdnmac.microsoft.com/pr/legal/mac/OfficeforMacAttributions.html), a suite of productivity applications developed by Microsoft for macOS, including tools for word processing, spreadsheets, and presentations
 - [**Microsoft Teams**](https://www.microsoft.com/microsoft-teams/), a team collaboration application offering workspace chat and video conferencing, file storage, and integration of proprietary and third-party applications and services
+- [**MuseScore**](https://github.com/musescore/MuseScore), a free and open-source music notation and composition application
+- [**NanaZip**](https://github.com/M2Team/NanaZip/blob/main/NanaZip.Codecs/NanaZip.Codecs.Archive.ElectronAsar.cpp), a 7-Zip derivative built for modern Windows
 - [**Nexthink Infinity**](https://docs.nexthink.com/legal/services-terms/experience-open-source-software-licenses/infinity-2022.8-software-licenses), a digital employee experience management platform for monitoring and improving IT performance
 - [**Sophos Connect Client**](https://docs.sophos.com/nsg/licenses/SophosConnect/SophosConnectAttribution.html), a secure VPN client from Sophos that allows remote users to connect to their corporate network, ensuring secure access to resources and data
 - [**Stonebranch**](https://stonebranchdocs.atlassian.net/wiki/spaces/UA77/pages/799545647/Licenses+for+Third-Party+Libraries), a cloud-based cybersecurity solution that integrates backup, disaster recovery, and cybersecurity features to protect data and ensure business continuity for organizations
 - [**Tablecruncher**](https://tablecruncher.com/), a data analysis tool that allows users to import, analyze, and visualize spreadsheet data, offering interactive features for better insights and decision-making
-- [**magicplan**](https://help.magicplan.app/acknowledgments), a mobile application for creating floor plans and interior designs using augmented reality
+- [**VNote**](https://github.com/vnotex/vnote/blob/master/src/core/services/notebookcoreservice.cpp), a Markdown-based note-taking application written in C++
 
 ## Databases and Big Data
 
 - [**ADIOS2**](https://code.ornl.gov/ecpcitest/adios2/-/tree/pr4285_FFSUpstream/thirdparty/nlohmann_json?ref_type=heads), a data management framework designed for high-performance input and output operations
+- [**Apache Doris**](https://github.com/apache/doris/blob/master/be/src/runtime/be_proc_monitor.cpp), a real-time analytical database for high-concurrency queries
+- [**Claris FileMaker Server**](https://www.claris.com/company/legal/docs/acknowledgements/filemaker-server-macwin/claris_fms2025_acknowledgements_en.pdf), the server platform hosting FileMaker custom apps and databases, developed by Apple subsidiary Claris
+- [**ClickHouse**](https://github.com/ClickHouse/ClickHouse), a column-oriented database management system for real-time analytical queries
 - [**Cribl Stream**](https://docs.cribl.io/stream/third-party-current-list/), a real-time data processing platform that enables organizations to collect, route, and transform observability data, enhancing visibility and insights into their systems
 - [**DB Browser for SQLite**](https://github.com/sqlitebrowser/sqlitebrowser), a visual open-source tool for creating, designing, and editing SQLite database files
+- [**Manticore Search**](https://github.com/manticoresoftware/manticoresearch/blob/main/src/searchdhttpcompat.cpp), a database for search, offering full-text and vector queries
+- [**Milvus**](https://github.com/milvus-io/milvus/blob/master/internal/core/src/query/PlanImpl.h), a cloud-native vector database built for embedding similarity search
+- [**MongoDB**](https://github.com/mongodb/mongo/blob/master/src/mongo/replay/config_handler.cpp), a general-purpose document database
 - [**MySQL Connector/C++**](https://docs.oracle.com/cd/E17952_01/connector-cpp-9.1-license-com-en/license-opentelemetry-cpp-com.html), a C++ library for connecting and interacting with MySQL databases
 - [**MySQL NDB Cluster**](https://downloads.mysql.com/docs/licenses/cluster-9.0-com-en.pdf), a distributed database system that provides high availability and scalability for MySQL databases
 - [**MySQL Shell**](https://downloads.mysql.com/docs/licenses/mysql-shell-8.0-gpl-en.pdf), an advanced client and code editor for interacting with MySQL servers, supporting SQL, Python, and JavaScript
-- [**PrestoDB**](https://github.com/prestodb/presto), a distributed SQL query engine designed for large-scale data analytics, originally developed by Facebook
+- [**PrestoDB**](https://github.com/prestodb/presto/blob/master/presto-native-execution/presto_cpp/main/Announcer.cpp), a distributed SQL query engine designed for large-scale data analytics, originally developed by Facebook
 - [**ROOT Data Analysis Framework**](https://root.cern/doc/v614/classnlohmann_1_1basic__json.html), an open-source data analysis framework widely used in high-energy physics and other fields for data processing and visualization
+- [**Typesense**](https://github.com/typesense/typesense/blob/v31/include/join.h), an open source typo-tolerant search engine
+- [**Vearch**](https://github.com/jd-opensource/vearch), a distributed vector database developed at JD.com for similarity search and retrieval-augmented generation
 - [**WiredTiger**](https://github.com/wiredtiger/wiredtiger), a high-performance storage engine for databases, offering support for compression, concurrency, and checkpointing
 
 ## Simulation and Modeling
 
+- [**Adobe Lagrange**](https://github.com/adobe/lagrange), a geometry processing library developed by Adobe for mesh manipulation and analysis
 - [**Arcturus HoloSuite**](https://www.datocms-assets.com/104353/1698904597-holosuite-third-party-software-credits-and-attributions-2.pdf), a software toolset for capturing, editing, and streaming volumetric video, featuring advanced compression technologies for high-quality 3D content creation
 - [**azul**](https://pure.tudelft.nl/ws/files/85338589/tgis.12673.pdf), a fast and efficient 3D city model viewer designed for visualizing urban environments and spatial data
+- [**Bambu Studio**](https://github.com/bambulab/BambuStudio), a slicing and print management application for Bambu Lab 3D printers
 - [**Blender**](https://projects.blender.org/blender/blender/search?q=nlohmann), a free and open-source 3D creation suite for modeling, animation, rendering, and more
 - [**cpplot**](https://cpplot.readthedocs.io/en/latest/library_api/function_eigen_8h_1ac080eac0541014c5892a55e41bf785e6.html), a library for creating interactive graphs and charts in C++, which can be viewed in web browsers
 - [**Foundry Nuke**](https://learn.foundry.com/nuke/content/misc/studio_third_party_libraries.html), a powerful node-based digital compositing and visual effects application used in film and television post-production
+- [**FreeCAD**](https://github.com/FreeCAD/FreeCAD), a free and open-source parametric 3D CAD modeler for product design and engineering
 - [**GAMS**](https://www.gams.com/47/docs/THIRDPARTY.html), a high-performance mathematical modeling system for optimization and decision support
+- [**Keysight WirelessPro**](https://docs.keysight.com/display/engdocwirelesspro/WirelessPro+2026+Release+Notes), a simulation platform for 5G, 5G-Advanced, and 6G cellular network research
 - [**Kitware SMTK**](https://github.com/Kitware/SMTK), a software toolkit for managing simulation models and workflows in scientific and engineering applications
 - [**M-Star**](https://docs.mstarcfd.com/3_Licensing/thirdparty-licenses.html), a computational fluid dynamics software for simulating and analyzing fluid flow
 - [**MapleSim CAD Toolbox**](https://www.maplesoft.com/support/help/MapleSim/view.aspx?path=CADToolbox/copyright), a software extension for MapleSim that integrates CAD models, allowing users to import, manipulate, and analyze 3D CAD data within the MapleSim environment for enhanced modeling and simulation
+- [**Microsoft AirSim**](https://github.com/microsoft/AirSim/blob/main/AirLib/include/common/Settings.hpp), a simulator for autonomous vehicles and drones built on Unreal Engine
 - [**NVIDIA Omniverse**](https://docs.omniverse.nvidia.com/composer/latest/common/product-licenses/usd-explorer/usd-explorer-2023.2.0-licenses-manifest.html), a platform for 3D content creation and collaboration that enables real-time simulations and interactive experiences across various industries
+- [**OpenSCAD**](https://github.com/openscad/openscad/blob/master/src/core/AIClient.cc), a script-driven solid 3D CAD modeller
+- [**OrcaSlicer**](https://github.com/SoftFever/OrcaSlicer), an open-source slicer supporting a wide range of consumer 3D printers
 - [**Pixar Renderman**](https://rmanwiki-26.pixar.com/space/REN26/19662083/Legal+Notice), a photorealistic 3D rendering software developed by Pixar, widely used in the film industry for creating high-quality visual effects and animations
+- [**PrusaSlicer**](https://github.com/prusa3d/PrusaSlicer), the slicing software developed by Prusa Research for its 3D printers
 - [**ROS - Robot Operating System**](http://docs.ros.org/en/noetic/api/behaviortree_cpp/html/json_8hpp_source.html), a set of software libraries and tools that assist in developing robot applications
 - [**UBS**](https://www.ubs.com/), a multinational financial services and banking company
 
@@ -161,18 +278,31 @@ the result of an internet search. If you know further customers of the library,
 - [**Acronis Cyber Protect Cloud**](https://care.acronis.com/s/article/59533-Third-party-software-used-in-Acronis-Cyber-Protect-Cloud?language=en_US), an all-in-one data protection solution that combines backup, disaster recovery, and cybersecurity to safeguard business data from threats like ransomware
 - [**Baereos**](https://gitlab.tiger-computing.co.uk/packages/bareos/-/blob/tiger/bullseye/third-party/CLI11/examples/json.cpp), a backup solution that provides data protection and recovery options for various environments, including physical and virtual systems
 - [**Bitdefender Home Scanner**](https://www.bitdefender.de/site/Main/view/home-scanner-open-source.html), a tool from Bitdefender that scans devices for malware and security threats, providing a safeguard against potential online dangers
+- [**Cisco MLS++**](https://github.com/cisco/mlspp), an implementation of the Messaging Layer Security protocol for end-to-end encrypted group messaging
 - [**Citrix Provisioning**](https://docs.citrix.com/en-us/provisioning/2203-ltsr/downloads/pvs-third-party-notices-2203.pdf), a solution that streamlines the delivery of virtual desktops and applications by allowing administrators to manage and provision resources efficiently across multiple environments
 - [**Citrix Virtual Apps and Desktops**](https://docs.citrix.com/en-us/citrix-virtual-apps-desktops/2305/downloads/third-party-notices-apps-and-desktops.pdf), a solution from Citrix that delivers virtual apps and desktops
 - [**Cyberarc**](https://docs.cyberark.com/Downloads/Legal/Privileged%20Session%20Manager%20for%20SSH%20Third-Party%20Notices.pdf), a security solution that specializes in privileged access management, enabling organizations to control and monitor access to critical systems and data, thereby enhancing overall cybersecurity posture
+- [**Deutsche Telekom sysrepo-plugins**](https://github.com/telekom/sysrepo-plugins), a collection of YANG datastore plugins used to manage network devices
 - [**Egnyte Desktop**](https://helpdesk.egnyte.com/hc/en-us/articles/360007071732-Third-Party-Software-Acknowledgements), a secure cloud storage solution designed for businesses, enabling file sharing, collaboration, and data management across teams while ensuring compliance and data protection
 - [**Elster**](https://www.secunet.com/en/about-us/press/article/elstersecure-bietet-komfortablen-login-ohne-passwort-dank-secunet-protect4use), a digital platform developed by German tax authorities for secure and efficient electronic tax filing and management using secunet protect4use
+- [**Envoy**](https://github.com/envoyproxy/envoy), a cloud-native edge and service proxy that forms the data plane of many service meshes
 - [**Ethereum Solidity**](https://github.com/ethereum/solidity), a high-level, object-oriented programming language designed for implementing smart contracts on the Ethereum platform
+- [**gVisor**](https://github.com/google/gvisor), an application kernel that provides a secure sandbox for running untrusted containers
+- [**IBM Storage Virtualize**](https://public.dhe.ibm.com/systems/support/warranty/pdfs/stgoilc/SV_for_FS_7300_v8_7_0_Base_OILC.pdf), the software powering IBM FlashSystem enterprise storage arrays
 - [**Inciga**](https://fossies.org/linux/icinga2/third-party/nlohmann_json/json.hpp), a monitoring tool for IT infrastructure, designed to provide insights into system performance and availability through customizable dashboards and alerts
 - [**Intel Accelerator Management Daemon for VMware ESXi**](https://downloadmirror.intel.com/772507/THIRD-PARTY.txt), a management tool designed for monitoring and controlling Intel hardware accelerators within VMware ESXi environments, optimizing performance and resource allocation
 - [**Juniper Identity Management Service**](https://www.juniper.net/documentation/us/en/software/jims/jims-guide/jims-guide.pdf)
+- [**Meta FBOSS**](https://github.com/facebook/fboss), the software stack that controls the network switches in Meta's data centers
 - [**Microsoft Azure IoT SDK**](https://library.e.abb.com/public/2779c5f85f30484192eb3cb3f666a201/IP%20Gateway%20Open%20License%20Declaration_9AKK108467A4095_Rev_C.pdf), a collection of tools and libraries to help developers connect, build, and deploy Internet of Things (IoT) solutions on the Azure cloud platform
+- [**Microsoft Confidential Consortium Framework**](https://github.com/microsoft/CCF), a framework for building secure, highly available applications on trusted execution environments
 - [**Microsoft WinGet**](https://github.com/microsoft/winget-cli), a command-line utility included in the Windows Package Manager
+- [**Mitsubishi Electric SECS/GEM**](https://dl.mitsubishielectric.com/dl/fa/document/manual/plc/sh082483eng/sh082483engi.pdf), the semiconductor equipment communication software running on Mitsubishi Electric C Controller and C intelligent function modules
+- [**Moxa**](https://www.moxa.com/getmedia/fbe2a0c7-8dda-4b5b-a501-15e45adebb1f/moxa-foss-statement-for-da-720-series-win-10-ltsc-21h2-declaration-v1.0.pdf), a provider of industrial networking, computing, and automation infrastructure
 - [**plexusAV**](https://www.sisme.com/media/10994/manual_plexusav-p-avn-4-form8244-c.pdf), a high-performance AV-over-IP transceiver device capable of video encoding and decoding using the IPMX standard
 - [**Pointr**](https://docs-dev.pointr.tech/docs/8.x/Developer%20Portal/Open%20Source%20Licenses/), a platform for indoor positioning and navigation solutions, offering tools and SDKs for developers to create location-based applications
 - [**secunet protect4use**](https://www.secunet.com/en/about-us/press/article/elstersecure-bietet-komfortablen-login-ohne-passwort-dank-secunet-protect4use), a secure, passwordless multifactor authentication solution that transforms smartphones into digital keyrings, ensuring high security for online services and digital identities
 - [**Sencore MRD 7000**](https://www.foccusdigital.com/wp-content/uploads/2025/03/MRD-7000-Manual-8175V.pdf), a professional multi-channel receiver and decoder supporting UHD and HD stream decoding
+- [**Siemens SINEC**](https://cache.industry.siemens.com/dl/files/917/109974917/att_1298783/v2/OSS_SINEC-NMS_99.pdf), a family of network management and infrastructure services for industrial networks
+- [**Toshiba Industrial Servers**](https://www.global.toshiba/content/dam/toshiba/jp/products-solutions/industrial/computer/product/server/fs20000r/pdf/FS20000R_OSS_License_6E8C5817_rev0.pdf), the FS20000R series of industrial servers for factory automation and control systems
+- [**Wazuh**](https://github.com/wazuh/wazuh/blob/main/src/data_provider/src/sysInfo.cpp), a security platform for threat detection, integrity monitoring and incident response
+- [**ZeroTier**](https://github.com/zerotier/ZeroTierOne/blob/dev/osdep/OSUtils.hpp), a software-defined networking service that creates virtual Ethernet networks

docs/mkdocs/docs/home/exceptions.md

@@ -291,9 +291,10 @@ A JSON Pointer array index must be a number.
 
 ### json.exception.parse_error.110
 
-When parsing CBOR or MessagePack, the byte vector ends before the complete value has been read.
+When parsing a [binary format](../features/binary_formats/index.md), the byte vector ends before the complete value has
+been read.
 
-!!! failure "Example message"
+!!! failure "Example messages"
 
     ```
     [json.exception.parse_error.110] parse error at byte 5: syntax error while parsing CBOR string: unexpected end of input
@@ -301,6 +302,9 @@ When parsing CBOR or MessagePack, the byte vector ends before the complete value
     ```
     [json.exception.parse_error.110] parse error at byte 2: syntax error while parsing UBJSON value: expected end of input; last byte: 0x5A
     ```
+    ```
+    [json.exception.parse_error.110] parse error at byte 8: syntax error while parsing BSON number: unexpected end of input
+    ```
 
 ### json.exception.parse_error.112
 
@@ -329,10 +333,14 @@ An unexpected byte was read in a [binary format](../features/binary_formats/inde
     ```
     [json.exception.parse_error.112] parse error at byte 9: syntax error while parsing CBOR value: negative integer overflow
     ```
+    ```
+    [json.exception.parse_error.112] parse error at byte 5: syntax error while parsing BSON document: document size 6 does not match the number of bytes read (5)
+    ```
 
 ### json.exception.parse_error.113
 
-While parsing a map key, a value that is not a string has been read.
+A string could not be read from a [binary format](../features/binary_formats/index.md): either a value that is not a
+string was read where one was required (for instance as a map key), or the string's length specification is invalid.
 
 !!! failure "Example messages"
 
@@ -345,6 +353,9 @@ While parsing a map key, a value that is not a string has been read.
     ```
     [json.exception.parse_error.113] parse error at byte 2: syntax error while parsing UBJSON char: byte after 'C' must be in range 0x00..0x7F; last byte: 0x82
     ```
+    ```
+    [json.exception.parse_error.113] parse error at byte 3: syntax error while parsing BJData string: string length must not be negative
+    ```
 
 ### json.exception.parse_error.114
 
@@ -853,13 +864,30 @@ and this exception no longer occurs.
 
 ### json.exception.out_of_range.408
 
-The size (following `#`) of an UBJSON array or object exceeds the maximal capacity.
+The size of an array or object in a [binary format](../features/binary_formats/index.md) exceeds the maximal capacity:
+the size following `#` for [UBJSON](../features/binary_formats/ubjson.md)/[BJData](../features/binary_formats/bjdata.md),
+or the encoded length for [CBOR](../features/binary_formats/cbor.md).
 
-!!! failure "Example message"
+The exception is also thrown for a [UBJSON](../features/binary_formats/ubjson.md) array of a type that is encoded by its
+marker alone (`Z`, `T` or `F`) whose declared count exceeds 1,048,576. Such an array has no payload, so its count alone
+decides how much memory is allocated, and a handful of bytes would otherwise describe billions of values.
+[`to_ubjson`](../api/basic_json/to_ubjson.md) writes longer arrays of these types without the size and type annotation,
+so any value it produces can still be read back.
+
+!!! failure "Example messages"
 
     ```
     excessive array size: 8658170730974374167
     ```
+    ```
+    [json.exception.out_of_range.408] syntax error while parsing CBOR size: excessive array size
+    ```
+    ```
+    [json.exception.out_of_range.408] syntax error while parsing CBOR size: excessive map size
+    ```
+    ```
+    [json.exception.out_of_range.408] syntax error while parsing UBJSON size: excessive array size
+    ```
 
 ### json.exception.out_of_range.409
 
@@ -946,3 +974,19 @@ A JSON Patch operation 'test' failed. The unsuccessful operation is also printed
     ```
     [json.exception.other_error.501] unsuccessful: {"op":"test","path":"/baz","value":"bar"}
     ```
+
+### json.exception.other_error.502
+
+[`to_ubjson`](../api/basic_json/to_ubjson.md) and [`to_bjdata`](../api/basic_json/to_bjdata.md) were called with
+`use_type = true` but `use_size = false`. UBJSON requires a size marker (`#`) after a type marker (`$`).
+
+!!! failure "Example message"
+
+    ```
+    [json.exception.other_error.502] use_type requires use_size = true
+    ```
+
+!!! note
+
+    This exception was added in version 3.13.0. Before that, debug builds aborted on an assertion and release builds
+    wrote a `$` marker without `#`, which [`from_ubjson`](../api/basic_json/from_ubjson.md) then rejected.

docs/mkdocs/mkdocs.yml

@@ -308,6 +308,7 @@ nav:
           - 'NLOHMANN_JSON_VERSION_MAJOR, NLOHMANN_JSON_VERSION_MINOR, NLOHMANN_JSON_VERSION_PATCH': api/macros/nlohmann_json_version_major.md
   - Community:
       - community/index.md
+      - community/ecosystem.md
       - "Code of Conduct": community/code_of_conduct.md
       - community/contribution_guidelines.md
       - community/quality_assurance.md

docs/mkdocs/requirements.txt

@@ -1,7 +1,7 @@
-wheel==0.47.0
+wheel==0.48.0
 
 mkdocs==1.6.1                                       # documentation framework
-mkdocs-git-revision-date-localized-plugin==1.5.3    # plugin "git-revision-date-localized"
+mkdocs-git-revision-date-localized-plugin==1.5.4    # plugin "git-revision-date-localized"
 mkdocs-material==9.7.7                             # theme for mkdocs
 mkdocs-material-extensions==1.3.1                   # extensions
 mkdocs-minify-plugin==0.8.0                         # plugin "minify"

include/nlohmann/detail/input/binary_reader.hpp

@@ -58,6 +58,26 @@ inline bool little_endianness(int num = 1) noexcept
     return *reinterpret_cast<char*>(&num) == 1;
 }
 
+/*!
+@brief largest element count accepted for a UBJSON container of a valueless type
+
+An element of type 'Z' (null), 'T' (true) or 'F' (false) is encoded by its
+type marker alone, so an optimized container of one of those types has no
+payload at all and its declared count is the only thing that decides how much
+is allocated: `[$Z#L` followed by a large count turns some ten bytes of input
+into that many values (see #2793, which reports 35 GB and 150 seconds). Every
+other type costs at least one byte per element and is bounded by the end of
+the input.
+
+This is a sanity bound rather than a security boundary, and it is far above
+any container met in practice. @ref binary_writer falls back to the
+unoptimized encoding for longer containers, so that a value serialized by
+this library can always be read back.
+
+@sa https://github.com/nlohmann/json/issues/2793
+*/
+JSON_INLINE_VARIABLE constexpr std::size_t max_valueless_container_size = 1 << 20;
+
 ///////////////////
 // binary reader //
 ///////////////////
@@ -110,6 +130,7 @@ class binary_reader
                    const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error)
     {
         sax = sax_;
+        container_stack.clear();
         bool result = false;
 
         switch (format)
@@ -159,6 +180,69 @@ class binary_reader
     }
 
   private:
+    ////////////////////////
+    // nested containers  //
+    ////////////////////////
+
+    /*!
+    @brief a container that has been opened and not closed yet
+
+    The binary readers do not call themselves once per nesting level. Like
+    @ref parser::sax_parse_internal, which does the same for JSON text, they
+    keep the containers they are inside of on a heap-allocated stack, so that
+    the native call stack does not grow with the nesting depth of the input
+    and a deeply nested value is bounded by memory rather than by the stack
+    (see #5104).
+
+    The members are ordered by decreasing alignment, which is the ordering that
+    keeps a struct from growing as members are added to it.
+    */
+    struct container_frame
+    {
+        container_frame(const std::size_t remaining_, const bool is_object_) noexcept
+            : remaining(remaining_), is_object(is_object_) {}
+
+        /// number of elements that have not been read yet
+        std::size_t remaining;
+        /// whether to close this container with end_object() or end_array()
+        bool is_object;
+    };
+
+    /*!
+    @brief open a nested array or object
+
+    Emits the SAX start event and records the container. This is the only
+    place the binary readers start a container, so a check that rejects one
+    can be made here and is then guaranteed to run before the start event.
+
+    @param[in] is_object  whether an object (true) or an array (false) begins
+    @param[in] len        number of elements the container declares
+
+    @return whether the SAX parser accepted the start event
+    */
+    bool enter_container(const bool is_object, const std::size_t len)
+    {
+        if (JSON_HEDLEY_UNLIKELY(is_object ? !sax->start_object(len) : !sax->start_array(len)))
+        {
+            return false;
+        }
+
+        container_stack.emplace_back(len, is_object);
+        return true;
+    }
+
+    /// @copydoc enter_container
+    bool enter_array(const std::size_t len)
+    {
+        return enter_container(/*is_object*/false, len);
+    }
+
+    /// @copydoc enter_container
+    bool enter_object(const std::size_t len)
+    {
+        return enter_container(/*is_object*/true, len);
+    }
+
     //////////
     // BSON //
     //////////
@@ -465,15 +549,6 @@ class binary_reader
     // CBOR //
     //////////
 
-    /*!
-    @param[in] get_char  whether a new character should be retrieved from the
-                         input (true) or whether the last read character should
-                         be considered instead (false)
-    @param[in] tag_handler how CBOR tags should be treated
-
-    @return whether a valid CBOR value was passed to the SAX parser
-    */
-
     template<typename NumberType>
     bool get_cbor_negative_integer()
     {
@@ -492,6 +567,14 @@ class binary_reader
         return sax->number_integer(static_cast<number_integer_t>(-1) - static_cast<number_integer_t>(number));
     }
 
+    /*!
+    @param[in] get_char  whether a new character should be retrieved from the
+                         input (true) or whether the last read character should
+                         be considered instead (false)
+    @param[in] tag_handler how CBOR tags should be treated
+
+    @return whether a valid CBOR value was passed to the SAX parser
+    */
     bool parse_cbor_internal(const bool get_char,
                              const cbor_tag_handler_t tag_handler)
     {
@@ -704,13 +787,15 @@ class binary_reader
             case 0x9A: // array (four-byte uint32_t for n follow)
             {
                 std::uint32_t len{};
-                return get_number(input_format_t::cbor, len) && get_cbor_array(conditional_static_cast<std::size_t>(len), tag_handler);
+                std::size_t size{};
+                return get_number(input_format_t::cbor, len) && get_cbor_container_size(len, size, "array") && get_cbor_array(size, tag_handler);
             }
 
             case 0x9B: // array (eight-byte uint64_t for n follow)
             {
                 std::uint64_t len{};
-                return get_number(input_format_t::cbor, len) && get_cbor_array(conditional_static_cast<std::size_t>(len), tag_handler);
+                std::size_t size{};
+                return get_number(input_format_t::cbor, len) && get_cbor_container_size(len, size, "array") && get_cbor_array(size, tag_handler);
             }
 
             case 0x9F: // array (indefinite length)
@@ -758,19 +843,27 @@ class binary_reader
             case 0xBA: // map (four-byte uint32_t for n follow)
             {
                 std::uint32_t len{};
-                return get_number(input_format_t::cbor, len) && get_cbor_object(conditional_static_cast<std::size_t>(len), tag_handler);
+                std::size_t size{};
+                return get_number(input_format_t::cbor, len) && get_cbor_container_size(len, size, "map") && get_cbor_object(size, tag_handler);
             }
 
             case 0xBB: // map (eight-byte uint64_t for n follow)
             {
                 std::uint64_t len{};
-                return get_number(input_format_t::cbor, len) && get_cbor_object(conditional_static_cast<std::size_t>(len), tag_handler);
+                std::size_t size{};
+                return get_number(input_format_t::cbor, len) && get_cbor_container_size(len, size, "map") && get_cbor_object(size, tag_handler);
             }
 
             case 0xBF: // map (indefinite length)
                 return get_cbor_object(detail::unknown_size(), tag_handler);
 
-            case 0xC6: // tagged item
+            case 0xC0: // tagged item
+            case 0xC1:
+            case 0xC2:
+            case 0xC3:
+            case 0xC4:
+            case 0xC5:
+            case 0xC6:
             case 0xC7:
             case 0xC8:
             case 0xC9:
@@ -785,6 +878,9 @@ class binary_reader
             case 0xD2:
             case 0xD3:
             case 0xD4:
+            case 0xD5:
+            case 0xD6:
+            case 0xD7:
             case 0xD8: // tagged item (1 byte follows)
             case 0xD9: // tagged item (2 bytes follow)
             case 0xDA: // tagged item (4 bytes follow)
@@ -807,25 +903,37 @@ class binary_reader
                             case 0xD8:
                             {
                                 std::uint8_t subtype_to_ignore{};
-                                get_number(input_format_t::cbor, subtype_to_ignore);
+                                if (!get_number(input_format_t::cbor, subtype_to_ignore))
+                                {
+                                    return false;
+                                }
                                 break;
                             }
                             case 0xD9:
                             {
                                 std::uint16_t subtype_to_ignore{};
-                                get_number(input_format_t::cbor, subtype_to_ignore);
+                                if (!get_number(input_format_t::cbor, subtype_to_ignore))
+                                {
+                                    return false;
+                                }
                                 break;
                             }
                             case 0xDA:
                             {
                                 std::uint32_t subtype_to_ignore{};
-                                get_number(input_format_t::cbor, subtype_to_ignore);
+                                if (!get_number(input_format_t::cbor, subtype_to_ignore))
+                                {
+                                    return false;
+                                }
                                 break;
                             }
                             case 0xDB:
                             {
                                 std::uint64_t subtype_to_ignore{};
-                                get_number(input_format_t::cbor, subtype_to_ignore);
+                                if (!get_number(input_format_t::cbor, subtype_to_ignore))
+                                {
+                                    return false;
+                                }
                                 break;
                             }
                             default:
@@ -843,28 +951,40 @@ class binary_reader
                             case 0xD8:
                             {
                                 std::uint8_t subtype{};
-                                get_number(input_format_t::cbor, subtype);
+                                if (!get_number(input_format_t::cbor, subtype))
+                                {
+                                    return false;
+                                }
                                 b.set_subtype(detail::conditional_static_cast<typename binary_t::subtype_type>(subtype));
                                 break;
                             }
                             case 0xD9:
                             {
                                 std::uint16_t subtype{};
-                                get_number(input_format_t::cbor, subtype);
+                                if (!get_number(input_format_t::cbor, subtype))
+                                {
+                                    return false;
+                                }
                                 b.set_subtype(detail::conditional_static_cast<typename binary_t::subtype_type>(subtype));
                                 break;
                             }
                             case 0xDA:
                             {
                                 std::uint32_t subtype{};
-                                get_number(input_format_t::cbor, subtype);
+                                if (!get_number(input_format_t::cbor, subtype))
+                                {
+                                    return false;
+                                }
                                 b.set_subtype(detail::conditional_static_cast<typename binary_t::subtype_type>(subtype));
                                 break;
                             }
                             case 0xDB:
                             {
                                 std::uint64_t subtype{};
-                                get_number(input_format_t::cbor, subtype);
+                                if (!get_number(input_format_t::cbor, subtype))
+                                {
+                                    return false;
+                                }
                                 b.set_subtype(detail::conditional_static_cast<typename binary_t::subtype_type>(subtype));
                                 break;
                             }
@@ -960,23 +1080,21 @@ class binary_reader
     }
 
     /*!
-    @brief reads a CBOR string
+    @brief reads a definite-length CBOR string
 
-    This function first reads starting bytes to determine the expected
+    Reads everything @ref get_cbor_string accepts except the indefinite-length
-    string length and then copies this number of bytes into a string.
+    form, which that function handles itself. The bytes are appended to @a
-    Additionally, CBOR's strings with indefinite lengths are supported.
+    result, so consecutive chunks of an indefinite-length string can be read
+    into the same string.
 
-    @param[out] result  created string
+    @param[out] result  string the bytes are appended to
 
     @return whether string creation completed
-    */
-    bool get_cbor_string(string_t& result)
-    {
-        if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "string")))
-        {
-            return false;
-        }
 
+    @pre @a current is not EOF
+    */
+    bool get_cbor_string_chunk(string_t& result)
+    {
         switch (current)
         {
             // UTF-8 string (0x00..0x17 bytes follow)
@@ -1032,20 +1150,6 @@ class binary_reader
                 return get_number(input_format_t::cbor, len) && get_string(input_format_t::cbor, len, result);
             }
 
-            case 0x7F: // UTF-8 string (indefinite length)
-            {
-                while (get() != 0xFF)
-                {
-                    string_t chunk;
-                    if (!get_cbor_string(chunk))
-                    {
-                        return false;
-                    }
-                    result.append(chunk);
-                }
-                return true;
-            }
-
             default:
             {
                 auto last_token = get_token_string();
@@ -1056,23 +1160,82 @@ class binary_reader
     }
 
     /*!
-    @brief reads a CBOR byte array
+    @brief reads a CBOR string
 
     This function first reads starting bytes to determine the expected
-    byte array length and then copies this number of bytes into the byte array.
+    string length and then copies this number of bytes into a string.
-    Additionally, CBOR's byte arrays with indefinite lengths are supported.
+    Additionally, CBOR's strings with indefinite lengths are supported.
 
-    @param[out] result  created byte array
+    @param[out] result  created string
+
+    @return whether string creation completed
+    */
+    bool get_cbor_string(string_t& result)
+    {
+        // number of indefinite-length strings that have been opened and not
+        // closed yet. RFC 8949, Section 3.2.3 does not permit nesting them,
+        // but this reader has always accepted it, so the open levels are
+        // counted instead of recursed through, which overflowed the stack for
+        // an input of repeated 0x7F bytes (see #5104). Every chunk is appended
+        // to the same result, so no per-level state is needed.
+        std::size_t open = 0;
+
+        while (true)
+        {
+            if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "string")))
+            {
+                return false;
+            }
+
+            if (current == 0x7F) // UTF-8 string (indefinite length)
+            {
+                ++open;
+                get();
+                continue;
+            }
+
+            // a break marker closes the innermost indefinite-length string;
+            // outside of one it is not a string and falls through to the error
+            if (open != 0 && current == 0xFF)
+            {
+                if (--open == 0)
+                {
+                    return true;
+                }
+                get();
+                continue;
+            }
+
+            if (JSON_HEDLEY_UNLIKELY(!get_cbor_string_chunk(result)))
+            {
+                return false;
+            }
+
+            if (open == 0)
+            {
+                return true;
+            }
+
+            get();
+        }
+    }
+
+    /*!
+    @brief reads a definite-length CBOR byte array
+
+    Reads everything @ref get_cbor_binary accepts except the indefinite-length
+    form, which that function handles itself. The bytes are appended to @a
+    result, so consecutive chunks of an indefinite-length byte array can be
+    read into the same byte array.
+
+    @param[out] result  byte array the bytes are appended to
 
     @return whether byte array creation completed
-    */
-    bool get_cbor_binary(binary_t& result)
-    {
-        if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "binary")))
-        {
-            return false;
-        }
 
+    @pre @a current is not EOF
+    */
+    bool get_cbor_binary_chunk(binary_t& result)
+    {
         switch (current)
         {
             // Binary data (0x00..0x17 bytes follow)
@@ -1132,20 +1295,6 @@ class binary_reader
                        get_binary(input_format_t::cbor, len, result);
             }
 
-            case 0x5F: // Binary data (indefinite length)
-            {
-                while (get() != 0xFF)
-                {
-                    binary_t chunk;
-                    if (!get_cbor_binary(chunk))
-                    {
-                        return false;
-                    }
-                    result.insert(result.end(), chunk.begin(), chunk.end());
-                }
-                return true;
-            }
-
             default:
             {
                 auto last_token = get_token_string();
@@ -1155,6 +1304,88 @@ class binary_reader
         }
     }
 
+    /*!
+    @brief reads a CBOR byte array
+
+    This function first reads starting bytes to determine the expected
+    byte array length and then copies this number of bytes into the byte array.
+    Additionally, CBOR's byte arrays with indefinite lengths are supported.
+
+    @param[out] result  created byte array
+
+    @return whether byte array creation completed
+    */
+    bool get_cbor_binary(binary_t& result)
+    {
+        // the open indefinite-length byte arrays are counted rather than
+        // recursed through, for the reason given in @ref get_cbor_string
+        std::size_t open = 0;
+
+        while (true)
+        {
+            if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "binary")))
+            {
+                return false;
+            }
+
+            if (current == 0x5F) // Binary data (indefinite length)
+            {
+                ++open;
+                get();
+                continue;
+            }
+
+            // a break marker closes the innermost indefinite-length byte
+            // array; outside of one it falls through to the error below
+            if (open != 0 && current == 0xFF)
+            {
+                if (--open == 0)
+                {
+                    return true;
+                }
+                get();
+                continue;
+            }
+
+            if (JSON_HEDLEY_UNLIKELY(!get_cbor_binary_chunk(result)))
+            {
+                return false;
+            }
+
+            if (open == 0)
+            {
+                return true;
+            }
+
+            get();
+        }
+    }
+
+    /*!
+    @brief narrow a definite CBOR array/map length to std::size_t
+
+    A definite length is rejected if it does not fit in std::size_t or if it
+    equals detail::unknown_size(), which is reserved to mark an indefinite-
+    length container and would otherwise make the length read as indefinite.
+    Both cases exceed any container's max_size(), so no representable input
+    is affected.
+
+    @param[in]  len      the declared length
+    @param[out] result   the length narrowed to std::size_t
+    @param[in]  context  "array" or "map", for the error message
+    @return whether the length is usable
+    */
+    bool get_cbor_container_size(const std::uint64_t len, std::size_t& result, const char* context)
+    {
+        if (JSON_HEDLEY_UNLIKELY(!value_in_range_of<std::size_t>(len) || len == detail::unknown_size()))
+        {
+            return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408,
+                                    exception_message(input_format_t::cbor, concat("excessive ", context, " size"), "size"), nullptr));
+        }
+        result = conditional_static_cast<std::size_t>(len);
+        return true;
+    }
+
     /*!
     @param[in] len  the length of the array or detail::unknown_size() for an
                     array of indefinite size
@@ -1255,7 +1486,17 @@ class binary_reader
     /*!
     @return whether a valid MessagePack value was passed to the SAX parser
     */
-    bool parse_msgpack_internal()
+    /*!
+    @brief read one MessagePack value
+
+    Reads a single value and passes it to the SAX parser. A value that begins
+    a container is not read to its end: the container is opened with
+    @ref enter_container and its elements are read by
+    @ref parse_msgpack_internal, so that nesting does not consume native stack.
+
+    @return whether reading the value succeeded
+    */
+    bool parse_msgpack_value()
     {
         switch (get())
         {
@@ -1411,7 +1652,7 @@ class binary_reader
             case 0x8D:
             case 0x8E:
             case 0x8F:
-                return get_msgpack_object(conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x0Fu));
+                return enter_object(conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x0Fu));
 
             // fixarray
             case 0x90:
@@ -1430,7 +1671,7 @@ class binary_reader
             case 0x9D:
             case 0x9E:
             case 0x9F:
-                return get_msgpack_array(conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x0Fu));
+                return enter_array(conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x0Fu));
 
             // fixstr
             case 0xA0:
@@ -1561,25 +1802,25 @@ class binary_reader
             case 0xDC: // array 16
             {
                 std::uint16_t len{};
-                return get_number(input_format_t::msgpack, len) && get_msgpack_array(static_cast<std::size_t>(len));
+                return get_number(input_format_t::msgpack, len) && enter_array(static_cast<std::size_t>(len));
             }
 
             case 0xDD: // array 32
             {
                 std::uint32_t len{};
-                return get_number(input_format_t::msgpack, len) && get_msgpack_array(conditional_static_cast<std::size_t>(len));
+                return get_number(input_format_t::msgpack, len) && enter_array(conditional_static_cast<std::size_t>(len));
             }
 
             case 0xDE: // map 16
             {
                 std::uint16_t len{};
-                return get_number(input_format_t::msgpack, len) && get_msgpack_object(static_cast<std::size_t>(len));
+                return get_number(input_format_t::msgpack, len) && enter_object(static_cast<std::size_t>(len));
             }
 
             case 0xDF: // map 32
             {
                 std::uint32_t len{};
-                return get_number(input_format_t::msgpack, len) && get_msgpack_object(conditional_static_cast<std::size_t>(len));
+                return get_number(input_format_t::msgpack, len) && enter_object(conditional_static_cast<std::size_t>(len));
             }
 
             // negative fixint
@@ -1827,55 +2068,69 @@ class binary_reader
     }
 
     /*!
-    @param[in] len  the length of the array
+    @brief read a MessagePack value and everything nested inside it
-    @return whether array creation completed
+
+    Reads values until the one that was begun here is complete, resuming the
+    enclosing container each time an element ends, so that the nesting depth
+    of the input costs heap rather than native stack (see #5104).
+
+    @return whether reading the value succeeded
     */
-    bool get_msgpack_array(const std::size_t len)
+    bool parse_msgpack_internal()
     {
-        if (JSON_HEDLEY_UNLIKELY(!sax->start_array(len)))
+        // the key currently being read; hoisted out of the loop so that its
-        {
+        // capacity is reused across elements and across nesting levels
-            return false;
-        }
-
-        for (std::size_t i = 0; i < len; ++i)
-        {
-            if (JSON_HEDLEY_UNLIKELY(!parse_msgpack_internal()))
-            {
-                return false;
-            }
-        }
-
-        return sax->end_array();
-    }
-
-    /*!
-    @param[in] len  the length of the object
-    @return whether object creation completed
-    */
-    bool get_msgpack_object(const std::size_t len)
-    {
-        if (JSON_HEDLEY_UNLIKELY(!sax->start_object(len)))
-        {
-            return false;
-        }
-
         string_t key;
-        for (std::size_t i = 0; i < len; ++i)
+
+        while (true)
         {
-            get();
+            if (!container_stack.empty())
-            if (JSON_HEDLEY_UNLIKELY(!get_msgpack_string(key) || !sax->key(key)))
+            {
+                // copied out before anything can push onto the stack and
+                // invalidate a reference into it
+                const bool is_object = container_stack.back().is_object;
+
+                if (container_stack.back().remaining == 0)
+                {
+                    container_stack.pop_back();
+                    if (JSON_HEDLEY_UNLIKELY(is_object ? !sax->end_object() : !sax->end_array()))
+                    {
+                        return false;
+                    }
+                    // the value begun here is complete once its container is
+                    if (container_stack.empty())
+                    {
+                        return true;
+                    }
+                    continue;
+                }
+
+                // claim the element about to be read
+                --container_stack.back().remaining;
+
+                if (is_object)
+                {
+                    get();
+                    key.clear();
+                    if (JSON_HEDLEY_UNLIKELY(!get_msgpack_string(key) || !sax->key(key)))
+                    {
+                        return false;
+                    }
+                }
+            }
+
+            if (JSON_HEDLEY_UNLIKELY(!parse_msgpack_value()))
             {
                 return false;
             }
 
-            if (JSON_HEDLEY_UNLIKELY(!parse_msgpack_internal()))
+            // a value that opened a container left it on the stack; one that
+            // did not, and that was not inside a container, was the whole value
+            if (container_stack.empty())
             {
-                return false;
+                return true;
             }
-            key.clear();
         }
-
-        return sax->end_object();
     }
 
     ////////////
@@ -1935,7 +2190,11 @@ class binary_reader
     {
         if (get_char)
         {
-            get();  // TODO(niels): may we ignore N here?
+            // no get_ignore_noop() here: the byte read next must be a string
+            // length type specification, and a no-op ('N') is not valid in
+            // that position. No-ops at positions where a value may appear are
+            // already consumed by the callers via get_ignore_noop().
+            get();
         }
 
         if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format, "value")))
@@ -2326,7 +2585,12 @@ class binary_reader
     {
         result.first = npos; // size
         result.second = 0; // type
-        bool is_ndarray = false;
+        // seed the flag with the caller's context: inside an ndarray dimension
+        // vector another ndarray is not allowed, and get_ubjson_size_value()
+        // rejects it up front instead of reading it and reporting afterwards.
+        // Seeding it with `false` made every '#' of a "[#[#[..." chain descend
+        // another level, which overflowed the stack (see #5104).
+        bool is_ndarray = inside_ndarray;
 
         get_ignore_noop();
 
@@ -2359,13 +2623,11 @@ class binary_reader
             }
 
             const bool is_error = get_ubjson_size_value(result.first, is_ndarray);
-            if (input_format == input_format_t::bjdata && is_ndarray)
+            // an ndarray was read here only if the flag flipped; when it was
+            // seeded true, get_ubjson_size_value() already rejected the nested
+            // dimension vector
+            if (input_format == input_format_t::bjdata && is_ndarray && !inside_ndarray)
             {
-                if (inside_ndarray)
-                {
-                    return sax->parse_error(chars_read, get_token_string(), parse_error::create(112, chars_read,
-                                            exception_message(input_format, "ndarray can not be recursive", "size"), nullptr));
-                }
                 result.second |= (1 << 8); // use bit 8 to indicate ndarray, all UBJSON and BJData markers should be ASCII letters
             }
             return is_error;
@@ -2374,7 +2636,7 @@ class binary_reader
         if (current == '#')
         {
             const bool is_error = get_ubjson_size_value(result.first, is_ndarray);
-            if (input_format == input_format_t::bjdata && is_ndarray)
+            if (input_format == input_format_t::bjdata && is_ndarray && !inside_ndarray)
             {
                 return sax->parse_error(chars_read, get_token_string(), parse_error::create(112, chars_read,
                                         exception_message(input_format, "ndarray requires both type and size", "size"), nullptr));
@@ -2645,6 +2907,17 @@ class binary_reader
 
         if (size_and_type.first != npos)
         {
+            // reading an element of a valueless type consumes no input, so the
+            // declared count alone decides how much is allocated; the check is
+            // made before the start event so that no container is opened that
+            // is then abandoned. See @ref max_valueless_container_size.
+            if (JSON_HEDLEY_UNLIKELY((size_and_type.second == 'Z' || size_and_type.second == 'T' || size_and_type.second == 'F')
+                                     && size_and_type.first > max_valueless_container_size))
+            {
+                return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408,
+                                        exception_message(input_format, "excessive array size", "size"), nullptr));
+            }
+
             if (JSON_HEDLEY_UNLIKELY(!sax->start_array(size_and_type.first)))
             {
                 return false;
@@ -2825,7 +3098,17 @@ class binary_reader
             case token_type::value_unsigned:
                 return sax->number_unsigned(number_lexer.get_number_unsigned());
             case token_type::value_float:
-                return sax->number_float(number_lexer.get_number_float(), std::move(number_string));
+            {
+                const auto parsed_float = number_lexer.get_number_float();
+                if (JSON_HEDLEY_UNLIKELY(!std::isfinite(parsed_float)))
+                {
+                    return sax->parse_error(
+                               chars_read,
+                               number_string,
+                               out_of_range::create(406, concat("number overflow parsing '", number_string, '\''), nullptr));
+                }
+                return sax->number_float(parsed_float, std::move(number_string));
+            }
             case token_type::uninitialized:
             case token_type::literal_true:
             case token_type::literal_false:
@@ -3152,6 +3435,9 @@ class binary_reader
     /// the SAX parser
     json_sax_t* sax = nullptr;
 
+    /// the containers that have been opened and not closed yet; see @ref container_frame
+    std::vector<container_frame> container_stack{};
+
     // excluded markers in bjdata optimized type
 #define JSON_BINARY_READER_MAKE_BJD_OPTIMIZED_TYPE_MARKERS_ \
     make_array<char_int_type>('F', 'H', 'N', 'S', 'T', 'Z', '[', '{')

include/nlohmann/detail/input/input_adapters.hpp

@@ -345,8 +345,12 @@ struct wide_string_input_helper<BaseInputAdapter, 4>
             }
             else
             {
-                // unknown character
+                // A code point above U+10FFFF has no UTF-8 encoding. Passing the
-                utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(wc);
+                // unit through would narrow it to int, where 0xFFFFFFFF becomes
+                // char_traits<char>::eof() and would end the input silently, so
+                // emit a byte that is never valid UTF-8 and let the decoder
+                // reject it.
+                utf8_bytes[0] = 0xFF;
                 utf8_bytes_filled = 1;
             }
         }

include/nlohmann/detail/input/json_sax.hpp

@@ -370,8 +370,10 @@ class json_sax_dom_parser
 
                 case value_t::string:
                 {
-                    // include the length of the quotes, which is 2
+                    // escape sequences make the token longer than the value it
-                    v.start_position = v.end_position - v.m_data.m_value.string->size() - 2;
+                    // parses to, so the start position cannot be derived from
+                    // the value; use the offset the lexer recorded instead
+                    v.start_position = m_lexer_ref->get_token_start_position();
                     break;
                 }
 
@@ -626,14 +628,7 @@ class json_sax_dom_callback_parser
         if (!ref_stack.empty() && ref_stack.back() && ref_stack.back()->is_structured())
         {
             // remove discarded value
-            for (auto it = ref_stack.back()->begin(); it != ref_stack.back()->end(); ++it)
+            remove_discarded_value(*ref_stack.back());
-            {
-                if (it->is_discarded())
-                {
-                    ref_stack.back()->erase(it);
-                    break;
-                }
-            }
         }
 
         return true;
@@ -674,8 +669,9 @@ class json_sax_dom_callback_parser
     bool end_array()
     {
         bool keep = true;
+        const bool stored = ref_stack.back() != nullptr;
 
-        if (ref_stack.back())
+        if (stored)
         {
             keep = callback(static_cast<int>(ref_stack.size()) - 1, parse_event_t::array_end, *ref_stack.back());
             if (keep)
@@ -709,9 +705,19 @@ class json_sax_dom_callback_parser
         keep_stack.pop_back();
 
         // remove discarded value
-        if (!keep && !ref_stack.empty() && ref_stack.back()->is_array())
+        if (!ref_stack.empty() && ref_stack.back())
         {
-            ref_stack.back()->m_data.m_value.array->pop_back();
+            if (!keep && ref_stack.back()->is_array())
+            {
+                ref_stack.back()->m_data.m_value.array->pop_back();
+            }
+            else if ((!keep || !stored) && ref_stack.back()->is_object())
+            {
+                // the array is either still stored under its key or was never
+                // stored, leaving the placeholder key() wrote; both show up as
+                // a discarded member of the parent object
+                remove_discarded_value(*ref_stack.back());
+            }
         }
 
         return true;
@@ -765,8 +771,10 @@ class json_sax_dom_callback_parser
 
                 case value_t::string:
                 {
-                    // include the length of the quotes, which is 2
+                    // escape sequences make the token longer than the value it
-                    v.start_position = v.end_position - v.m_data.m_value.string->size() - 2;
+                    // parses to, so the start position cannot be derived from
+                    // the value; use the offset the lexer recorded instead
+                    v.start_position = m_lexer_ref->get_token_start_position();
                     break;
                 }
 
@@ -801,6 +809,19 @@ class json_sax_dom_callback_parser
     }
 #endif
 
+    /// remove the discarded value the callback rejected from its parent
+    static void remove_discarded_value(BasicJsonType& parent)
+    {
+        for (auto it = parent.begin(); it != parent.end(); ++it)
+        {
+            if (it->is_discarded())
+            {
+                parent.erase(it);
+                break;
+            }
+        }
+    }
+
     /*!
     @param[in] v  value to add to the JSON value we build during parsing
     @param[in] skip_callback  whether we should skip calling the callback
@@ -841,6 +862,18 @@ class json_sax_dom_callback_parser
         // do not handle this value if we just learnt it shall be discarded
         if (!keep)
         {
+            // if the value was to become an object member, key() already
+            // stored a placeholder for it that has to be removed again
+            if (!ref_stack.empty() && ref_stack.back() && ref_stack.back()->is_object())
+            {
+                JSON_ASSERT(!key_keep_stack.empty());
+                const bool placeholder_stored = key_keep_stack.back();
+                key_keep_stack.pop_back();
+                if (placeholder_stored)
+                {
+                    remove_discarded_value(*ref_stack.back());
+                }
+            }
             return {false, nullptr};
         }
 

include/nlohmann/detail/input/lexer.hpp

@@ -1357,6 +1357,11 @@ scan_number_done:
         token_buffer.clear();
         decimal_point_position = std::string::npos;
 
+#if JSON_DIAGNOSTIC_POSITIONS
+        // the first character of the token has already been read, hence the -1
+        token_start_position = position.chars_read_total - 1;
+#endif
+
         note_token_start(std::integral_constant<bool, lazy_token_string> {});
     }
 
@@ -1519,6 +1524,15 @@ scan_number_done:
         return position;
     }
 
+#if JSON_DIAGNOSTIC_POSITIONS
+    /// return the offset of the first character of the last read token; unlike
+    /// the token's parsed value, this accounts for escape sequences
+    constexpr std::size_t get_token_start_position() const noexcept
+    {
+        return token_start_position;
+    }
+#endif
+
     /// seekable adapter: rebuild the last read token from the input on demand
     const std::vector<char_type>& collect_token_chars(std::vector<char_type>& out, std::true_type /*lazy*/) const
     {
@@ -1719,6 +1733,12 @@ scan_number_done:
     /// the last read token on error for seekable adapters (see collect_token_chars)
     std::size_t token_string_start = 0;
 
+#if JSON_DIAGNOSTIC_POSITIONS
+    /// start offset of the current token within the input, used to report
+    /// diagnostic positions (see reset())
+    std::size_t token_start_position = 0;
+#endif
+
     /// buffer for variable-length tokens (numbers, strings)
     string_t token_buffer {};
 

include/nlohmann/detail/meta/type_traits.hpp

@@ -231,7 +231,9 @@ struct char_traits<signed char> : std::char_traits<char>
     // Redefine to_int_type function
     static int_type to_int_type(char_type c) noexcept
     {
-        return static_cast<int_type>(c);
+        // cast via unsigned char: sign-extending a negative char_type would make
+        // byte 0xFF indistinguishable from eof()
+        return static_cast<int_type>(static_cast<unsigned char>(c));
     }
 
     static char_type to_char_type(int_type i) noexcept
@@ -699,21 +701,35 @@ struct is_json_pointer_of<A, ::nlohmann::json_pointer<A>> : std::true_type {};
 template <typename A>
 struct is_json_pointer_of<A, ::nlohmann::json_pointer<A>&> : std::true_type {};
 
-// checks if A and B are comparable using Compare functor
+// checks if A and B are comparable using Compare functor, assuming that
+// neither A nor B is a json_pointer type (that case is handled by
+// is_comparable below, which never instantiates this helper otherwise)
 template<typename Compare, typename A, typename B, typename = void>
-struct is_comparable : std::false_type {};
+struct is_comparable_no_json_pointer : std::false_type {};
 
-// We exclude json_pointer here, because the checks using Compare(A, B) will
-// use json_pointer::operator string_t() which triggers a deprecation warning
-// for GCC. See https://github.com/nlohmann/json/issues/4621. The call to
-// is_json_pointer_of can be removed once the deprecated function has been
-// removed.
 template<typename Compare, typename A, typename B>
-struct is_comparable < Compare, A, B, enable_if_t < !is_json_pointer_of<A, B>::value
+struct is_comparable_no_json_pointer < Compare, A, B, enable_if_t <
-&& std::is_constructible <decltype(std::declval<Compare>()(std::declval<A>(), std::declval<B>()))>::value
+std::is_constructible <decltype(std::declval<Compare>()(std::declval<A>(), std::declval<B>()))>::value
 && std::is_constructible <decltype(std::declval<Compare>()(std::declval<B>(), std::declval<A>()))>::value
 >> : std::true_type {};
 
+// checks if A and B are comparable using Compare functor
+// We dispatch on is_json_pointer_of as a plain bool (rather than folding it
+// into a single enable_if_t condition together with the checks below) so
+// that the Compare(A, B) checks are only ever written - and thus only ever
+// instantiated - when A/B are not a json_pointer/string pair. Those checks
+// use json_pointer::operator string_t() (GCC, see #4621) resp. the
+// deprecated json_pointer/string operator== (Clang, see #5288), and merely
+// naming them as later operands of a plain && chain is not sufficient to
+// avoid their instantiation on all compilers, even when the first operand
+// is false. The dispatch on is_json_pointer_of can be removed once the
+// deprecated json_pointer comparison operators have been removed.
+template<typename Compare, typename A, typename B, bool = is_json_pointer_of<A, B>::value>
+struct is_comparable : std::false_type {};
+
+template<typename Compare, typename A, typename B>
+struct is_comparable<Compare, A, B, false> : is_comparable_no_json_pointer<Compare, A, B> {};
+
 template<typename T>
 using detect_is_transparent = typename T::is_transparent;
 

include/nlohmann/detail/output/binary_writer.hpp

@@ -813,7 +813,10 @@ class binary_writer
                 bool prefix_required = true;
                 if (use_type && !j.m_data.m_value.array->empty())
                 {
-                    JSON_ASSERT(use_count);
+                    if (!use_count)
+                    {
+                        JSON_THROW(other_error::create(502, "use_type requires use_size = true", &j));
+                    }
                     const CharType first_prefix = ubjson_prefix(j.front(), use_bjdata);
                     const bool same_prefix = std::all_of(j.begin() + 1, j.end(),
                                                          [this, first_prefix, use_bjdata](const BasicJsonType & v)
@@ -823,7 +826,17 @@ class binary_writer
 
                     std::vector<CharType> bjdx = {'[', '{', 'S', 'H', 'T', 'F', 'N', 'Z'}; // excluded markers in bjdata optimized type
 
-                    if (same_prefix && !(use_bjdata && std::find(bjdx.begin(), bjdx.end(), first_prefix) != bjdx.end()))
+                    // an optimized array of a valueless type carries no payload, so a
+                    // reader has nothing but the declared count to bound the allocation
+                    // by and refuses an excessive one. Write the unoptimized form for
+                    // those, at one byte per element, so the result can be read back.
+                    // Objects are not affected: every element is preceded by its key.
+                    const bool valueless_type = (first_prefix == 'Z' || first_prefix == 'T' || first_prefix == 'F');
+                    const bool excessive_valueless = valueless_type
+                                                     && j.m_data.m_value.array->size() > detail::max_valueless_container_size;
+
+                    if (same_prefix && !excessive_valueless
+                            && !(use_bjdata && std::find(bjdx.begin(), bjdx.end(), first_prefix) != bjdx.end()))
                     {
                         prefix_required = false;
                         oa->write_character(to_char_type('$'));
@@ -859,7 +872,10 @@ class binary_writer
 
                 if (use_type && (bjdata_draft3 || !j.m_data.m_value.binary->empty()))
                 {
-                    JSON_ASSERT(use_count);
+                    if (!use_count)
+                    {
+                        JSON_THROW(other_error::create(502, "use_type requires use_size = true", &j));
+                    }
                     oa->write_character(to_char_type('$'));
                     oa->write_character(bjdata_draft3 ? 'B' : 'U');
                 }
@@ -911,7 +927,10 @@ class binary_writer
                 bool prefix_required = true;
                 if (use_type && !j.m_data.m_value.object->empty())
                 {
-                    JSON_ASSERT(use_count);
+                    if (!use_count)
+                    {
+                        JSON_THROW(other_error::create(502, "use_type requires use_size = true", &j));
+                    }
                     const CharType first_prefix = ubjson_prefix(j.front(), use_bjdata);
                     const bool same_prefix = std::all_of(j.begin(), j.end(),
                                                          [this, first_prefix, use_bjdata](const BasicJsonType & v)
@@ -1659,6 +1678,15 @@ class binary_writer
         CharType dtype = it->second;
 
         key = "_ArraySize_";
+        // the dimensions are written verbatim as the header length below, so a
+        // value that is not an array cannot produce a valid one: null emits 'Z'
+        // and an object emits '{', neither of which a reader accepts after '#'.
+        // Such an object is not a valid ndarray and falls back to a plain object.
+        if (!value.at(key).is_array())
+        {
+            return true;
+        }
+
         std::size_t len = (value.at(key).empty() ? 0 : 1);
         for (const auto& el : value.at(key))
         {
@@ -1670,7 +1698,23 @@ class binary_writer
             {
                 return true;
             }
-            len *= static_cast<std::size_t>(el.template get<std::uint64_t>());
+
+            // a dimension that does not fit into std::size_t, or a product that
+            // overflows it, would wrap around and could match the size of
+            // _ArrayData_ by accident; the resulting header announces an
+            // element count that no reader can honor (the binary reader rejects
+            // it with out_of_range.408), so encode as a plain object instead
+            const auto dim = el.template get<std::uint64_t>();
+            if (!value_in_range_of<std::size_t>(dim))
+            {
+                return true;
+            }
+            const auto dim_size = static_cast<std::size_t>(dim);
+            if (dim_size != 0 && len > (std::numeric_limits<std::size_t>::max)() / dim_size)
+            {
+                return true;
+            }
+            len *= dim_size;
         }
 
         key = "_ArrayData_";

include/nlohmann/detail/value_t.hpp

@@ -9,9 +9,12 @@
 #pragma once
 
 #include <array> // array
+#include <cmath> // isnan, ldexp, trunc
 #include <cstddef> // size_t
 #include <cstdint> // uint8_t
+#include <limits> // numeric_limits
 #include <string> // string
+#include <type_traits> // is_signed
 
 #include <nlohmann/detail/macro_scope.hpp>
 #if JSON_HAS_THREE_WAY_COMPARISON
@@ -114,5 +117,67 @@ inline bool operator<(const value_t lhs, const value_t rhs) noexcept
 }
 #endif
 
+
+/*!
+@brief compare an integer with a floating point number without precision loss
+
+Widening the integer to the floating point type loses precision beyond the
+float's mantissa, which makes equality intransitive: both 2^63-2 and 2^63-1
+round to 2^63, so each compares equal to that float while differing from each
+other. Ordering built on that is not a strict weak ordering, so sorting such
+values, or using them as keys in an ordered container, is undefined behavior.
+
+Returns a value to be compared against zero with the original operator, which
+reproduces the exact ordering. A NaN operand is returned as is, so comparing it
+against zero keeps NaN's semantics: false for the relational operators and
+unordered for `<=>`.
+*/
+template<typename IntegerType, typename FloatType>
+FloatType compare_integer_with_float(const IntegerType i, const FloatType f) noexcept
+{
+    const auto ordered = [](int c) noexcept
+    {
+        return static_cast<FloatType>(c);
+    };
+
+    if (std::isnan(f))
+    {
+        return f;
+    }
+
+    // values of IntegerType lie in [-bound, bound) when signed and in
+    // [0, bound) when unsigned; digits excludes the sign bit, so bound is a
+    // power of two that the float represents exactly
+    const FloatType bound = std::ldexp(static_cast<FloatType>(1), std::numeric_limits<IntegerType>::digits);
+    if (f >= bound)
+    {
+        return ordered(-1);
+    }
+    if (std::is_signed<IntegerType>::value ? (f < -bound) : (f < static_cast<FloatType>(0)))
+    {
+        return ordered(1);
+    }
+
+    // f is now within the integer's range, so truncating it is exact
+    const FloatType truncated = std::trunc(f);
+    const auto as_integer = static_cast<IntegerType>(truncated);
+    if (i != as_integer)
+    {
+        return ordered(i < as_integer ? -1 : 1);
+    }
+
+    // the integer parts agree, so any fractional part decides
+    const FloatType fraction = f - truncated;
+    if (fraction > static_cast<FloatType>(0))
+    {
+        return ordered(-1);
+    }
+    if (fraction < static_cast<FloatType>(0))
+    {
+        return ordered(1);
+    }
+    return ordered(0);
+}
+
 }  // namespace detail
 NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/json.hpp

@@ -3516,7 +3516,10 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
             if (merge_objects && it.value().is_object())
             {
                 auto it2 = m_data.m_value.object->find(it.key());
-                if (it2 != m_data.m_value.object->end())
+                // Only recurse when the existing value is itself an object.
+                // Otherwise overwrite, matching the documented "all other values
+                // are overwritten as usual" behavior (see #5402).
+                if (it2 != m_data.m_value.object->end() && it2->second.is_object())
                 {
                     it2->second.update(it.value(), true);
 #if JSON_DIAGNOSTICS
@@ -3652,6 +3655,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     // note parentheses around operands are necessary; see
     // https://github.com/nlohmann/json/issues/1530
+    // Mixed signed/unsigned integer comparisons check whether the signed value
+    // is negative before casting. If it is, the comparison is performed with
+    // the fixed values -1 and 1, which preserves the ordering relationship
+    // because any negative signed value is smaller than any unsigned value.
+    // Otherwise, the non-negative signed value is cast to unsigned before the
+    // comparison to avoid wraparound.
 #define JSON_IMPLEMENT_OPERATOR(op, null_result, unordered_result, default_result)                       \
     const auto lhs_type = lhs.type();                                                                    \
     const auto rhs_type = rhs.type();                                                                    \
@@ -3694,28 +3703,32 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     }                                                                                                    \
     else if (lhs_type == value_t::number_integer && rhs_type == value_t::number_float)                   \
     {                                                                                                    \
-        return static_cast<number_float_t>(lhs.m_data.m_value.number_integer) op rhs.m_data.m_value.number_float;      \
+        return (detail::compare_integer_with_float(lhs.m_data.m_value.number_integer, rhs.m_data.m_value.number_float)) op (static_cast<number_float_t>(0)); \
     }                                                                                                    \
     else if (lhs_type == value_t::number_float && rhs_type == value_t::number_integer)                   \
     {                                                                                                    \
-        return lhs.m_data.m_value.number_float op static_cast<number_float_t>(rhs.m_data.m_value.number_integer);      \
+        return (static_cast<number_float_t>(0)) op (detail::compare_integer_with_float(rhs.m_data.m_value.number_integer, lhs.m_data.m_value.number_float)); \
     }                                                                                                    \
     else if (lhs_type == value_t::number_unsigned && rhs_type == value_t::number_float)                  \
     {                                                                                                    \
-        return static_cast<number_float_t>(lhs.m_data.m_value.number_unsigned) op rhs.m_data.m_value.number_float;     \
+        return (detail::compare_integer_with_float(lhs.m_data.m_value.number_unsigned, rhs.m_data.m_value.number_float)) op (static_cast<number_float_t>(0)); \
     }                                                                                                    \
     else if (lhs_type == value_t::number_float && rhs_type == value_t::number_unsigned)                  \
     {                                                                                                    \
-        return lhs.m_data.m_value.number_float op static_cast<number_float_t>(rhs.m_data.m_value.number_unsigned);     \
+        return (static_cast<number_float_t>(0)) op (detail::compare_integer_with_float(rhs.m_data.m_value.number_unsigned, lhs.m_data.m_value.number_float)); \
     }                                                                                                    \
     else if (lhs_type == value_t::number_unsigned && rhs_type == value_t::number_integer)                \
     {                                                                                                    \
-        return static_cast<number_integer_t>(lhs.m_data.m_value.number_unsigned) op rhs.m_data.m_value.number_integer; \
+        return (rhs.m_data.m_value.number_integer < 0)                                                   \
+               ? (number_integer_t(1) op number_integer_t(-1))                                           \
+               : (lhs.m_data.m_value.number_unsigned op static_cast<number_unsigned_t>(rhs.m_data.m_value.number_integer)); \
     }                                                                                                    \
     else if (lhs_type == value_t::number_integer && rhs_type == value_t::number_unsigned)                \
     {                                                                                                    \
-        return lhs.m_data.m_value.number_integer op static_cast<number_integer_t>(rhs.m_data.m_value.number_unsigned); \
+        return (lhs.m_data.m_value.number_integer < 0)                                                   \
-    }                                                                                                    \
+               ? (number_integer_t(-1) op number_integer_t(1))                                           \
+               : (static_cast<number_unsigned_t>(lhs.m_data.m_value.number_integer) op rhs.m_data.m_value.number_unsigned); \
+    }                                                                                             \
     else if(compares_unordered(lhs, rhs))\
     {\
         return (unordered_result);\
@@ -4460,8 +4473,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     /// @brief create a JSON value from an input in CBOR format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4477,8 +4493,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     template<typename T>
@@ -4503,8 +4522,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     /// @brief create a JSON value from an input in MessagePack format
@@ -4518,8 +4540,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     /// @brief create a JSON value from an input in MessagePack format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4534,8 +4559,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     template<typename T>
@@ -4558,8 +4586,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     /// @brief create a JSON value from an input in UBJSON format
@@ -4573,8 +4604,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     /// @brief create a JSON value from an input in UBJSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4589,8 +4623,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     template<typename T>
@@ -4613,8 +4650,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     /// @brief create a JSON value from an input in BJData format
@@ -4628,8 +4668,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     /// @brief create a JSON value from an input in BJData format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4644,8 +4687,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     /// @brief create a JSON value from an input in BSON format
@@ -4659,8 +4705,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     /// @brief create a JSON value from an input in BSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4675,8 +4724,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     template<typename T>
@@ -4699,8 +4751,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
     /// @}
 
@@ -5115,19 +5170,17 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
                 // We now reached the end of at least one array
                 // in a second pass, traverse the remaining elements
 
-                // remove my remaining elements
+                // remove my remaining elements, highest index first; appending
-                const auto end_index = static_cast<difference_type>(result.size());
+                // in that order avoids the quadratic reinsertion done before
-                while (i < source.size())
+                for (std::size_t j = source.size(); j > i; --j)
                 {
-                    // add operations in reverse order to avoid invalid
+                    result.push_back(object(
-                    // indices
-                    result.insert(result.begin() + end_index, object(
                     {
                         {"op", "remove"},
-                        {"path", detail::concat<string_t>(path, '/', detail::to_string<string_t>(i))}
+                        {"path", detail::concat<string_t>(path, '/', detail::to_string<string_t>(j - 1))}
                     }));
-                    ++i;
                 }
+                i = source.size();
 
                 // add other remaining elements
                 while (i < target.size())

tests/src/unit-32bit.cpp

@@ -132,3 +132,37 @@ TEST_CASE("BJData")
         }
     }
 }
+
+TEST_CASE("CBOR")
+{
+    SECTION("parse errors")
+    {
+        SECTION("array/map size larger than std::size_t")
+        {
+            // declared lengths do not fit in a 32-bit std::size_t and must not be truncated
+            std::vector<uint8_t> const varr = {0x9B, 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x05};
+            std::vector<uint8_t> const vmap = {0xBB, 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x05};
+
+            json _;
+            CHECK_THROWS_WITH_AS(_ = json::from_cbor(varr), "[json.exception.out_of_range.408] syntax error while parsing CBOR size: excessive array size", json::out_of_range&);
+            CHECK(json::from_cbor(varr, true, false).is_discarded());
+
+            CHECK_THROWS_WITH_AS(_ = json::from_cbor(vmap), "[json.exception.out_of_range.408] syntax error while parsing CBOR size: excessive map size", json::out_of_range&);
+            CHECK(json::from_cbor(vmap, true, false).is_discarded());
+        }
+
+        SECTION("array/map size equal to the indefinite-length sentinel")
+        {
+            // on 32-bit platforms a four-byte length of 0xFFFFFFFF aliases unknown_size()
+            std::vector<uint8_t> const varr = {0x9A, 0xFF, 0xFF, 0xFF, 0xFF};
+            std::vector<uint8_t> const vmap = {0xBA, 0xFF, 0xFF, 0xFF, 0xFF};
+
+            json _;
+            CHECK_THROWS_WITH_AS(_ = json::from_cbor(varr), "[json.exception.out_of_range.408] syntax error while parsing CBOR size: excessive array size", json::out_of_range&);
+            CHECK(json::from_cbor(varr, true, false).is_discarded());
+
+            CHECK_THROWS_WITH_AS(_ = json::from_cbor(vmap), "[json.exception.out_of_range.408] syntax error while parsing CBOR size: excessive map size", json::out_of_range&);
+            CHECK(json::from_cbor(vmap, true, false).is_discarded());
+        }
+    }
+}

tests/src/unit-bjdata.cpp

@@ -1347,6 +1347,8 @@ TEST_CASE("BJData")
                     CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vec2), "[json.exception.parse_error.115] parse error at byte 5: syntax error while parsing BJData high-precision number: invalid number text: 1A", json::parse_error);
                     std::vector<uint8_t> const vec3 = {'H', 'i', 2, '1', '.'};
                     CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vec3), "[json.exception.parse_error.115] parse error at byte 5: syntax error while parsing BJData high-precision number: invalid number text: 1.", json::parse_error);
+                    std::vector<uint8_t> const vec_overflow = {'H', 'i', 5, '1', 'e', '4', '0', '0'};
+                    CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vec_overflow), "[json.exception.out_of_range.406] number overflow parsing '1e400'", json::out_of_range);
                     std::vector<uint8_t> const vec4 = {'H', 2, '1', '0'};
                     CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vec4), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing BJData size: expected length type specification (U, i, u, I, m, l, M, L) after '#'; last byte: 0x02", json::parse_error);
                 }
@@ -2728,6 +2730,52 @@ TEST_CASE("BJData")
                 CHECK(json::from_bjdata(json::to_bjdata(j_type), true, true) == j_type);
                 CHECK(json::from_bjdata(json::to_bjdata(j_size), true, true) == j_size);
             }
+
+            SECTION("ndarray whose dimensions overflow stays as object")
+            {
+                // the product of the dimensions wraps around std::size_t to 0
+                // and so matches the size of the empty _ArrayData_; writing this
+                // as an ndarray would announce an element count no reader can
+                // honor, so it has to stay a plain object
+                json j_overflow = json({{"_ArrayData_", json::array()}, {"_ArraySize_", {9223372036854775808ull, 2}}, {"_ArrayType_", "uint8"}});
+                CHECK(json::from_bjdata(json::to_bjdata(j_overflow), true, true) == j_overflow);
+
+                // a single dimension that does not fit into std::size_t is
+                // rejected for the same reason (only observable where
+                // std::size_t is narrower than 64 bit)
+                json j_huge = json({{"_ArrayData_", json::array()}, {"_ArraySize_", {18446744073709551615ull}}, {"_ArrayType_", "uint8"}});
+                CHECK(json::from_bjdata(json::to_bjdata(j_huge), true, true) == j_huge);
+
+                // a well-formed ndarray is still encoded as one
+                json j_ok = json({{"_ArrayData_", {1, 2, 3, 4, 5, 6}}, {"_ArraySize_", {2, 3}}, {"_ArrayType_", "uint8"}});
+                CHECK(json::to_bjdata(j_ok) == std::vector<uint8_t>({'[', '$', 'U', '#', '[', 'i', 2, 'i', 3, ']', 1, 2, 3, 4, 5, 6}));
+                CHECK(json::from_bjdata(json::to_bjdata(j_ok), true, true) == j_ok);
+            }
+
+            SECTION("ndarray whose _ArraySize_ is not an array stays as object")
+            {
+                // the shape is written verbatim as the header length, so a
+                // value that is not an array cannot produce a valid one: null
+                // would emit 'Z' and an object '{', neither of which a reader
+                // accepts after '#'. Both have to stay plain objects.
+                json const j_null = json({{"_ArrayType_", "uint8"}, {"_ArraySize_", nullptr}, {"_ArrayData_", json::array()}});
+                const auto out_null = json::to_bjdata(j_null);
+                CHECK(out_null.at(0) == '{');
+                CHECK(json::from_bjdata(out_null) == j_null);
+
+                // an object shape passes the per-entry check by iterating its
+                // values rather than dimensions, so it needs rejecting too
+                json const j_obj = json({{"_ArrayType_", "uint8"}, {"_ArraySize_", {{"a", 1}}}, {"_ArrayData_", {1}}});
+                const auto out_obj = json::to_bjdata(j_obj);
+                CHECK(out_obj.at(0) == '{');
+                CHECK(json::from_bjdata(out_obj) == j_obj);
+
+                // a scalar shape is not a dimension list either
+                json const j_num = json({{"_ArrayType_", "uint8"}, {"_ArraySize_", 1}, {"_ArrayData_", {1}}});
+                const auto out_num = json::to_bjdata(j_num);
+                CHECK(out_num.at(0) == '{');
+                CHECK(json::from_bjdata(out_num) == j_num);
+            }
         }
     }
 
@@ -3240,8 +3288,10 @@ TEST_CASE("BJData")
             CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR1), "[json.exception.parse_error.113] parse error at byte 6: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
             CHECK(json::from_bjdata(vR1, true, false).is_discarded());
 
+            // a dimension vector that opens another one is rejected where the
+            // nested '[' is read, rather than after it has been descended into
             std::vector<uint8_t> const vR2 = {'[', '$', 'i', '#', '[', '#', '[', 'i', 1, ']', ']', 1};
-            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR2), "[json.exception.parse_error.113] parse error at byte 11: syntax error while parsing BJData size: expected length type specification (U, i, u, I, m, l, M, L) after '#'; last byte: 0x5D", json::parse_error&);
+            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR2), "[json.exception.parse_error.113] parse error at byte 7: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
             CHECK(json::from_bjdata(vR2, true, false).is_discarded());
 
             std::vector<uint8_t> const vR3 = {'[', '#', '[', 'i', '2', 'i', 2, ']'};
@@ -3249,7 +3299,7 @@ TEST_CASE("BJData")
             CHECK(json::from_bjdata(vR3, true, false).is_discarded());
 
             std::vector<uint8_t> const vR4 = {'[', '$', 'i', '#', '[', '$', 'i', '#', '[', 'i', 1, ']', 1};
-            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR4), "[json.exception.parse_error.110] parse error at byte 14: syntax error while parsing BJData number: unexpected end of input", json::parse_error&);
+            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR4), "[json.exception.parse_error.113] parse error at byte 9: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
             CHECK(json::from_bjdata(vR4, true, false).is_discarded());
 
             std::vector<uint8_t> const vR5 = {'[', '$', 'i', '#', '[', '[', '[', ']', ']', ']'};
@@ -3257,12 +3307,25 @@ TEST_CASE("BJData")
             CHECK(json::from_bjdata(vR5, true, false).is_discarded());
 
             std::vector<uint8_t> const vR6 = {'[', '$', 'i', '#', '[', '$', 'i', '#', '[', 'i', '2', 'i', 2, ']'};
-            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR6), "[json.exception.parse_error.112] parse error at byte 14: syntax error while parsing BJData size: ndarray can not be recursive", json::parse_error&);
+            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR6), "[json.exception.parse_error.113] parse error at byte 9: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
             CHECK(json::from_bjdata(vR6, true, false).is_discarded());
 
             std::vector<uint8_t> const vH = {'[', 'H', '[', '#', '[', '$', 'i', '#', '[', 'i', '2', 'i', 2, ']'};
             CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vH), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
             CHECK(json::from_bjdata(vH, true, false).is_discarded());
+
+            // Every "#[" of this chain used to open another dimension vector
+            // and cost several stack frames before anything was rejected, so a
+            // long enough chain crashed the process (see #5104). The nested
+            // vector is refused where it is read, so the length is irrelevant.
+            std::vector<uint8_t> vRdeep = {'['};
+            for (std::size_t i = 0; i < 100000; ++i)
+            {
+                vRdeep.push_back('#');
+                vRdeep.push_back('[');
+            }
+            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vRdeep), "[json.exception.parse_error.113] parse error at byte 5: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
+            CHECK(json::from_bjdata(vRdeep, true, false).is_discarded());
         }
 
         SECTION("objects")
@@ -3820,6 +3883,48 @@ TEST_CASE("all BJData first bytes")
 }
 #endif
 
+TEST_CASE("BJData use_type requires use_size")
+{
+    SECTION("non-empty object throws other_error.502")
+    {
+        const json j = {{"a", 1}, {"b", 2}};
+        CHECK_THROWS_WITH_AS(json::to_bjdata(j, false, true),
+                             "[json.exception.other_error.502] use_type requires use_size = true",
+                             json::other_error&);
+    }
+
+    SECTION("non-empty array throws other_error.502")
+    {
+        const json j = {1, 2, 3};
+        CHECK_THROWS_WITH_AS(json::to_bjdata(j, false, true),
+                             "[json.exception.other_error.502] use_type requires use_size = true",
+                             json::other_error&);
+    }
+
+    SECTION("scalars do not throw with use_type=true, use_count=false")
+    {
+        CHECK_NOTHROW(json::to_bjdata(42, false, true));
+        CHECK_NOTHROW(json::to_bjdata(3.14, false, true));
+        CHECK_NOTHROW(json::to_bjdata("hello", false, true));
+        CHECK_NOTHROW(json::to_bjdata(true, false, true));
+        CHECK_NOTHROW(json::to_bjdata(nullptr, false, true));
+    }
+
+    SECTION("empty containers do not throw with use_type=true, use_count=false")
+    {
+        CHECK_NOTHROW(json::to_bjdata(json::array(), false, true));
+        CHECK_NOTHROW(json::to_bjdata(json::object(), false, true));
+    }
+
+    SECTION("valid combinations on non-empty containers")
+    {
+        const json j = {{"a", 1}, {"b", 2}};
+        CHECK_NOTHROW(json::to_bjdata(j, false, false));
+        CHECK_NOTHROW(json::to_bjdata(j, true, false));
+        CHECK_NOTHROW(json::to_bjdata(j, true, true));
+    }
+}
+
 TEST_CASE("BJData roundtrips" * doctest::skip())
 {
     SECTION("input from self-generated BJData files")

tests/src/unit-cbor.cpp

@@ -1999,6 +1999,94 @@ TEST_CASE("CBOR regressions")
 }
 #endif
 
+TEST_CASE("CBOR definite length equal to the indefinite-length sentinel")
+{
+    // A definite-length array or map whose declared element count equals the
+    // reserved unknown_size() sentinel (SIZE_MAX) must be rejected. Otherwise
+    // it is read as an indefinite-length container and the following bytes are
+    // silently accepted instead of the (impossible) count being reported.
+    json _;
+
+    SECTION("array")
+    {
+        // 0x9B: array with eight-byte length; length = 0xFFFFFFFFFFFFFFFF
+        const std::vector<uint8_t> input = {0x9B, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x01, 0x02, 0xFF};
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.out_of_range.408] syntax error while parsing CBOR size: excessive array size", json::out_of_range&);
+    }
+
+    SECTION("map")
+    {
+        // 0xBB: map with eight-byte length; length = 0xFFFFFFFFFFFFFFFF
+        const std::vector<uint8_t> input = {0xBB, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x61, 0x61, 0x01, 0xFF};
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.out_of_range.408] syntax error while parsing CBOR size: excessive map size", json::out_of_range&);
+    }
+
+    SECTION("indefinite-length containers are unaffected")
+    {
+        CHECK(json::from_cbor(std::vector<uint8_t>({0x9F, 0x01, 0x02, 0xFF})) == json({1, 2}));
+        CHECK(json::from_cbor(std::vector<uint8_t>({0xBF, 0x61, 0x61, 0x01, 0xFF})) == json({{"a", 1}}));
+    }
+
+    SECTION("ordinary four-byte length containers are unaffected")
+    {
+        // 0x9A/0xBA carry a four-byte length; a normal count still parses
+        CHECK(json::from_cbor(std::vector<uint8_t>({0x9A, 0x00, 0x00, 0x00, 0x02, 0x01, 0x02})) == json({1, 2}));
+        CHECK(json::from_cbor(std::vector<uint8_t>({0xBA, 0x00, 0x00, 0x00, 0x01, 0x61, 0x61, 0x01})) == json({{"a", 1}}));
+    }
+}
+
+TEST_CASE("CBOR indefinite-length strings do not recurse per chunk")
+{
+    // Reading an indefinite-length string or byte array used to call itself
+    // once per chunk, so a payload of repeated 0x7F (or 0x5F) bytes exhausted
+    // the call stack before any of the input was rejected. The open levels are
+    // counted now, and the levels below prove the reader still reads the same
+    // values and reports the same errors at the same byte offsets.
+    json _;
+
+    SECTION("many open levels are reported, not crashed on")
+    {
+        const std::vector<uint8_t> input(200000, 0x7F);
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.parse_error.110] parse error at byte 200001: syntax error while parsing CBOR string: unexpected end of input", json::parse_error&);
+        CHECK(json::from_cbor(input, true, false).is_discarded());
+    }
+
+    SECTION("many open levels are reported, not crashed on (binary)")
+    {
+        const std::vector<uint8_t> input(200000, 0x5F);
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.parse_error.110] parse error at byte 200001: syntax error while parsing CBOR binary: unexpected end of input", json::parse_error&);
+        CHECK(json::from_cbor(input, true, false).is_discarded());
+    }
+
+    SECTION("chunks are still concatenated")
+    {
+        CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0xFF})) == json(""));
+        CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x61, 0x61, 0xFF})) == json("a"));
+        // nested indefinite-length strings are concatenated across levels
+        CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x7F, 0x61, 0x61, 0xFF, 0x61, 0x62, 0xFF})) == json("ab"));
+        CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x7F, 0x7F, 0x61, 0x7A, 0xFF, 0xFF, 0xFF})) == json("z"));
+        CHECK(json::from_cbor(std::vector<uint8_t>({0xA1, 0x7F, 0x61, 0x61, 0xFF, 0x01})) == json({{"a", 1}}));
+    }
+
+    SECTION("chunks are still concatenated (binary)")
+    {
+        CHECK(json::from_cbor(std::vector<uint8_t>({0x5F, 0x41, 0x61, 0xFF})) == json::binary({0x61}));
+        CHECK(json::from_cbor(std::vector<uint8_t>({0x5F, 0x5F, 0x41, 0x61, 0xFF, 0x41, 0x62, 0xFF})) == json::binary({0x61, 0x62}));
+    }
+
+    SECTION("a chunk that is not a string is still rejected")
+    {
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x7F, 0x7F, 0x00})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0x00", json::parse_error&);
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x5F, 0x5F, 0x00})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR binary: expected length specification (0x40-0x5B) or indefinite binary array type (0x5F); last byte: 0x00", json::parse_error&);
+    }
+
+    SECTION("a break marker outside an indefinite-length string is not a string")
+    {
+        // 0xFF only closes a string that was opened; on its own it is not one
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xA1, 0xFF, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0xFF", json::parse_error&);
+    }
+}
+
 TEST_CASE("CBOR roundtrips" * doctest::skip())
 {
     SECTION("input from flynn")
@@ -2529,11 +2617,16 @@ TEST_CASE("Tagged values")
     const json j = "s";
     auto v = json::to_cbor(j);
 
-    SECTION("0xC6..0xD4")
+    const json j_bin_payload = json::binary(std::vector<std::uint8_t> {0x01, 0x02, 0x03});
+    auto v_bin_payload = json::to_cbor(j_bin_payload);
+
+    SECTION("0xC0..0xD7")
     {
         for (const auto b : std::vector<std::uint8_t>
     {
-        0xC6, 0xC7, 0xC8, 0xC9, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF, 0xD0, 0xD1, 0xD2, 0xD3, 0xD4
+        0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5,
+        0xC6, 0xC7, 0xC8, 0xC9, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF, 0xD0, 0xD1, 0xD2, 0xD3, 0xD4,
+        0xD5, 0xD6, 0xD7
     })
         {
             CAPTURE(b);
@@ -2553,6 +2646,12 @@ TEST_CASE("Tagged values")
 
             auto j_tagged_stored = json::from_cbor(v_tagged, true, true, json::cbor_tag_handler_t::store);
             CHECK(j_tagged_stored == j);
+
+            auto v_binary_tagged = v_bin_payload;
+            v_binary_tagged.insert(v_binary_tagged.begin(), b);
+            auto j_binary_tagged_stored = json::from_cbor(v_binary_tagged, true, true, json::cbor_tag_handler_t::store);
+            CHECK(j_binary_tagged_stored == j_bin_payload);
+            CHECK(!j_binary_tagged_stored.get_binary().has_subtype());
         }
     }
 

tests/src/unit-class_parser.cpp

@@ -1440,6 +1440,13 @@ TEST_CASE("parser class")
             ]
         )";
 
+        const auto* structured_object = R"(
+            {
+                "foo": [1, 2],
+                "bar": 3
+            }
+        )";
+
         SECTION("filter nothing")
         {
             const json j_object = json::parse(s_object, [](int /*unused*/, json::parse_event_t /*unused*/, const json& /*unused*/) noexcept
@@ -1515,6 +1522,48 @@ TEST_CASE("parser class")
             CHECK (j_filtered2 == json({1}));
         }
 
+        SECTION("filter array in object")
+        {
+            // the array is discarded once it is already stored under its key
+            const json j_filtered1 = json::parse(structured_object, [](int /*unused*/, json::parse_event_t e, const json& /*parsed*/) noexcept
+            {
+                return e != json::parse_event_t::array_end;
+            });
+
+            CHECK (j_filtered1 == json({{"bar", 3}}));
+
+            // the array is discarded before it is stored, leaving the
+            // placeholder the key event wrote
+            const json j_filtered2 = json::parse(structured_object, [](int /*unused*/, json::parse_event_t e, const json& /*parsed*/) noexcept
+            {
+                return e != json::parse_event_t::array_start;
+            });
+
+            CHECK (j_filtered2 == json({{"bar", 3}}));
+        }
+
+        SECTION("filter value in object")
+        {
+            // the value is discarded after its key was kept, leaving the
+            // placeholder the key event wrote
+            const json j_filtered1 = json::parse(structured_object, [](int /*unused*/, json::parse_event_t e, const json & parsed) noexcept
+            {
+                return !(e == json::parse_event_t::value && parsed == json(3));
+            });
+
+            CHECK (j_filtered1 == json({{"foo", {1, 2}}}));
+
+            // the same value is discarded together with its key, so no
+            // placeholder was stored for it
+            const json j_filtered2 = json::parse(structured_object, [](int /*unused*/, json::parse_event_t e, const json & parsed) noexcept
+            {
+                return !((e == json::parse_event_t::key && parsed == json("bar")) ||
+                         (e == json::parse_event_t::value && parsed == json(3)));
+            });
+
+            CHECK (j_filtered2 == json({{"foo", {1, 2}}}));
+        }
+
         SECTION("filter specific events")
         {
             SECTION("first closing event")

tests/src/unit-comparison.cpp

@@ -15,6 +15,8 @@
 
 #include "doctest_compatibility.h"
 
+#include <cstdint>
+
 #define JSON_TESTS_PRIVATE
 #include <nlohmann/json.hpp>
 using nlohmann::json;
@@ -255,6 +257,126 @@ TEST_CASE("lexicographical comparison operators")
             {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_FALSE(above_int64_max == negative_one);
+            CHECK(above_int64_max != negative_one);
+            CHECK(negative_one < above_int64_max);
+            CHECK(negative_one <= above_int64_max);
+            CHECK_FALSE(negative_one > above_int64_max);
+            CHECK_FALSE(negative_one >= above_int64_max);
+            CHECK_FALSE(above_int64_max < negative_one);
+            CHECK_FALSE(above_int64_max <= negative_one);
+            CHECK(above_int64_max > negative_one);
+            CHECK(above_int64_max >= negative_one);
+            CHECK(negative_one != above_int64_max);
+            CHECK_FALSE(negative_one == above_int64_max);
+
+            CHECK_FALSE(max_uint64 == negative_one);
+            CHECK(max_uint64 != negative_one);
+            CHECK(negative_one < max_uint64);
+            CHECK(negative_one <= max_uint64);
+            CHECK_FALSE(negative_one > max_uint64);
+            CHECK_FALSE(negative_one >= max_uint64);
+            CHECK_FALSE(max_uint64 < negative_one);
+            CHECK_FALSE(max_uint64 <= negative_one);
+            CHECK(max_uint64 > negative_one);
+            CHECK(max_uint64 >= negative_one);
+            CHECK(negative_one != max_uint64);
+            CHECK_FALSE(negative_one == max_uint64);
+
+            CHECK_FALSE(one == above_int64_max);
+            CHECK(one != above_int64_max);
+            CHECK(one < above_int64_max);
+            CHECK(one <= above_int64_max);
+            CHECK_FALSE(one > above_int64_max);
+            CHECK_FALSE(one >= above_int64_max);
+            CHECK_FALSE(above_int64_max < one);
+            CHECK_FALSE(above_int64_max <= one);
+            CHECK(above_int64_max > one);
+            CHECK(above_int64_max >= one);
+
+            CHECK_FALSE(max_int64 == above_int64_max);
+            CHECK(max_int64 != above_int64_max);
+            CHECK(max_int64 < above_int64_max);
+            CHECK(max_int64 <= above_int64_max);
+            CHECK_FALSE(max_int64 > above_int64_max);
+            CHECK_FALSE(max_int64 >= above_int64_max);
+            CHECK_FALSE(above_int64_max < max_int64);
+            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")
+        {
+            // 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;
+
+            CHECK_FALSE(below_two_63 == two_63);
+            CHECK_FALSE(max_int64 == two_63);
+            CHECK(below_two_63 != max_int64);
+            CHECK(below_two_63 < max_int64);
+            CHECK(below_two_63 < two_63);
+            CHECK(max_int64 < two_63);
+            CHECK(two_63 > max_int64);
+            CHECK_FALSE(two_63 < max_int64);
+
+            // the same past the unsigned range
+            const json max_uint64 = (std::numeric_limits<std::uint64_t>::max)();
+            const json two_64 = 18446744073709551616.0;
+            CHECK_FALSE(max_uint64 == two_64);
+            CHECK(max_uint64 < two_64);
+            CHECK(two_64 > max_uint64);
+
+            // values a double represents exactly still compare equal
+            CHECK(json(1) == json(1.0));
+            CHECK(json(1u) == json(1.0));
+            CHECK(json(-3) == json(-3.0));
+            CHECK(json(1) < json(1.5));
+            CHECK(json(1.5) < json(2));
+            CHECK(json(2) > json(1.5));
+
+            // a NaN operand stays unordered against either integer kind
+            CHECK_FALSE(json(1) == json(nan));
+            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")
         {
             std::vector<std::vector<bool>> expected =

tests/src/unit-deserialization.cpp

@@ -427,6 +427,30 @@ TEST_CASE("deserialization")
                 CHECK(l.events == std::vector<std::string>({"boolean(true)"}));
             }
 
+            SECTION("from std::vector<signed char>")
+            {
+                std::vector<signed char> const v = {'t', 'r', 'u', 'e'};
+                CHECK(json::parse(v) == json(true));
+                CHECK(json::accept(v));
+
+                SaxEventLogger l;
+                CHECK(json::sax_parse(v, &l));
+                CHECK(l.events.size() == 1);
+                CHECK(l.events == std::vector<std::string>({"boolean(true)"}));
+
+                // bytes outside ASCII are negative here and must not be sign-extended;
+                // 0xC3 and 0xA9 do not fit in signed char (MSVC C4309), so spell them as negative values
+                std::vector<signed char> const umlaut = {'"', static_cast<signed char>(0xC3 - 0x100), static_cast<signed char>(0xA9 - 0x100), '"'};
+                CHECK(json::parse(umlaut) == json("\xC3\xA9"));
+                CHECK(json::accept(umlaut));
+
+                // 0xFF (spelled as -1 to stay in range) must not be reported as end of input
+                std::vector<signed char> const trailing = {'t', 'r', 'u', 'e', static_cast<signed char>(0xFF - 0x100)};
+                json _;
+                CHECK_THROWS_WITH_AS(_ = json::parse(trailing), "[json.exception.parse_error.101] parse error at line 1, column 5: syntax error while parsing value - invalid literal; last read: 'true\xFF'; expected end of input", json::parse_error&);
+                CHECK(!json::accept(trailing));
+            }
+
             SECTION("from std::array")
             {
                 std::array<uint8_t, 5> const v { {'t', 'r', 'u', 'e'} };

tests/src/unit-diagnostic-positions.cpp

@@ -38,6 +38,36 @@ TEST_CASE("Better diagnostics with positions")
                              "[json.exception.type_error.302] type must be number, but is string", json::type_error);
     }
 
+    SECTION("positions of strings containing escape sequences")
+    {
+        // escape sequences make the token longer than the string it parses to,
+        // so the positions must not be derived from the parsed value's length
+        const auto check = [](const std::string & text, const std::string & token)
+        {
+            CAPTURE(text)
+            CAPTURE(token)
+            const json j = json::parse(text);
+            const json& v = j.at("a");
+            CHECK(text.substr(v.start_pos(), v.end_pos() - v.start_pos()) == token);
+        };
+
+        check(R"({"a":"plain"})", R"("plain")");
+        check(R"({"a":"tab\there"})", R"("tab\there")");
+        check(R"({"a":"\n\n\n\n\n\n"})", R"("\n\n\n\n\n\n")");
+        check(R"({"a":"\""})", R"("\"")");
+        check(R"({"a":"\\"})", R"("\\")");
+        check(R"({"a":"é"})", R"("é")");
+        check(R"({"a":"🌞"})", R"("🌞")");
+        check("{\"a\":\"\xc3\xa9\"}", "\"\xc3\xa9\"");  // multi-byte UTF-8, no escapes
+
+        // a string at the root, where an escape would otherwise push the
+        // reported start position past the opening quote
+        const std::string root = R"("a\tb")";
+        const json j = json::parse(root);
+        CHECK(j.start_pos() == 0);
+        CHECK(j.end_pos() == root.size());
+    }
+
     SECTION("JSON patch add to primitive parent (#4292)")
     {
         // the JSON Patch "add" target /foo/bar/baz has a string parent

tests/src/unit-json_patch.cpp

@@ -1388,3 +1388,84 @@ TEST_CASE("JSON patch - add to a primitive parent (regression #4292)")
         CHECK_THROWS_AS(doc.patch(patch), json::out_of_range&);
     }
 }
+
+TEST_CASE("JSON patch - diff emits array removals in descending index order")
+{
+    SECTION("array shrunk to empty")
+    {
+        json const source = {0, 1, 2, 3, 4};
+        json const target = json::array();
+
+        json const patch = json::diff(source, target);
+
+        json const expected = R"(
+            [
+                {"op": "remove", "path": "/4"},
+                {"op": "remove", "path": "/3"},
+                {"op": "remove", "path": "/2"},
+                {"op": "remove", "path": "/1"},
+                {"op": "remove", "path": "/0"}
+            ]
+        )"_json;
+
+        CHECK(patch == expected);
+        CHECK(source.patch(patch) == target);
+    }
+
+    SECTION("array partially shrunk, after a replacement at a common index")
+    {
+        json const source = {0, 1, 2, 3, 4};
+        json const target = {0, 9};
+
+        json const patch = json::diff(source, target);
+
+        // the replacement comes first, then the removals, highest index first
+        json const expected = R"(
+            [
+                {"op": "replace", "path": "/1", "value": 9},
+                {"op": "remove", "path": "/4"},
+                {"op": "remove", "path": "/3"},
+                {"op": "remove", "path": "/2"}
+            ]
+        )"_json;
+
+        CHECK(patch == expected);
+        CHECK(source.patch(patch) == target);
+    }
+
+    SECTION("nested array shrunk")
+    {
+        json const source = {{"a", {0, 1, 2}}};
+        json const target = {{"a", json::array()}};
+
+        json const patch = json::diff(source, target);
+
+        json const expected = R"(
+            [
+                {"op": "remove", "path": "/a/2"},
+                {"op": "remove", "path": "/a/1"},
+                {"op": "remove", "path": "/a/0"}
+            ]
+        )"_json;
+
+        CHECK(patch == expected);
+        CHECK(source.patch(patch) == target);
+    }
+
+    SECTION("many removals still round-trip")
+    {
+        json source = json::array();
+        for (int i = 0; i < 1000; ++i)
+        {
+            source.push_back(i);
+        }
+        json const target = json::array();
+
+        json const patch = json::diff(source, target);
+
+        CHECK(patch.size() == 1000);
+        CHECK(patch.front().at("path") == "/999");
+        CHECK(patch.back().at("path") == "/0");
+        CHECK(source.patch(patch) == target);
+    }
+}

tests/src/unit-modifiers.cpp

@@ -801,6 +801,30 @@ TEST_CASE("modifiers")
                     j1.update(j2, true);
                     CHECK(j1 == json({{"string", "t"}, {"numbers", 1}}));
                 }
+
+                SECTION("overwrite primitive with object")
+                {
+                    json j1 = {{"k", 1}};
+                    json const j2 = {{"k", {{"x", 2}}}};
+                    j1.update(j2, true);
+                    CHECK(j1 == json({{"k", {{"x", 2}}}}));
+                }
+
+                SECTION("overwrite array with object")
+                {
+                    json j1 = {{"k", {1, 2}}};
+                    json const j2 = {{"k", {{"x", 2}}}};
+                    j1.update(j2, true);
+                    CHECK(j1 == json({{"k", {{"x", 2}}}}));
+                }
+
+                SECTION("overwrite nested primitive with object")
+                {
+                    json j1 = {{"k", {{"inner", 1}}}};
+                    json const j2 = {{"k", {{"inner", {{"x", 2}}}}}};
+                    j1.update(j2, true);
+                    CHECK(j1 == json({{"k", {{"inner", {{"x", 2}}}}}}));
+                }
             }
         }
     }

tests/src/unit-msgpack.cpp

@@ -1598,6 +1598,67 @@ TEST_CASE("MessagePack")
 }
 
 // use this testcase outside [hide] to run it with Valgrind
+TEST_CASE("MessagePack nesting does not consume the call stack")
+{
+    // Reading a container used to call back into the value reader once per
+    // element, so the native call stack grew with the nesting depth of the
+    // input: one frame per byte for repeated 0x91 (a one-element array), which
+    // crashes the process long before the input is exhausted (#5104). The
+    // containers are kept on a heap stack now.
+    //
+    // Note that deeply nested values must not be compared, copied or dumped
+    // here: those operations are still recursive, and would reintroduce the
+    // very crash this checks for. Depth is measured by descending instead.
+
+    SECTION("an unterminated chain is reported, not crashed on")
+    {
+        json _;
+        const std::vector<uint8_t> input(300000, 0x91);
+        CHECK_THROWS_WITH_AS(_ = json::from_msgpack(input), "[json.exception.parse_error.110] parse error at byte 300001: syntax error while parsing MessagePack value: unexpected end of input", json::parse_error&);
+        CHECK(json::from_msgpack(input, true, false).is_discarded());
+    }
+
+    SECTION("a well-formed deep value is read through the SAX interface")
+    {
+        std::vector<uint8_t> input(300000, 0x91);
+        input.push_back(0x01); // innermost value
+
+        SaxCountdown accept_all(600001);
+        CHECK(json::sax_parse(input, &accept_all, json::input_format_t::msgpack));
+    }
+
+    SECTION("a well-formed deep value is read into a value")
+    {
+        const std::size_t depth = 10000;
+        std::vector<uint8_t> input(depth, 0x91);
+        input.push_back(0x01);
+
+        json j = json::from_msgpack(input);
+
+        std::size_t measured = 0;
+        const json* p = &j;
+        while (p->is_array() && !p->empty())
+        {
+            p = &p->front();
+            ++measured;
+        }
+        CHECK(measured == depth);
+        CHECK(p->is_number());
+    }
+
+    SECTION("containers are still read the same way")
+    {
+        CHECK(json::from_msgpack(std::vector<uint8_t>({0x90})) == json::array());
+        CHECK(json::from_msgpack(std::vector<uint8_t>({0x80})) == json::object());
+        CHECK(json::from_msgpack(std::vector<uint8_t>({0x92, 0x90, 0x80})) == json({json::array(), json::object()}));
+        CHECK(json::from_msgpack(std::vector<uint8_t>({0x91, 0x91, 0x91, 0x90})) == json({{{json::array()}}}));
+        CHECK(json::from_msgpack(std::vector<uint8_t>({0x81, 0xA1, 'a', 0x81, 0xA1, 'b', 0x92, 0x01, 0x02})) == json({{"a", {{"b", {1, 2}}}}}));
+        // array 16 and map 32, i.e. the counted forms
+        CHECK(json::from_msgpack(std::vector<uint8_t>({0xDC, 0x00, 0x02, 0x01, 0x02})) == json({1, 2}));
+        CHECK(json::from_msgpack(std::vector<uint8_t>({0xDF, 0x00, 0x00, 0x00, 0x01, 0xA1, 'k', 0xC3})) == json({{"k", true}}));
+    }
+}
+
 TEST_CASE("single MessagePack roundtrip")
 {
     SECTION("sample.json")

tests/src/unit-regression2.cpp

@@ -239,209 +239,6 @@ class my_allocator : public std::allocator<T>
     };
 };
 
-/////////////////////////////////////////////////////////////////////
-// for #3077
-/////////////////////////////////////////////////////////////////////
-
-class FooAlloc
-{};
-
-class Foo
-{
-  public:
-    explicit Foo(const FooAlloc& /* unused */ = FooAlloc()) {}
-
-    bool value = false;
-};
-
-class FooBar
-{
-  public:
-    Foo foo{}; // NOLINT(readability-redundant-member-init)
-};
-
-inline void from_json(const nlohmann::json& j, FooBar& fb) // NOLINT(misc-use-internal-linkage)
-{
-    j.at("value").get_to(fb.foo.value);
-}
-
-/////////////////////////////////////////////////////////////////////
-// for #3171
-/////////////////////////////////////////////////////////////////////
-
-struct for_3171_base // NOLINT(cppcoreguidelines-special-member-functions)
-{
-    for_3171_base(const std::string& /*unused*/ = {}) {}
-    virtual ~for_3171_base();
-
-    for_3171_base(const for_3171_base& other) // NOLINT(hicpp-use-equals-default,modernize-use-equals-default)
-        : str(other.str)
-    {}
-
-    for_3171_base& operator=(const for_3171_base& other)
-    {
-        if (this != &other)
-        {
-            str = other.str;
-        }
-        return *this;
-    }
-
-    for_3171_base(for_3171_base&& other) noexcept
-        : str(std::move(other.str))
-    {}
-
-    for_3171_base& operator=(for_3171_base&& other) noexcept
-    {
-        if (this != &other)
-        {
-            str = std::move(other.str);
-        }
-        return *this;
-    }
-
-    virtual void _from_json(const json& j)
-    {
-        j.at("str").get_to(str);
-    }
-
-    std::string str{}; // NOLINT(readability-redundant-member-init)
-};
-
-for_3171_base::~for_3171_base() = default;
-
-struct for_3171_derived : public for_3171_base
-{
-    for_3171_derived() = default;
-    ~for_3171_derived() override;
-    explicit for_3171_derived(const std::string& /*unused*/) { }
-
-    for_3171_derived(const for_3171_derived& other) // NOLINT(hicpp-use-equals-default,modernize-use-equals-default)
-        : for_3171_base(other)
-    {}
-
-    for_3171_derived& operator=(const for_3171_derived& other)
-    {
-        if (this != &other)
-        {
-            for_3171_base::operator=(other); // Call base class assignment operator
-        }
-        return *this;
-    }
-
-    for_3171_derived(for_3171_derived&& other) noexcept
-        : for_3171_base(std::move(other))
-    {}
-
-    for_3171_derived& operator=(for_3171_derived&& other) noexcept
-    {
-        if (this != &other)
-        {
-            for_3171_base::operator=(std::move(other)); // Call base class move assignment operator
-        }
-        return *this;
-    }
-};
-
-for_3171_derived::~for_3171_derived() = default;
-
-inline void from_json(const json& j, for_3171_base& tb) // NOLINT(misc-use-internal-linkage)
-{
-    tb._from_json(j);
-}
-
-/////////////////////////////////////////////////////////////////////
-// for #3312
-/////////////////////////////////////////////////////////////////////
-
-#ifdef JSON_HAS_CPP_20
-struct for_3312
-{
-    std::string name;
-};
-
-inline void from_json(const json& j, for_3312& obj) // NOLINT(misc-use-internal-linkage)
-{
-    j.at("name").get_to(obj.name);
-}
-#endif
-
-/////////////////////////////////////////////////////////////////////
-// for #3204
-/////////////////////////////////////////////////////////////////////
-
-struct for_3204_foo
-{
-    for_3204_foo() = default;
-    explicit for_3204_foo(std::string /*unused*/) {} // NOLINT(performance-unnecessary-value-param)
-};
-
-struct for_3204_bar
-{
-    enum constructed_from_t // NOLINT(cppcoreguidelines-use-enum-class)
-    {
-        constructed_from_none = 0,
-        constructed_from_foo = 1,
-        constructed_from_json = 2
-    };
-
-    explicit for_3204_bar(std::function<void(for_3204_foo)> /*unused*/) noexcept // NOLINT(performance-unnecessary-value-param)
-        : constructed_from(constructed_from_foo) {}
-    explicit for_3204_bar(std::function<void(json)> /*unused*/) noexcept // NOLINT(performance-unnecessary-value-param)
-        : constructed_from(constructed_from_json) {}
-
-    constructed_from_t constructed_from = constructed_from_none;
-};
-
-/////////////////////////////////////////////////////////////////////
-// for #3333
-/////////////////////////////////////////////////////////////////////
-
-struct for_3333 final
-{
-    for_3333(int x_ = 0, int y_ = 0) : x(x_), y(y_) {}
-
-    template <class T>
-    for_3333(const T& /*unused*/)
-    {
-        CHECK(false);
-    }
-
-    int x = 0;
-    int y = 0;
-};
-
-template <>
-inline for_3333::for_3333(const json& j)
-    : for_3333(j.value("x", 0), j.value("y", 0))
-{}
-
-/////////////////////////////////////////////////////////////////////
-// for #3810
-/////////////////////////////////////////////////////////////////////
-
-struct Example_3810
-{
-    int bla{};
-
-    Example_3810() = default;
-};
-
-NLOHMANN_DEFINE_TYPE_NON_INTRUSIVE(Example_3810, bla) // NOLINT(misc-use-internal-linkage)
-
-/////////////////////////////////////////////////////////////////////
-// for #4740
-/////////////////////////////////////////////////////////////////////
-
-#ifdef JSON_HAS_CPP_17
-struct Example_4740
-{
-    std::optional<std::string> host = std::nullopt;
-    std::optional<int> port = std::nullopt;
-    NLOHMANN_DEFINE_TYPE_INTRUSIVE_WITH_DEFAULT(Example_4740, host, port)
-};
-#endif
-
 TEST_CASE("regression tests 2")
 {
     SECTION("issue #1001 - Fix memory leak during parser callback")
@@ -959,575 +756,6 @@ TEST_CASE("regression tests 2")
         CHECK(j == k);
     }
 
-#if JSON_HAS_FILESYSTEM || JSON_HAS_EXPERIMENTAL_FILESYSTEM
-    // JSON_HAS_CPP_17 (do not remove; see note at top of file)
-    SECTION("issue #3070 - Version 3.10.3 breaks backward-compatibility with 3.10.2 ")
-    {
-        nlohmann::detail::std_fs::path text_path("/tmp/text.txt");
-        const json j(text_path);
-
-        const auto j_path = j.get<nlohmann::detail::std_fs::path>();
-        CHECK(j_path == text_path);
-
-#if DOCTEST_CLANG || DOCTEST_GCC >= DOCTEST_COMPILER(8, 4, 0)
-        // only known to work on Clang and GCC >=8.4
-        CHECK_THROWS_WITH_AS(nlohmann::detail::std_fs::path(json(1)), "[json.exception.type_error.302] type must be string, but is number", json::type_error);
-#endif
-    }
-#endif
-
-    SECTION("issue #3077 - explicit constructor with default does not compile")
-    {
-        json j;
-        j[0]["value"] = true;
-        std::vector<FooBar> foo;
-        j.get_to(foo);
-    }
-
-    SECTION("issue #3108 - ordered_json doesn't support range based erase")
-    {
-        ordered_json j = {1, 2, 2, 4};
-
-        auto last = std::unique(j.begin(), j.end());
-        j.erase(last, j.end());
-
-        CHECK(j.dump() == "[1,2,4]");
-
-        j.erase(std::remove_if(j.begin(), j.end(), [](const ordered_json & val)
-        {
-            return val == 2;
-        }), j.end());
-
-        CHECK(j.dump() == "[1,4]");
-    }
-
-    SECTION("issue #3343 - json and ordered_json are not interchangeable")
-    {
-        json::object_t jobj({ { "product", "one" } });
-        ordered_json::object_t ojobj({{"product", "one"}});
-
-        auto jit = jobj.begin();
-        auto ojit = ojobj.begin();
-
-        CHECK(jit->first == ojit->first);
-        CHECK(jit->second.get<std::string>() == ojit->second.get<std::string>());
-    }
-
-    SECTION("issue #3171 - if class is_constructible from std::string wrong from_json overload is being selected, compilation failed")
-    {
-        const json j{{ "str", "value"}};
-
-        // failed with: error: no match for ‘operator=’ (operand types are ‘for_3171_derived’ and ‘const nlohmann::basic_json<>::string_t’
-        //                                               {aka ‘const std::__cxx11::basic_string<char>’})
-        //                  s = *j.template get_ptr<const typename BasicJsonType::string_t*>();
-        auto td = j.get<for_3171_derived>();
-
-        CHECK(td.str == "value");
-    }
-
-#ifdef JSON_HAS_CPP_20
-    SECTION("issue #3312 - Parse to custom class from unordered_json breaks on G++11.2.0 with C++20")
-    {
-        // see test for #3171
-        const ordered_json j = {{"name", "class"}};
-        for_3312 obj{};
-
-        j.get_to(obj);
-
-        CHECK(obj.name == "class");
-    }
-#endif
-
-#if defined(JSON_HAS_CPP_17) && JSON_USE_IMPLICIT_CONVERSIONS
-    SECTION("issue #3428 - Error occurred when converting nlohmann::json to std::any")
-    {
-        const json j;
-        const std::any a1 = j;
-        std::any&& a2 = j;
-
-        CHECK(a1.type() == typeid(j));
-        CHECK(a2.type() == typeid(j));
-    }
-#endif
-
-    SECTION("issue #3204 - ambiguous regression")
-    {
-        const for_3204_bar bar_from_foo([](for_3204_foo) noexcept {}); // NOLINT(performance-unnecessary-value-param)
-        const for_3204_bar bar_from_json([](json) noexcept {}); // NOLINT(performance-unnecessary-value-param)
-
-        CHECK(bar_from_foo.constructed_from == for_3204_bar::constructed_from_foo);
-        CHECK(bar_from_json.constructed_from == for_3204_bar::constructed_from_json);
-    }
-
-    SECTION("issue #3333 - Ambiguous conversion from nlohmann::basic_json<> to custom class")
-    {
-        const json j
-        {
-            {"x", 1},
-            {"y", 2}
-        };
-        const for_3333 p = j;
-
-        CHECK(p.x == 1);
-        CHECK(p.y == 2);
-    }
-
-    SECTION("issue #3810 - ordered_json doesn't support construction from C array of custom type")
-    {
-        Example_3810 states[45]; // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
-
-        // fix "not used" warning
-        states[0].bla = 1;
-
-        const auto* const expected = R"([{"bla":1},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0}])";
-
-        // This works:
-        nlohmann::json j;
-        j["test"] = states;
-        CHECK(j["test"].dump() == expected);
-
-        // This doesn't compile:
-        nlohmann::ordered_json oj;
-        oj["test"] = states;
-        CHECK(oj["test"].dump() == expected);
-    }
-
-#ifdef JSON_HAS_CPP_17
-    SECTION("issue #4740 - build issue with std::optional")
-    {
-        const auto t1 = Example_4740();
-        const auto j1 = nlohmann::json(t1);
-        CHECK(j1.dump() == "{\"host\":null,\"port\":null}");
-        const auto t2 = j1.get<Example_4740>();
-        CHECK(!t2.host.has_value());
-        CHECK(!t2.port.has_value());
-
-        // improve coverage
-        auto t3 = Example_4740();
-        t3.port = 80;
-        t3.host = "example.com";
-        const auto j2 = nlohmann::json(t3);
-        CHECK(j2.dump() == "{\"host\":\"example.com\",\"port\":80}");
-        const auto t4 = j2.get<Example_4740>();
-        CHECK(t4.host.has_value());
-        CHECK(t4.port.has_value());
-    }
-#endif
-
-#if !defined(_MSVC_LANG)
-    // MSVC returns garbage on invalid enum values, so this test is excluded
-    // there.
-    SECTION("issue #4762 - json exception 302 with unhelpful explanation : type must be number, but is number")
-    {
-        // In #4762, the main issue was that a json object with an invalid type
-        // returned "number" as type_name(), because this was the default case.
-        // This test makes sure we now return "invalid" instead.
-        json j;
-        j.m_data.m_type = static_cast<json::value_t>(100); // NOLINT(clang-analyzer-optin.core.EnumCastOutOfRange)
-        CHECK(j.type_name() == "invalid");
-    }
-#endif
-
-#ifdef JSON_HAS_CPP_17
-    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 = json_4804::from_cbor(data);
-        CHECK((decoded == json_4804::array()));
-    }
-
-    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 json_4804 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 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 = json_4804::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});
-    }
-
-    SECTION("issue #5046 - implicit conversion of return json to std::optional no longer implicit")
-    {
-        const json jval{};
-        auto GetValue = [](const json & valRoot) -> std::optional<json>
-        {
-            if (valRoot.contains("default"))
-            {
-                return valRoot.at("default");
-            }
-            return std::nullopt;
-        };
-        auto result = GetValue(jval);
-        CHECK(!result.has_value());
-    }
-#endif
-
-#if JSON_HAS_RANGES == 1
-    SECTION("issue #4440 - assert when using std::views::filter and GCC 10")
-    {
-        auto noOpFilter = std::views::filter([](auto&&) noexcept
-        {
-            return true;
-        });
-        json j = {1, 2, 3};
-        auto filtered = j | noOpFilter;
-        CHECK(*filtered.begin() == 1);
-    }
-#endif
-
-#if JSON_HAS_RANGES && !defined(__MINGW32__)
-    SECTION("issue #4916 - constructing array from C++20 ranges view does not work")
-    {
-        std::vector<int> nums{1, 2, 37, 42, 21};
-        auto filteredNums = nums | std::views::filter([](int i)
-        {
-            return i > 10;
-        });
-        json const j(filteredNums);
-        CHECK(j.type() == json::value_t::array);
-        CHECK(j == json({37, 42, 21}));
-    }
-#endif
-
-    // owning_view is not available in libstdc++ < 12
-#if JSON_HAS_RANGES && !defined(__MINGW32__) && !(defined(__GLIBCXX__) && _GLIBCXX_RELEASE < 12)
-    SECTION("issue #4916 - constructing array from prvalue C++20 ranges view (owning_view)")
-    {
-        json const j(std::vector<int> {1, 2, 37, 42, 21} | std::views::filter([](int i)
-        {
-            return i > 10;
-        }));
-        CHECK(j.type() == json::value_t::array);
-        CHECK(j == json({37, 42, 21}));
-    }
-#endif
-
-#if JSON_HAS_RANGES && !defined(__MINGW32__)
-    SECTION("issue #4916 - constructing array from C++20 transform view (prvalue elements)")
-    {
-        std::vector<int> nums{1, 2, 3};
-        auto t = nums | std::views::transform([](int i) noexcept
-        {
-            return i * 2;
-        });
-        json const j(t);
-        CHECK(j.type() == json::value_t::array);
-        CHECK(j == json({2, 4, 6}));
-    }
-#endif
-}
-
-TEST_CASE_TEMPLATE("issue #4798 - nlohmann::json::to_msgpack() encode float NaN as double", T, double, float) // NOLINT(readability-math-missing-parentheses, bugprone-throwing-static-initialization)
-{
-    // With issue #4798, we encode NaN, infinity, and -infinity as float instead
-    // of double to allow for smaller encodings.
-    const json jx = std::numeric_limits<T>::quiet_NaN();
-    const json jy = std::numeric_limits<T>::infinity();
-    const json jz = -std::numeric_limits<T>::infinity();
-
-    /////////////////////////////////////////////////////////////////////////
-    // MessagePack
-    /////////////////////////////////////////////////////////////////////////
-
-    // expected MessagePack values
-    const std::vector<std::uint8_t> msgpack_x = {{0xCA, 0x7F, 0xC0, 0x00, 0x00}};
-    const std::vector<std::uint8_t> msgpack_y = {{0xCA, 0x7F, 0x80, 0x00, 0x00}};
-    const std::vector<std::uint8_t> msgpack_z = {{0xCA, 0xFF, 0x80, 0x00, 0x00}};
-
-    CHECK(json::to_msgpack(jx) == msgpack_x);
-    CHECK(json::to_msgpack(jy) == msgpack_y);
-    CHECK(json::to_msgpack(jz) == msgpack_z);
-
-    CHECK(std::isnan(json::from_msgpack(msgpack_x).get<T>()));
-    CHECK(json::from_msgpack(msgpack_y).get<T>() == std::numeric_limits<T>::infinity());
-    CHECK(json::from_msgpack(msgpack_z).get<T>() == -std::numeric_limits<T>::infinity());
-
-    // Make sure the other MessagePakc encodings for NaN, infinity, and
-    // -infinity are still supported.
-    const std::vector<std::uint8_t> msgpack_x_2 = {{0xCB, 0x7F, 0xF8, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}};
-    const std::vector<std::uint8_t> msgpack_y_2 = {{0xCB, 0x7F, 0xF0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}};
-    const std::vector<std::uint8_t> msgpack_z_2 = {{0xCB, 0xFF, 0xF0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}};
-    CHECK(std::isnan(json::from_msgpack(msgpack_x_2).get<T>()));
-    CHECK(json::from_msgpack(msgpack_y_2).get<T>() == std::numeric_limits<T>::infinity());
-    CHECK(json::from_msgpack(msgpack_z_2).get<T>() == -std::numeric_limits<T>::infinity());
-
-    /////////////////////////////////////////////////////////////////////////
-    // CBOR
-    /////////////////////////////////////////////////////////////////////////
-
-    // expected CBOR values
-    const std::vector<std::uint8_t> cbor_x = {{0xF9, 0x7E, 0x00}};
-    const std::vector<std::uint8_t> cbor_y = {{0xF9, 0x7C, 0x00}};
-    const std::vector<std::uint8_t> cbor_z = {{0xF9, 0xfC, 0x00}};
-
-    CHECK(json::to_cbor(jx) == cbor_x);
-    CHECK(json::to_cbor(jy) == cbor_y);
-    CHECK(json::to_cbor(jz) == cbor_z);
-
-    CHECK(std::isnan(json::from_cbor(cbor_x).get<T>()));
-    CHECK(json::from_cbor(cbor_y).get<T>() == std::numeric_limits<T>::infinity());
-    CHECK(json::from_cbor(cbor_z).get<T>() == -std::numeric_limits<T>::infinity());
-
-    // Make sure the other CBOR encodings for NaN, infinity, and -infinity are
-    // still supported.
-    const std::vector<std::uint8_t> cbor_x_2 = {{0xFA, 0x7F, 0xC0, 0x00, 0x00}};
-    const std::vector<std::uint8_t> cbor_y_2 = {{0xFA, 0x7F, 0x80, 0x00, 0x00}};
-    const std::vector<std::uint8_t> cbor_z_2 = {{0xFA, 0xFF, 0x80, 0x00, 0x00}};
-    const std::vector<std::uint8_t> cbor_x_3 = {{0xFB, 0x7F, 0xF8, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}};
-    const std::vector<std::uint8_t> cbor_y_3 = {{0xFB, 0x7F, 0xF0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}};
-    const std::vector<std::uint8_t> cbor_z_3 = {{0xFB, 0xFF, 0xF0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}};
-    CHECK(std::isnan(json::from_cbor(cbor_x_2).get<T>()));
-    CHECK(json::from_cbor(cbor_y_2).get<T>() == std::numeric_limits<T>::infinity());
-    CHECK(json::from_cbor(cbor_z_2).get<T>() == -std::numeric_limits<T>::infinity());
-    CHECK(std::isnan(json::from_cbor(cbor_x_3).get<T>()));
-    CHECK(json::from_cbor(cbor_y_3).get<T>() == std::numeric_limits<T>::infinity());
-    CHECK(json::from_cbor(cbor_z_3).get<T>() == -std::numeric_limits<T>::infinity());
-}
-
-TEST_CASE("regression test #5074 - portable workaround for single-element brace init")
-{
-    json const j_obj = {{"key", "value"}};
-
-    json const j = json::array({j_obj});
-    CHECK(j.is_array());
-    CHECK(j.size() == 1);
-    CHECK(j[0] == j_obj);
-}
-
-#if defined(JSON_BRACE_INIT_COPY_SEMANTICS) && (JSON_BRACE_INIT_COPY_SEMANTICS == 1)
-TEST_CASE("regression test #5074 - single-element brace init with JSON_BRACE_INIT_COPY_SEMANTICS")
-{
-    // with JSON_BRACE_INIT_COPY_SEMANTICS: single-element brace init copies/moves
-    json const j_obj = {{"key", "value"}, {"num", 42}};
-    json const j_arr = {1, 2, 3};
-
-    // object: brace init copies instead of wrapping
-    json const j1{j_obj};
-    CHECK(j1.is_object());
-    CHECK(j1 == j_obj);
-
-    // array: brace init copies instead of wrapping
-    json const j2{j_arr};
-    CHECK(j2.is_array());
-    CHECK(j2.size() == 3);
-    CHECK(j2 == j_arr);
-
-    // primitives still work as initializer lists
-    json const j3{true};
-    CHECK(j3.is_boolean());
-
-    json const j4{42};
-    CHECK(j4.is_number_integer());
-}
-#endif
-
-struct Example_5122
-{
-    float b = 2;
-    nlohmann::ordered_map<std::string, std::string> c{}; // NOLINT(readability-redundant-member-init): needed for GCC -Weffc++
-    int a = 1;
-    NLOHMANN_DEFINE_TYPE_INTRUSIVE_WITH_DEFAULT(Example_5122, b, c, a)
-};
-
-TEST_CASE("regression test #5122 - from_json into types holding nlohmann::ordered_map")
-{
-    Example_5122 src;
-    src.c.emplace("first", "1");
-    src.c.emplace("second", "2");
-
-    ordered_json const j = src;
-    Example_5122 const dst = j.get<Example_5122>();
-
-    CHECK(dst.b == src.b);
-    CHECK(dst.a == src.a);
-    REQUIRE(dst.c.size() == src.c.size());
-    auto src_it = src.c.begin();
-    auto dst_it = dst.c.begin();
-    for (; src_it != src.c.end(); ++src_it, ++dst_it)
-    {
-        CHECK(dst_it->first == src_it->first);
-        CHECK(dst_it->second == src_it->second);
-    }
-}
-
-// -Wself-assign-overloaded was introduced in Clang 7. Gate the pragma on
-// __has_warning so older Clang versions do not error with "unknown warning
-// group". The __has_warning check has to stay inside the __clang__ branch
-// because GCC does not provide it and would tokenize-error on the argument.
-#if defined(__clang__) && defined(__has_warning)
-    #if __has_warning("-Wself-assign-overloaded")
-        DOCTEST_CLANG_SUPPRESS_WARNING_PUSH
-        DOCTEST_CLANG_SUPPRESS_WARNING("-Wself-assign-overloaded")
-    #endif
-#endif
-
-TEST_CASE("regression test #5122 - nlohmann::ordered_map copy-assignment is self-assignment safe")
-{
-    nlohmann::ordered_map<std::string, std::string> m;
-    m.emplace("first", "1");
-    m.emplace("second", "2");
-
-    // Insertion order is preserved by ordered_map, so we can check it directly.
-    m = m;
-
-    REQUIRE(m.size() == 2);
-    auto it = m.begin();
-    CHECK(it->first == "first");
-    CHECK(it->second == "1");
-    ++it;
-    CHECK(it->first == "second");
-    CHECK(it->second == "2");
-}
-
-#if defined(__clang__) && defined(__has_warning)
-    #if __has_warning("-Wself-assign-overloaded")
-        DOCTEST_CLANG_SUPPRESS_WARNING_POP
-    #endif
-#endif
-
-TEST_CASE("regression test #5122 - nlohmann::ordered_map move-assignment transfers contents")
-{
-    nlohmann::ordered_map<std::string, std::string> src;
-    src.emplace("first", "1");
-    src.emplace("second", "2");
-
-    nlohmann::ordered_map<std::string, std::string> dst;
-    dst.emplace("stale", "x");
-    dst = std::move(src);
-
-    REQUIRE(dst.size() == 2);
-    auto it = dst.begin();
-    CHECK(it->first == "first");
-    CHECK(it->second == "1");
-    ++it;
-    CHECK(it->first == "second");
-    CHECK(it->second == "2");
-
-    // Re-assigning into the moved-from object must leave it in a usable state.
-    src = nlohmann::ordered_map<std::string, std::string> {};
-    src.emplace("after-move", "3");
-    REQUIRE(src.size() == 1);
-    CHECK(src.begin()->first == "after-move");
-}
-
-// Stand-in for a third-party library (e.g., Eigen as of 3.4, which added
-// STL-compatible begin()/end() to its vector types), living in its own
-// namespace with its own to_json overload for its vector type.
-namespace issue_4320_eigen
-{
-// "array-compatible" from the library's point of view (it has begin()/end()),
-// but for which this (fake) third-party namespace provides its own to_json.
-struct vector3
-{
-    double v[3]; // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays,cppcoreguidelines-use-default-member-init,modernize-use-default-member-init)
-    vector3(double x, double y, double z) : v{x, y, z} {} // NOLINT(hicpp-member-init,cppcoreguidelines-pro-type-member-init)
-    double x() const
-    {
-        return v[0];
-    }
-    double y() const
-    {
-        return v[1];
-    }
-    double z() const
-    {
-        return v[2];
-    }
-    double* begin()
-    {
-        return v;
-    }
-    double* end()
-    {
-        return v + 3;
-    }
-    const double* begin() const
-    {
-        return v;
-    }
-    const double* end() const
-    {
-        return v + 3;
-    }
-};
-
-inline void to_json(json& j, const vector3& v) // NOLINT(misc-use-internal-linkage)
-{
-    j = {{"x", v.x()}, {"y", v.y()}, {"z", v.z()}};
-}
-} // namespace issue_4320_eigen
-
-// The user's own namespace, using the (fake) Eigen type as an implementation
-// detail behind a payload type that has nothing to do with vectors/arrays.
-namespace issue_4320
-{
-// Publicly derives from issue_4320_eigen::vector3 but does *not* define its
-// own to_json - it is only ever used as a temporary to reach the base
-// class's to_json via ADL.
-struct vector3_wrapper : issue_4320_eigen::vector3
-{
-    using issue_4320_eigen::vector3::vector3;
-};
-
-struct payload
-{
-    double x, y, z;
-};
-
-inline vector3_wrapper to_eigen(const payload& p) // NOLINT(misc-use-internal-linkage)
-{
-    return {p.x, p.y, p.z};
-}
-
-inline void to_json(json& j, const payload& p) // NOLINT(misc-use-internal-linkage)
-{
-    // Unqualified call, passing a *derived* vector3_wrapper: relies on ADL
-    // finding issue_4320_eigen::to_json(json&, const vector3&) through the
-    // vector3 base class, via a derived-to-base conversion. Must NOT resolve
-    // to the library's own generic array-compatible to_json (an exact-match
-    // template for vector3_wrapper, since it also has begin()/end()), which
-    // would serialize this as [x, y, z] instead of {"x":x, "y":y, "z":z}.
-    to_json(j, to_eigen(p));
-}
-} // namespace issue_4320
-
-TEST_CASE("issue #4320 - custom base class must not leak nlohmann::detail into ADL")
-{
-    // Before the fix, basic_json unconditionally derived from a type living in
-    // nlohmann::detail (json_default_base), which made nlohmann::detail an
-    // associated namespace of every basic_json for ADL purposes. That leaked
-    // the library's internal generic-array to_json overload into unqualified
-    // to_json() calls made from user code, silently bypassing user-defined
-    // to_json overloads reached via a derived-to-base conversion.
-    const issue_4320::payload p{1.0, 2.0, 3.0};
-
-    json j;
-    to_json(j, p);
-    CHECK(j == json({{"x", 1.0}, {"y", 2.0}, {"z", 3.0}}));
 }
 
 DOCTEST_CLANG_SUPPRESS_WARNING_POP

tests/src/unit-regression3.cpp

@@ -0,0 +1,899 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  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
+
+// cmake/test.cmake selects the C++ standard versions with which to build a
+// unit test based on the presence of JSON_HAS_CPP_<VERSION> macros.
+// When using macros that are only defined for particular versions of the standard
+// (e.g., JSON_HAS_FILESYSTEM for C++17 and up), please mention the corresponding
+// 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"
+
+// for some reason including this after the json header leads to linker errors with VS 2017...
+#include <locale>
+
+#define JSON_TESTS_PRIVATE
+#include <nlohmann/json.hpp>
+using json = nlohmann::json;
+using ordered_json = nlohmann::ordered_json;
+#ifdef JSON_TEST_NO_GLOBAL_UDLS
+    using namespace nlohmann::literals; // NOLINT(google-build-using-namespace)
+#endif
+
+#include <cstdio>
+#include <list>
+#include <type_traits>
+#include <utility>
+
+#ifdef JSON_HAS_CPP_17
+    #include <any>
+    #include <variant>
+#endif
+
+#ifdef JSON_HAS_CPP_17
+    #if __has_include(<optional>)
+        #include <optional>
+    #elif __has_include(<experimental/optional>)
+    #endif
+
+    /////////////////////////////////////////////////////////////////////
+    // for #4804
+    /////////////////////////////////////////////////////////////////////
+    using json_4804 = nlohmann::basic_json<std::map,        // ObjectType
+    std::vector,     // ArrayType
+    std::string,     // StringType
+    bool,            // BooleanType
+    std::int64_t,    // NumberIntegerType
+    std::uint64_t,   // NumberUnsignedType
+    double,          // NumberFloatType
+    std::allocator,  // AllocatorType
+    nlohmann::adl_serializer,  // JSONSerializer
+    std::vector<std::byte>,    // BinaryType
+    void                       // CustomBaseClass
+    >;
+#endif
+
+#ifdef JSON_HAS_CPP_20
+    #if __has_include(<span>)
+        #include <span>
+    #endif
+#endif
+
+/////////////////////////////////////////////////////////////////////
+// for #4825 - explicitly instantiating basic_json must compile; this
+// forces instantiation of binary_writer::write_bjdata_ndarray, whose
+// static_cast<string_t> was ambiguous under explicit instantiation on
+// C++17. Merely compiling this translation unit is the regression test.
+/////////////////////////////////////////////////////////////////////
+template class nlohmann::basic_json<>;
+
+/////////////////////////////////////////////////////////////////////
+// for #4440
+/////////////////////////////////////////////////////////////////////
+#if JSON_HAS_RANGES == 1
+    #include <ranges>
+#endif
+
+// NLOHMANN_JSON_SERIALIZE_ENUM uses a static std::pair
+DOCTEST_CLANG_SUPPRESS_WARNING_PUSH
+DOCTEST_CLANG_SUPPRESS_WARNING("-Wexit-time-destructors")
+/////////////////////////////////////////////////////////////////////
+// for #3077
+/////////////////////////////////////////////////////////////////////
+
+class FooAlloc
+{};
+
+class Foo
+{
+  public:
+    explicit Foo(const FooAlloc& /* unused */ = FooAlloc()) {}
+
+    bool value = false;
+};
+
+class FooBar
+{
+  public:
+    Foo foo{}; // NOLINT(readability-redundant-member-init)
+};
+
+inline void from_json(const nlohmann::json& j, FooBar& fb) // NOLINT(misc-use-internal-linkage)
+{
+    j.at("value").get_to(fb.foo.value);
+}
+
+/////////////////////////////////////////////////////////////////////
+// for #3171
+/////////////////////////////////////////////////////////////////////
+
+struct for_3171_base // NOLINT(cppcoreguidelines-special-member-functions)
+{
+    for_3171_base(const std::string& /*unused*/ = {}) {}
+    virtual ~for_3171_base();
+
+    for_3171_base(const for_3171_base& other) // NOLINT(hicpp-use-equals-default,modernize-use-equals-default)
+        : str(other.str)
+    {}
+
+    for_3171_base& operator=(const for_3171_base& other)
+    {
+        if (this != &other)
+        {
+            str = other.str;
+        }
+        return *this;
+    }
+
+    for_3171_base(for_3171_base&& other) noexcept
+        : str(std::move(other.str))
+    {}
+
+    for_3171_base& operator=(for_3171_base&& other) noexcept
+    {
+        if (this != &other)
+        {
+            str = std::move(other.str);
+        }
+        return *this;
+    }
+
+    virtual void _from_json(const json& j)
+    {
+        j.at("str").get_to(str);
+    }
+
+    std::string str{}; // NOLINT(readability-redundant-member-init)
+};
+
+for_3171_base::~for_3171_base() = default;
+
+struct for_3171_derived : public for_3171_base
+{
+    for_3171_derived() = default;
+    ~for_3171_derived() override;
+    explicit for_3171_derived(const std::string& /*unused*/) { }
+
+    for_3171_derived(const for_3171_derived& other) // NOLINT(hicpp-use-equals-default,modernize-use-equals-default)
+        : for_3171_base(other)
+    {}
+
+    for_3171_derived& operator=(const for_3171_derived& other)
+    {
+        if (this != &other)
+        {
+            for_3171_base::operator=(other); // Call base class assignment operator
+        }
+        return *this;
+    }
+
+    for_3171_derived(for_3171_derived&& other) noexcept
+        : for_3171_base(std::move(other))
+    {}
+
+    for_3171_derived& operator=(for_3171_derived&& other) noexcept
+    {
+        if (this != &other)
+        {
+            for_3171_base::operator=(std::move(other)); // Call base class move assignment operator
+        }
+        return *this;
+    }
+};
+
+for_3171_derived::~for_3171_derived() = default;
+
+inline void from_json(const json& j, for_3171_base& tb) // NOLINT(misc-use-internal-linkage)
+{
+    tb._from_json(j);
+}
+
+/////////////////////////////////////////////////////////////////////
+// for #3312
+/////////////////////////////////////////////////////////////////////
+
+#ifdef JSON_HAS_CPP_20
+struct for_3312
+{
+    std::string name;
+};
+
+inline void from_json(const json& j, for_3312& obj) // NOLINT(misc-use-internal-linkage)
+{
+    j.at("name").get_to(obj.name);
+}
+#endif
+
+/////////////////////////////////////////////////////////////////////
+// for #3204
+/////////////////////////////////////////////////////////////////////
+
+struct for_3204_foo
+{
+    for_3204_foo() = default;
+    explicit for_3204_foo(std::string /*unused*/) {} // NOLINT(performance-unnecessary-value-param)
+};
+
+struct for_3204_bar
+{
+    enum constructed_from_t // NOLINT(cppcoreguidelines-use-enum-class)
+    {
+        constructed_from_none = 0,
+        constructed_from_foo = 1,
+        constructed_from_json = 2
+    };
+
+    explicit for_3204_bar(std::function<void(for_3204_foo)> /*unused*/) noexcept // NOLINT(performance-unnecessary-value-param)
+        : constructed_from(constructed_from_foo) {}
+    explicit for_3204_bar(std::function<void(json)> /*unused*/) noexcept // NOLINT(performance-unnecessary-value-param)
+        : constructed_from(constructed_from_json) {}
+
+    constructed_from_t constructed_from = constructed_from_none;
+};
+
+/////////////////////////////////////////////////////////////////////
+// for #3333
+/////////////////////////////////////////////////////////////////////
+
+struct for_3333 final
+{
+    for_3333(int x_ = 0, int y_ = 0) : x(x_), y(y_) {}
+
+    template <class T>
+    for_3333(const T& /*unused*/)
+    {
+        CHECK(false);
+    }
+
+    int x = 0;
+    int y = 0;
+};
+
+template <>
+inline for_3333::for_3333(const json& j)
+    : for_3333(j.value("x", 0), j.value("y", 0))
+{}
+
+/////////////////////////////////////////////////////////////////////
+// for #3810
+/////////////////////////////////////////////////////////////////////
+
+struct Example_3810
+{
+    int bla{};
+
+    Example_3810() = default;
+};
+
+NLOHMANN_DEFINE_TYPE_NON_INTRUSIVE(Example_3810, bla) // NOLINT(misc-use-internal-linkage)
+
+/////////////////////////////////////////////////////////////////////
+// for #4740
+/////////////////////////////////////////////////////////////////////
+
+#ifdef JSON_HAS_CPP_17
+struct Example_4740
+{
+    std::optional<std::string> host = std::nullopt;
+    std::optional<int> port = std::nullopt;
+    NLOHMANN_DEFINE_TYPE_INTRUSIVE_WITH_DEFAULT(Example_4740, host, port)
+};
+#endif
+
+TEST_CASE("regression tests 3")
+{
+#if JSON_HAS_FILESYSTEM || JSON_HAS_EXPERIMENTAL_FILESYSTEM
+    // JSON_HAS_CPP_17 (do not remove; see note at top of file)
+    SECTION("issue #3070 - Version 3.10.3 breaks backward-compatibility with 3.10.2 ")
+    {
+        nlohmann::detail::std_fs::path text_path("/tmp/text.txt");
+        const json j(text_path);
+
+        const auto j_path = j.get<nlohmann::detail::std_fs::path>();
+        CHECK(j_path == text_path);
+
+#if DOCTEST_CLANG || DOCTEST_GCC >= DOCTEST_COMPILER(8, 4, 0)
+        // only known to work on Clang and GCC >=8.4
+        CHECK_THROWS_WITH_AS(nlohmann::detail::std_fs::path(json(1)), "[json.exception.type_error.302] type must be string, but is number", json::type_error);
+#endif
+    }
+#endif
+
+    SECTION("issue #3077 - explicit constructor with default does not compile")
+    {
+        json j;
+        j[0]["value"] = true;
+        std::vector<FooBar> foo;
+        j.get_to(foo);
+    }
+
+    SECTION("issue #3108 - ordered_json doesn't support range based erase")
+    {
+        ordered_json j = {1, 2, 2, 4};
+
+        auto last = std::unique(j.begin(), j.end());
+        j.erase(last, j.end());
+
+        CHECK(j.dump() == "[1,2,4]");
+
+        j.erase(std::remove_if(j.begin(), j.end(), [](const ordered_json & val)
+        {
+            return val == 2;
+        }), j.end());
+
+        CHECK(j.dump() == "[1,4]");
+    }
+
+    SECTION("issue #3343 - json and ordered_json are not interchangeable")
+    {
+        json::object_t jobj({ { "product", "one" } });
+        ordered_json::object_t ojobj({{"product", "one"}});
+
+        auto jit = jobj.begin();
+        auto ojit = ojobj.begin();
+
+        CHECK(jit->first == ojit->first);
+        CHECK(jit->second.get<std::string>() == ojit->second.get<std::string>());
+    }
+
+    SECTION("issue #3171 - if class is_constructible from std::string wrong from_json overload is being selected, compilation failed")
+    {
+        const json j{{ "str", "value"}};
+
+        // failed with: error: no match for ‘operator=’ (operand types are ‘for_3171_derived’ and ‘const nlohmann::basic_json<>::string_t’
+        //                                               {aka ‘const std::__cxx11::basic_string<char>’})
+        //                  s = *j.template get_ptr<const typename BasicJsonType::string_t*>();
+        auto td = j.get<for_3171_derived>();
+
+        CHECK(td.str == "value");
+    }
+
+#ifdef JSON_HAS_CPP_20
+    SECTION("issue #3312 - Parse to custom class from unordered_json breaks on G++11.2.0 with C++20")
+    {
+        // see test for #3171
+        const ordered_json j = {{"name", "class"}};
+        for_3312 obj{};
+
+        j.get_to(obj);
+
+        CHECK(obj.name == "class");
+    }
+#endif
+
+#if defined(JSON_HAS_CPP_17) && JSON_USE_IMPLICIT_CONVERSIONS
+    SECTION("issue #3428 - Error occurred when converting nlohmann::json to std::any")
+    {
+        const json j;
+        const std::any a1 = j;
+        std::any&& a2 = j;
+
+        CHECK(a1.type() == typeid(j));
+        CHECK(a2.type() == typeid(j));
+    }
+#endif
+
+    SECTION("issue #3204 - ambiguous regression")
+    {
+        const for_3204_bar bar_from_foo([](for_3204_foo) noexcept {}); // NOLINT(performance-unnecessary-value-param)
+        const for_3204_bar bar_from_json([](json) noexcept {}); // NOLINT(performance-unnecessary-value-param)
+
+        CHECK(bar_from_foo.constructed_from == for_3204_bar::constructed_from_foo);
+        CHECK(bar_from_json.constructed_from == for_3204_bar::constructed_from_json);
+    }
+
+    SECTION("issue #3333 - Ambiguous conversion from nlohmann::basic_json<> to custom class")
+    {
+        const json j
+        {
+            {"x", 1},
+            {"y", 2}
+        };
+        const for_3333 p = j;
+
+        CHECK(p.x == 1);
+        CHECK(p.y == 2);
+    }
+
+    SECTION("issue #3810 - ordered_json doesn't support construction from C array of custom type")
+    {
+        Example_3810 states[45]; // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+
+        // fix "not used" warning
+        states[0].bla = 1;
+
+        const auto* const expected = R"([{"bla":1},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0},{"bla":0}])";
+
+        // This works:
+        nlohmann::json j;
+        j["test"] = states;
+        CHECK(j["test"].dump() == expected);
+
+        // This doesn't compile:
+        nlohmann::ordered_json oj;
+        oj["test"] = states;
+        CHECK(oj["test"].dump() == expected);
+    }
+
+#ifdef JSON_HAS_CPP_17
+    SECTION("issue #4740 - build issue with std::optional")
+    {
+        const auto t1 = Example_4740();
+        const auto j1 = nlohmann::json(t1);
+        CHECK(j1.dump() == "{\"host\":null,\"port\":null}");
+        const auto t2 = j1.get<Example_4740>();
+        CHECK(!t2.host.has_value());
+        CHECK(!t2.port.has_value());
+
+        // improve coverage
+        auto t3 = Example_4740();
+        t3.port = 80;
+        t3.host = "example.com";
+        const auto j2 = nlohmann::json(t3);
+        CHECK(j2.dump() == "{\"host\":\"example.com\",\"port\":80}");
+        const auto t4 = j2.get<Example_4740>();
+        CHECK(t4.host.has_value());
+        CHECK(t4.port.has_value());
+    }
+#endif
+
+#if !defined(_MSVC_LANG)
+    // MSVC returns garbage on invalid enum values, so this test is excluded
+    // there.
+    SECTION("issue #4762 - json exception 302 with unhelpful explanation : type must be number, but is number")
+    {
+        // In #4762, the main issue was that a json object with an invalid type
+        // returned "number" as type_name(), because this was the default case.
+        // This test makes sure we now return "invalid" instead.
+        json j;
+        j.m_data.m_type = static_cast<json::value_t>(100); // NOLINT(clang-analyzer-optin.core.EnumCastOutOfRange)
+        CHECK(j.type_name() == "invalid");
+    }
+#endif
+
+#ifdef JSON_HAS_CPP_17
+    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 = json_4804::from_cbor(data);
+        CHECK((decoded == json_4804::array()));
+    }
+
+    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 json_4804 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 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 = json_4804::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});
+    }
+
+    SECTION("issue #5046 - implicit conversion of return json to std::optional no longer implicit")
+    {
+        const json jval{};
+        auto GetValue = [](const json & valRoot) -> std::optional<json>
+        {
+            if (valRoot.contains("default"))
+            {
+                return valRoot.at("default");
+            }
+            return std::nullopt;
+        };
+        auto result = GetValue(jval);
+        CHECK(!result.has_value());
+    }
+#endif
+
+#if JSON_HAS_RANGES == 1
+    SECTION("issue #4440 - assert when using std::views::filter and GCC 10")
+    {
+        auto noOpFilter = std::views::filter([](auto&&) noexcept
+        {
+            return true;
+        });
+        json j = {1, 2, 3};
+        auto filtered = j | noOpFilter;
+        CHECK(*filtered.begin() == 1);
+    }
+#endif
+
+#if JSON_HAS_RANGES && !defined(__MINGW32__)
+    SECTION("issue #4916 - constructing array from C++20 ranges view does not work")
+    {
+        std::vector<int> nums{1, 2, 37, 42, 21};
+        auto filteredNums = nums | std::views::filter([](int i)
+        {
+            return i > 10;
+        });
+        json const j(filteredNums);
+        CHECK(j.type() == json::value_t::array);
+        CHECK(j == json({37, 42, 21}));
+    }
+#endif
+
+    // owning_view is not available in libstdc++ < 12
+#if JSON_HAS_RANGES && !defined(__MINGW32__) && !(defined(__GLIBCXX__) && _GLIBCXX_RELEASE < 12)
+    SECTION("issue #4916 - constructing array from prvalue C++20 ranges view (owning_view)")
+    {
+        json const j(std::vector<int> {1, 2, 37, 42, 21} | std::views::filter([](int i)
+        {
+            return i > 10;
+        }));
+        CHECK(j.type() == json::value_t::array);
+        CHECK(j == json({37, 42, 21}));
+    }
+#endif
+
+#if JSON_HAS_RANGES && !defined(__MINGW32__)
+    SECTION("issue #4916 - constructing array from C++20 transform view (prvalue elements)")
+    {
+        std::vector<int> nums{1, 2, 3};
+        auto t = nums | std::views::transform([](int i) noexcept
+        {
+            return i * 2;
+        });
+        json const j(t);
+        CHECK(j.type() == json::value_t::array);
+        CHECK(j == json({2, 4, 6}));
+    }
+#endif
+}
+
+TEST_CASE_TEMPLATE("issue #4798 - nlohmann::json::to_msgpack() encode float NaN as double", T, double, float) // NOLINT(readability-math-missing-parentheses, bugprone-throwing-static-initialization)
+{
+    // With issue #4798, we encode NaN, infinity, and -infinity as float instead
+    // of double to allow for smaller encodings.
+    const json jx = std::numeric_limits<T>::quiet_NaN();
+    const json jy = std::numeric_limits<T>::infinity();
+    const json jz = -std::numeric_limits<T>::infinity();
+
+    /////////////////////////////////////////////////////////////////////////
+    // MessagePack
+    /////////////////////////////////////////////////////////////////////////
+
+    // expected MessagePack values
+    const std::vector<std::uint8_t> msgpack_x = {{0xCA, 0x7F, 0xC0, 0x00, 0x00}};
+    const std::vector<std::uint8_t> msgpack_y = {{0xCA, 0x7F, 0x80, 0x00, 0x00}};
+    const std::vector<std::uint8_t> msgpack_z = {{0xCA, 0xFF, 0x80, 0x00, 0x00}};
+
+    CHECK(json::to_msgpack(jx) == msgpack_x);
+    CHECK(json::to_msgpack(jy) == msgpack_y);
+    CHECK(json::to_msgpack(jz) == msgpack_z);
+
+    CHECK(std::isnan(json::from_msgpack(msgpack_x).get<T>()));
+    CHECK(json::from_msgpack(msgpack_y).get<T>() == std::numeric_limits<T>::infinity());
+    CHECK(json::from_msgpack(msgpack_z).get<T>() == -std::numeric_limits<T>::infinity());
+
+    // Make sure the other MessagePakc encodings for NaN, infinity, and
+    // -infinity are still supported.
+    const std::vector<std::uint8_t> msgpack_x_2 = {{0xCB, 0x7F, 0xF8, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}};
+    const std::vector<std::uint8_t> msgpack_y_2 = {{0xCB, 0x7F, 0xF0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}};
+    const std::vector<std::uint8_t> msgpack_z_2 = {{0xCB, 0xFF, 0xF0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}};
+    CHECK(std::isnan(json::from_msgpack(msgpack_x_2).get<T>()));
+    CHECK(json::from_msgpack(msgpack_y_2).get<T>() == std::numeric_limits<T>::infinity());
+    CHECK(json::from_msgpack(msgpack_z_2).get<T>() == -std::numeric_limits<T>::infinity());
+
+    /////////////////////////////////////////////////////////////////////////
+    // CBOR
+    /////////////////////////////////////////////////////////////////////////
+
+    // expected CBOR values
+    const std::vector<std::uint8_t> cbor_x = {{0xF9, 0x7E, 0x00}};
+    const std::vector<std::uint8_t> cbor_y = {{0xF9, 0x7C, 0x00}};
+    const std::vector<std::uint8_t> cbor_z = {{0xF9, 0xfC, 0x00}};
+
+    CHECK(json::to_cbor(jx) == cbor_x);
+    CHECK(json::to_cbor(jy) == cbor_y);
+    CHECK(json::to_cbor(jz) == cbor_z);
+
+    CHECK(std::isnan(json::from_cbor(cbor_x).get<T>()));
+    CHECK(json::from_cbor(cbor_y).get<T>() == std::numeric_limits<T>::infinity());
+    CHECK(json::from_cbor(cbor_z).get<T>() == -std::numeric_limits<T>::infinity());
+
+    // Make sure the other CBOR encodings for NaN, infinity, and -infinity are
+    // still supported.
+    const std::vector<std::uint8_t> cbor_x_2 = {{0xFA, 0x7F, 0xC0, 0x00, 0x00}};
+    const std::vector<std::uint8_t> cbor_y_2 = {{0xFA, 0x7F, 0x80, 0x00, 0x00}};
+    const std::vector<std::uint8_t> cbor_z_2 = {{0xFA, 0xFF, 0x80, 0x00, 0x00}};
+    const std::vector<std::uint8_t> cbor_x_3 = {{0xFB, 0x7F, 0xF8, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}};
+    const std::vector<std::uint8_t> cbor_y_3 = {{0xFB, 0x7F, 0xF0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}};
+    const std::vector<std::uint8_t> cbor_z_3 = {{0xFB, 0xFF, 0xF0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}};
+    CHECK(std::isnan(json::from_cbor(cbor_x_2).get<T>()));
+    CHECK(json::from_cbor(cbor_y_2).get<T>() == std::numeric_limits<T>::infinity());
+    CHECK(json::from_cbor(cbor_z_2).get<T>() == -std::numeric_limits<T>::infinity());
+    CHECK(std::isnan(json::from_cbor(cbor_x_3).get<T>()));
+    CHECK(json::from_cbor(cbor_y_3).get<T>() == std::numeric_limits<T>::infinity());
+    CHECK(json::from_cbor(cbor_z_3).get<T>() == -std::numeric_limits<T>::infinity());
+}
+
+TEST_CASE("regression test #5074 - portable workaround for single-element brace init")
+{
+    json const j_obj = {{"key", "value"}};
+
+    json const j = json::array({j_obj});
+    CHECK(j.is_array());
+    CHECK(j.size() == 1);
+    CHECK(j[0] == j_obj);
+}
+
+#if defined(JSON_BRACE_INIT_COPY_SEMANTICS) && (JSON_BRACE_INIT_COPY_SEMANTICS == 1)
+TEST_CASE("regression test #5074 - single-element brace init with JSON_BRACE_INIT_COPY_SEMANTICS")
+{
+    // with JSON_BRACE_INIT_COPY_SEMANTICS: single-element brace init copies/moves
+    json const j_obj = {{"key", "value"}, {"num", 42}};
+    json const j_arr = {1, 2, 3};
+
+    // object: brace init copies instead of wrapping
+    json const j1{j_obj};
+    CHECK(j1.is_object());
+    CHECK(j1 == j_obj);
+
+    // array: brace init copies instead of wrapping
+    json const j2{j_arr};
+    CHECK(j2.is_array());
+    CHECK(j2.size() == 3);
+    CHECK(j2 == j_arr);
+
+    // primitives still work as initializer lists
+    json const j3{true};
+    CHECK(j3.is_boolean());
+
+    json const j4{42};
+    CHECK(j4.is_number_integer());
+}
+#endif
+
+struct Example_5122
+{
+    float b = 2;
+    nlohmann::ordered_map<std::string, std::string> c{}; // NOLINT(readability-redundant-member-init): needed for GCC -Weffc++
+    int a = 1;
+    NLOHMANN_DEFINE_TYPE_INTRUSIVE_WITH_DEFAULT(Example_5122, b, c, a)
+};
+
+TEST_CASE("regression test #5122 - from_json into types holding nlohmann::ordered_map")
+{
+    Example_5122 src;
+    src.c.emplace("first", "1");
+    src.c.emplace("second", "2");
+
+    ordered_json const j = src;
+    Example_5122 const dst = j.get<Example_5122>();
+
+    CHECK(dst.b == src.b);
+    CHECK(dst.a == src.a);
+    REQUIRE(dst.c.size() == src.c.size());
+    auto src_it = src.c.begin();
+    auto dst_it = dst.c.begin();
+    for (; src_it != src.c.end(); ++src_it, ++dst_it)
+    {
+        CHECK(dst_it->first == src_it->first);
+        CHECK(dst_it->second == src_it->second);
+    }
+}
+
+// -Wself-assign-overloaded was introduced in Clang 7. Gate the pragma on
+// __has_warning so older Clang versions do not error with "unknown warning
+// group". The __has_warning check has to stay inside the __clang__ branch
+// because GCC does not provide it and would tokenize-error on the argument.
+#if defined(__clang__) && defined(__has_warning)
+    #if __has_warning("-Wself-assign-overloaded")
+        DOCTEST_CLANG_SUPPRESS_WARNING_PUSH
+        DOCTEST_CLANG_SUPPRESS_WARNING("-Wself-assign-overloaded")
+    #endif
+#endif
+
+TEST_CASE("regression test #5122 - nlohmann::ordered_map copy-assignment is self-assignment safe")
+{
+    nlohmann::ordered_map<std::string, std::string> m;
+    m.emplace("first", "1");
+    m.emplace("second", "2");
+
+    // Insertion order is preserved by ordered_map, so we can check it directly.
+    m = m;
+
+    REQUIRE(m.size() == 2);
+    auto it = m.begin();
+    CHECK(it->first == "first");
+    CHECK(it->second == "1");
+    ++it;
+    CHECK(it->first == "second");
+    CHECK(it->second == "2");
+}
+
+#if defined(__clang__) && defined(__has_warning)
+    #if __has_warning("-Wself-assign-overloaded")
+        DOCTEST_CLANG_SUPPRESS_WARNING_POP
+    #endif
+#endif
+
+TEST_CASE("regression test #5122 - nlohmann::ordered_map move-assignment transfers contents")
+{
+    nlohmann::ordered_map<std::string, std::string> src;
+    src.emplace("first", "1");
+    src.emplace("second", "2");
+
+    nlohmann::ordered_map<std::string, std::string> dst;
+    dst.emplace("stale", "x");
+    dst = std::move(src);
+
+    REQUIRE(dst.size() == 2);
+    auto it = dst.begin();
+    CHECK(it->first == "first");
+    CHECK(it->second == "1");
+    ++it;
+    CHECK(it->first == "second");
+    CHECK(it->second == "2");
+
+    // Re-assigning into the moved-from object must leave it in a usable state.
+    src = nlohmann::ordered_map<std::string, std::string> {};
+    src.emplace("after-move", "3");
+    REQUIRE(src.size() == 1);
+    CHECK(src.begin()->first == "after-move");
+}
+
+// Stand-in for a third-party library (e.g., Eigen as of 3.4, which added
+// STL-compatible begin()/end() to its vector types), living in its own
+// namespace with its own to_json overload for its vector type.
+namespace issue_4320_eigen
+{
+// "array-compatible" from the library's point of view (it has begin()/end()),
+// but for which this (fake) third-party namespace provides its own to_json.
+struct vector3
+{
+    double v[3]; // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays,cppcoreguidelines-use-default-member-init,modernize-use-default-member-init)
+    vector3(double x, double y, double z) : v{x, y, z} {} // NOLINT(hicpp-member-init,cppcoreguidelines-pro-type-member-init)
+    double x() const
+    {
+        return v[0];
+    }
+    double y() const
+    {
+        return v[1];
+    }
+    double z() const
+    {
+        return v[2];
+    }
+    double* begin()
+    {
+        return v;
+    }
+    double* end()
+    {
+        return v + 3;
+    }
+    const double* begin() const
+    {
+        return v;
+    }
+    const double* end() const
+    {
+        return v + 3;
+    }
+};
+
+inline void to_json(json& j, const vector3& v) // NOLINT(misc-use-internal-linkage)
+{
+    j = {{"x", v.x()}, {"y", v.y()}, {"z", v.z()}};
+}
+} // namespace issue_4320_eigen
+
+// The user's own namespace, using the (fake) Eigen type as an implementation
+// detail behind a payload type that has nothing to do with vectors/arrays.
+namespace issue_4320
+{
+// Publicly derives from issue_4320_eigen::vector3 but does *not* define its
+// own to_json - it is only ever used as a temporary to reach the base
+// class's to_json via ADL.
+struct vector3_wrapper : issue_4320_eigen::vector3
+{
+    using issue_4320_eigen::vector3::vector3;
+};
+
+struct payload
+{
+    double x, y, z;
+};
+
+inline vector3_wrapper to_eigen(const payload& p) // NOLINT(misc-use-internal-linkage)
+{
+    return {p.x, p.y, p.z};
+}
+
+inline void to_json(json& j, const payload& p) // NOLINT(misc-use-internal-linkage)
+{
+    // Unqualified call, passing a *derived* vector3_wrapper: relies on ADL
+    // finding issue_4320_eigen::to_json(json&, const vector3&) through the
+    // vector3 base class, via a derived-to-base conversion. Must NOT resolve
+    // to the library's own generic array-compatible to_json (an exact-match
+    // template for vector3_wrapper, since it also has begin()/end()), which
+    // would serialize this as [x, y, z] instead of {"x":x, "y":y, "z":z}.
+    to_json(j, to_eigen(p));
+}
+} // namespace issue_4320
+
+TEST_CASE("issue #4320 - custom base class must not leak nlohmann::detail into ADL")
+{
+    // Before the fix, basic_json unconditionally derived from a type living in
+    // nlohmann::detail (json_default_base), which made nlohmann::detail an
+    // associated namespace of every basic_json for ADL purposes. That leaked
+    // the library's internal generic-array to_json overload into unqualified
+    // to_json() calls made from user code, silently bypassing user-defined
+    // to_json overloads reached via a derived-to-base conversion.
+    const issue_4320::payload p{1.0, 2.0, 3.0};
+
+    json j;
+    to_json(j, p);
+    CHECK(j == json({{"x", 1.0}, {"y", 2.0}, {"z", 3.0}}));
+}
+
+TEST_CASE("issue #5338 - truncated CBOR tagged binary subtype is rejected")
+{
+    const std::vector<std::vector<std::uint8_t>> truncated_tags =
+    {
+        {0xD8},
+        {0xD9, 0x00},
+        {0xDA, 0x00, 0x00, 0x00},
+        {0xDB, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}
+    };
+
+    for (const auto& data : truncated_tags)
+    {
+        CAPTURE(data);
+        for (const auto tag_handler :
+                {
+                    json::cbor_tag_handler_t::ignore, json::cbor_tag_handler_t::store
+                })
+        {
+            CAPTURE(tag_handler);
+            const auto result = json::from_cbor(data, true, false, tag_handler);
+            CHECK(result.is_discarded());
+        }
+    }
+}
+
+TEST_CASE("issue #5402 - update(merge_objects=true) overwrites a primitive with an object")
+{
+    json t = {{"k", 1}};
+    t.update(json{{"k", {{"x", 2}}}}, true);
+    CHECK(t == json({{"k", {{"x", 2}}}}));
+
+    json mixed = {{"keep", {{"a", 1}}}, {"replace", 1}};
+    mixed.update(json{{"keep", {{"b", 2}}}, {"replace", {{"x", 2}}}}, true);
+    CHECK(mixed == json({{"keep", {{"a", 1}, {"b", 2}}}, {"replace", {{"x", 2}}}}));
+}
+
+
+DOCTEST_CLANG_SUPPRESS_WARNING_POP

tests/src/unit-type_traits.cpp

@@ -53,4 +53,34 @@ TEST_CASE("type traits")
             // NOLINTEND(hicpp-avoid-c-arrays,modernize-avoid-c-arrays,cppcoreguidelines-avoid-c-arrays)
         }
     }
+
+    SECTION("char_traits")
+    {
+        SECTION("to_int_type does not sign-extend")
+        {
+            using unsigned_traits = nlohmann::detail::char_traits<unsigned char>;
+            using signed_traits = nlohmann::detail::char_traits<signed char>;
+
+            CHECK(unsigned_traits::to_int_type(static_cast<unsigned char>(0x7F)) == 0x7F);
+            CHECK(unsigned_traits::to_int_type(static_cast<unsigned char>(0x80)) == 0x80);
+            CHECK(unsigned_traits::to_int_type(static_cast<unsigned char>(0xFF)) == 0xFF);
+
+            CHECK(signed_traits::to_int_type(static_cast<signed char>(0x7F)) == 0x7F);
+            // 0x80 and 0xFF do not fit in signed char (MSVC C4309), so spell them as negative values
+            CHECK(signed_traits::to_int_type(static_cast<signed char>(0x80 - 0x100)) == 0x80);
+            CHECK(signed_traits::to_int_type(static_cast<signed char>(0xFF - 0x100)) == 0xFF);
+        }
+
+        SECTION("no byte value collides with eof")
+        {
+            using unsigned_traits = nlohmann::detail::char_traits<unsigned char>;
+            using signed_traits = nlohmann::detail::char_traits<signed char>;
+
+            for (int i = 0; i < 256; ++i)
+            {
+                CHECK(unsigned_traits::to_int_type(static_cast<unsigned char>(i)) != unsigned_traits::eof());
+                CHECK(signed_traits::to_int_type(static_cast<signed char>(i)) != signed_traits::eof());
+            }
+        }
+    }
 }

tests/src/unit-ubjson.cpp

@@ -819,6 +819,8 @@ TEST_CASE("UBJSON")
                     CHECK_THROWS_WITH_AS(_ = json::from_ubjson(vec2), "[json.exception.parse_error.115] parse error at byte 5: syntax error while parsing UBJSON high-precision number: invalid number text: 1A", json::parse_error);
                     std::vector<uint8_t> const vec3 = {'H', 'i', 2, '1', '.'};
                     CHECK_THROWS_WITH_AS(_ = json::from_ubjson(vec3), "[json.exception.parse_error.115] parse error at byte 5: syntax error while parsing UBJSON high-precision number: invalid number text: 1.", json::parse_error);
+                    std::vector<uint8_t> const vec_overflow = {'H', 'i', 5, '1', 'e', '4', '0', '0'};
+                    CHECK_THROWS_WITH_AS(_ = json::from_ubjson(vec_overflow), "[json.exception.out_of_range.406] number overflow parsing '1e400'", json::out_of_range&);
                     std::vector<uint8_t> const vec4 = {'H', 2, '1', '0'};
                     CHECK_THROWS_WITH_AS(_ = json::from_ubjson(vec4), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing UBJSON size: expected length type specification (U, i, I, l, L) after '#'; last byte: 0x02", json::parse_error);
                 }
@@ -1711,6 +1713,44 @@ TEST_CASE("UBJSON")
             CHECK(json::to_ubjson(json::from_ubjson(s_L)) == s_i);
         }
 
+        SECTION("no-op markers")
+        {
+            // A no-op ('N') is valid wherever a value may start; it is consumed
+            // by get_ignore_noop() before the value is read. It is not valid
+            // where a string length type specification is expected.
+
+            SECTION("accepted where a value may start")
+            {
+                // at top level, also repeated
+                CHECK(json::from_ubjson(std::vector<uint8_t>({'N', 'i', 1})) == json(1));
+                CHECK(json::from_ubjson(std::vector<uint8_t>({'N', 'N', 'N', 'i', 1})) == json(1));
+
+                // inside an array of unknown size, before and after an element
+                CHECK(json::from_ubjson(std::vector<uint8_t>({'[', 'N', 'i', 1, ']'})) == json({1}));
+                CHECK(json::from_ubjson(std::vector<uint8_t>({'[', 'i', 1, 'N', ']'})) == json({1}));
+
+                // inside an object of unknown size: before a key, between key
+                // and value, and before the closing '}'
+                CHECK(json::from_ubjson(std::vector<uint8_t>({'{', 'N', 'U', 1, 'a', 'i', 1, '}'})) == json({{"a", 1}}));
+                CHECK(json::from_ubjson(std::vector<uint8_t>({'{', 'U', 1, 'a', 'N', 'i', 1, '}'})) == json({{"a", 1}}));
+                CHECK(json::from_ubjson(std::vector<uint8_t>({'{', 'U', 1, 'a', 'i', 1, 'N', '}'})) == json({{"a", 1}}));
+            }
+
+            SECTION("rejected where a length type specification is expected")
+            {
+                json _;
+
+                // after the 'S' marker of a string value
+                std::vector<uint8_t> const v_S = {'S', 'N', 'U', 1, 'a'};
+                CHECK_THROWS_WITH_AS(_ = json::from_ubjson(v_S), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing UBJSON string: expected length type specification (U, i, I, l, L); last byte: 0x4E", json::parse_error&);
+
+                // as the key length of an object with a known size, where
+                // no-ops are not permitted in the first place
+                std::vector<uint8_t> const v_key = {'{', '#', 'i', 1, 'N', 'U', 1, 'a', 'i', 1};
+                CHECK_THROWS_WITH_AS(_ = json::from_ubjson(v_key), "[json.exception.parse_error.113] parse error at byte 5: syntax error while parsing UBJSON string: expected length type specification (U, i, I, l, L); last byte: 0x4E", json::parse_error&);
+            }
+        }
+
         SECTION("number")
         {
             SECTION("float")
@@ -2109,6 +2149,67 @@ TEST_CASE("UBJSON")
     }
 }
 
+TEST_CASE("UBJSON optimized arrays of a valueless type are bounded")
+{
+    // An element of type 'Z', 'T' or 'F' is encoded by its marker alone, so an
+    // optimized array of one of those has no payload and the declared count is
+    // the only thing deciding how much is allocated. Ten bytes used to produce
+    // billions of values (#2793); every other type costs at least one byte per
+    // element and is bounded by the end of the input.
+    json _;
+
+    SECTION("an excessive count is rejected")
+    {
+        // 'l' is a big-endian int32: 0x7FFFFFFF elements, about 34 GB of value
+        for (const auto marker :
+                {'Z', 'T', 'F'
+                })
+        {
+            const std::vector<uint8_t> input = {'[', '$', static_cast<uint8_t>(marker), '#', 'l', 0x7F, 0xFF, 0xFF, 0xFF};
+            CHECK_THROWS_WITH_AS(_ = json::from_ubjson(input), "[json.exception.out_of_range.408] syntax error while parsing UBJSON size: excessive array size", json::out_of_range&);
+            CHECK(json::from_ubjson(input, true, false).is_discarded());
+        }
+    }
+
+    SECTION("ordinary counts are unaffected")
+    {
+        CHECK(json::from_ubjson(std::vector<uint8_t>({'[', '$', 'Z', '#', 'i', 3})) == json({nullptr, nullptr, nullptr}));
+        CHECK(json::from_ubjson(std::vector<uint8_t>({'[', '$', 'T', '#', 'i', 2})) == json({true, true}));
+        CHECK(json::from_ubjson(std::vector<uint8_t>({'[', '$', 'F', '#', 'i', 2})) == json({false, false}));
+        // 'N' is a no-op rather than a value, and still yields an empty array
+        CHECK(json::from_ubjson(std::vector<uint8_t>({'[', '$', 'N', '#', 'i', 2})) == json::array());
+    }
+
+    SECTION("a type with a payload is unaffected")
+    {
+        // A count past the limit is not rejected for 'U', which costs a byte
+        // per element and is bounded by the end of the input instead. The
+        // count is kept just past the limit rather than made huge, because a
+        // count that also exceeds the array's max_size() is reported as
+        // out_of_range before the input runs out, and max_size() depends on
+        // the width of std::size_t.
+        const std::vector<uint8_t> input = {'[', '$', 'U', '#', 'l', 0x00, 0x10, 0x00, 0x01};
+        CHECK_THROWS_WITH_AS(_ = json::from_ubjson(input), "[json.exception.parse_error.110] parse error at byte 10: syntax error while parsing UBJSON number: unexpected end of input", json::parse_error&);
+        CHECK(json::from_ubjson(input, true, false).is_discarded());
+    }
+
+    SECTION("the writer stays within what the reader accepts")
+    {
+        // below the limit the optimized form is used and is tiny; above it the
+        // writer falls back so that the result can still be read back
+        json const at_limit(1048576, nullptr);
+        const auto v_at_limit = json::to_ubjson(at_limit, true, true);
+        CHECK(v_at_limit.size() == 9);
+        CHECK(v_at_limit.at(1) == '$');
+        CHECK(json::from_ubjson(v_at_limit) == at_limit);
+
+        json const above_limit(1048577, nullptr);
+        const auto v_above_limit = json::to_ubjson(above_limit, true, true);
+        CHECK(v_above_limit.at(1) != '$');
+        CHECK(json::from_ubjson(v_above_limit) == above_limit);
+    }
+}
+
 TEST_CASE("Universal Binary JSON Specification Examples 1")
 {
     SECTION("Null Value")
@@ -2463,6 +2564,48 @@ TEST_CASE("all UBJSON first bytes")
 }
 #endif
 
+TEST_CASE("UBJSON use_type requires use_size")
+{
+    SECTION("non-empty array throws other_error.502")
+    {
+        const json j = {1, 2, 3};
+        CHECK_THROWS_WITH_AS(json::to_ubjson(j, false, true),
+                             "[json.exception.other_error.502] use_type requires use_size = true",
+                             json::other_error&);
+    }
+
+    SECTION("non-empty object throws other_error.502")
+    {
+        const json j = {{"a", 1}, {"b", 2}};
+        CHECK_THROWS_WITH_AS(json::to_ubjson(j, false, true),
+                             "[json.exception.other_error.502] use_type requires use_size = true",
+                             json::other_error&);
+    }
+
+    SECTION("scalars do not throw with use_type=true, use_count=false")
+    {
+        CHECK_NOTHROW(json::to_ubjson(42, false, true));
+        CHECK_NOTHROW(json::to_ubjson(3.14, false, true));
+        CHECK_NOTHROW(json::to_ubjson("hello", false, true));
+        CHECK_NOTHROW(json::to_ubjson(true, false, true));
+        CHECK_NOTHROW(json::to_ubjson(nullptr, false, true));
+    }
+
+    SECTION("empty containers do not throw with use_type=true, use_count=false")
+    {
+        CHECK_NOTHROW(json::to_ubjson(json::array(), false, true));
+        CHECK_NOTHROW(json::to_ubjson(json::object(), false, true));
+    }
+
+    SECTION("valid combinations on non-empty containers")
+    {
+        const json j = {1, 2, 3};
+        CHECK_NOTHROW(json::to_ubjson(j, false, false));
+        CHECK_NOTHROW(json::to_ubjson(j, true, false));
+        CHECK_NOTHROW(json::to_ubjson(j, true, true));
+    }
+}
+
 TEST_CASE("UBJSON roundtrips" * doctest::skip())
 {
     SECTION("input from self-generated UBJSON files")

tests/src/unit-wstring.cpp

@@ -125,6 +125,16 @@ TEST_CASE("wide strings")
             std::u32string const w = U"\"\x110000";
             json _;
             CHECK_THROWS_AS(_ = json::parse(w), json::parse_error&);
+
+            // a code unit above U+10FFFF must not be narrowed onto the EOF
+            // sentinel: 0xFFFFFFFF would otherwise end the document silently and
+            // let everything following it pass the strict end-of-input check
+            std::u32string const trailing{U'[', U'1', U']', static_cast<char32_t>(0xFFFFFFFF), U'x'};
+            CHECK_THROWS_WITH_AS(_ = json::parse(trailing), "[json.exception.parse_error.101] parse error at line 1, column 4: syntax error while parsing value - invalid literal; last read: '1]\xFF'; expected end of input", json::parse_error&);
+            CHECK(!json::accept(trailing));
+
+            // the same unit inside a string is reported as an ill-formed byte
+            CHECK_THROWS_WITH_AS(_ = json::parse(std::u32string{U'"', static_cast<char32_t>(0xFFFFFFFF), U'"'}), "[json.exception.parse_error.101] parse error at line 1, column 2: syntax error while parsing value - invalid string: ill-formed UTF-8 byte; last read: '\"\xFF'", json::parse_error&);
         }
     }
 }