Merge branch 'develop' into ci/path-filters

Keep ci_test_documentation in repository_checks.yml and apply the harden-runner 2.22.2 bump from #5962 there. Signed-off-by: Niels Lohmann <mail@nlohmann.me>
json_view benchmarks: compare fairly and state what each row means (#5914 )
2026-11-12 23:20:46 +00:00 · 2026-10-30 15:35:39 +01:00 · 2026-10-30 15:20:12 +01:00 · 2026-10-30 15:19:42 +01:00 · 2026-10-30 15:19:08 +01:00 · 2026-10-30 15:18:56 +01:00
69 changed files with 5979 additions and 2800 deletions
@@ -154,6 +154,11 @@ and each page's title (H1) and declaration by
 [`docs/docset/generate_docset.py`](https://github.com/nlohmann/json/blob/develop/docs/docset/generate_docset.py);
 `make build` reports API pages that cannot be classified.

+A pull request that changes only the documentation, Markdown files, GitHub metadata, or license files skips the
+compiler workflows (Ubuntu, macOS, Windows); the documentation and license checks still run. See
+[`tools/check_path_filters`](https://github.com/nlohmann/json/tree/develop/tools/check_path_filters) for the list of
+skipped files and what to do when a compiler job starts reading one of them.
+
 ### Amalgamate the source code

 The single-header files
@@ -28,7 +28,7 @@ jobs:

    steps:
      - name: Harden Runner
-        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
+        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
        with:
          egress-policy: audit

@@ -22,7 +22,7 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - name: Harden Runner
-        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
+        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
        with:
          egress-policy: audit

@@ -46,7 +46,7 @@ jobs:

    steps:
      - name: Harden Runner
-        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
+        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
        with:
          egress-policy: audit

@@ -20,7 +20,7 @@ jobs:
    timeout-minutes: 30
    steps:
      - name: Harden Runner
-        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
+        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
        with:
          egress-policy: audit

@@ -13,7 +13,7 @@ jobs:
    runs-on: ubuntu-22.04
    steps:
    - name: Harden Runner
-      uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
+      uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
      with:
        egress-policy: audit

@@ -27,7 +27,7 @@ jobs:

    steps:
    - name: Harden Runner
-      uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
+      uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
      with:
        egress-policy: audit

@@ -38,14 +38,14 @@ jobs:

    # Initializes the CodeQL tools for scanning.
    - name: Initialize CodeQL
-      uses: github/codeql-action/init@6f2ac81f5cd81fe351a197ba0b00d91d03cd2aee # v4.39.0
+      uses: github/codeql-action/init@9b3254085494b55a0f7c4c2b3d2d52cc712ce370 # v4.39.1
      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@6f2ac81f5cd81fe351a197ba0b00d91d03cd2aee # v4.39.0
+      uses: github/codeql-action/autobuild@9b3254085494b55a0f7c4c2b3d2d52cc712ce370 # v4.39.1

    - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@6f2ac81f5cd81fe351a197ba0b00d91d03cd2aee # v4.39.0
+      uses: github/codeql-action/analyze@9b3254085494b55a0f7c4c2b3d2d52cc712ce370 # v4.39.1
@@ -20,7 +20,7 @@ jobs:
      pull-requests: write
    steps:
      - name: Harden Runner
-        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
+        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
        with:
          egress-policy: audit

@@ -21,7 +21,7 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - name: Harden Runner
-        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
+        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
        with:
          egress-policy: audit

@@ -31,7 +31,7 @@ jobs:
      security-events: write
    steps:
      - name: Harden Runner
-        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
+        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
        with:
          egress-policy: audit

@@ -48,6 +48,6 @@ jobs:
          output: 'flawfinder_results.sarif'

      - name: Upload analysis results to GitHub Security tab
-        uses: github/codeql-action/upload-sarif@6f2ac81f5cd81fe351a197ba0b00d91d03cd2aee # v4.39.0
+        uses: github/codeql-action/upload-sarif@9b3254085494b55a0f7c4c2b3d2d52cc712ce370 # v4.39.1
        with:
          sarif_file: ${{github.workspace}}/flawfinder_results.sarif
@@ -54,7 +54,7 @@ jobs:
    timeout-minutes: 60
    steps:
      - name: Harden Runner
-        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
+        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
        with:
          egress-policy: audit

@@ -23,7 +23,7 @@ jobs:

    steps:
      - name: Harden Runner
-        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
+        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
        with:
          egress-policy: audit

@@ -7,6 +7,25 @@ on:
      - master
      - release/*
  pull_request:
+    # Skip pull requests that change only files no job here reads. The list is checked by
+    # tools/check_path_filters/check_path_filters.py (repository_checks.yml); change both together.
+    paths:
+      - '**'
+      - '!docs/**'
+      - '!**.md'
+      - '!.github/*'
+      - '!.github/ISSUE_TEMPLATE/**'
+      - '!.github/external_ci/**'
+      - '!.github/workflows/**'
+      - '!.reuse/**'
+      - '!LICENSES/**'
+      - '!CITATION.cff'
+      - '!REUSE.toml'
+      # read by tools/check_build_options in the ci_meson_install job (ubuntu.yml)
+      - 'docs/mkdocs/docs/integration/package_managers.md'
+      # built by the swiftpm job (macos.yml)
+      - 'docs/mkdocs/docs/integration/swift/**'
+      - '.github/workflows/macos.yml'
  workflow_dispatch:

 concurrency:
@@ -37,7 +37,7 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - name: Harden Runner
-        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
+        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
        with:
          egress-policy: audit

@@ -0,0 +1,78 @@
+name: Repository checks
+
+# Checks that concern files the compiler workflows (ubuntu.yml, macos.yml,
+# windows.yml) skip with their path filter: the documentation, the license
+# information, and the path filter itself. This workflow has no path filter.
+on:
+  push:
+    branches:
+      - develop
+      - master
+      - release/*
+  pull_request:
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  check_path_filters:
+    runs-on: ubuntu-26.04
+    steps:
+      - name: Harden Runner
+        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
+        with:
+          egress-policy: audit
+
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+      - name: Check the path filters of the compiler workflows
+        run: python3 tools/check_path_filters/check_path_filters.py
+
+  ci_reuse_compliance:
+    runs-on: ubuntu-26.04
+    steps:
+      - name: Harden Runner
+        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
+        with:
+          egress-policy: audit
+
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+      - name: Get latest CMake and ninja
+        uses: lukka/get-cmake@a89e43e22a96abafcd7a62db652a65ecd33052c9 # v4.4.4
+      - name: Run CMake
+        run: cmake -S . -B build -DJSON_CI=On
+      - name: Build
+        run: cmake --build build --target ci_reuse_compliance
+
+  ci_test_documentation:
+    runs-on: ubuntu-26.04
+    strategy:
+      matrix:
+        target: [ci_test_examples, ci_test_build_documentation, ci_test_documentation_mermaid]
+    steps:
+      - name: Harden Runner
+        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
+        with:
+          egress-policy: audit
+
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+          # the git-revision-date-localized plugin needs the history; a shallow clone makes the strict build fail
+          fetch-depth: ${{ matrix.target == 'ci_test_build_documentation' && '0' || '1' }}
+      - uses: actions/setup-node@949feb2413d6458794dcd2491c4babbbce0c15c1 # v7.1.0
+        if: matrix.target == 'ci_test_documentation_mermaid'
+        with:
+          node-version: 24
+      - name: Run CMake
+        run: cmake -S . -B build -DJSON_CI=On
+      - name: Build
+        run: cmake --build build --target ${{ matrix.target }}
@@ -40,7 +40,7 @@ jobs:

    steps:
      - name: Harden Runner
-        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
+        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
        with:
          egress-policy: audit

@@ -80,6 +80,6 @@ jobs:

      # Upload the results to GitHub's code scanning dashboard.
      - name: "Upload to code-scanning"
-        uses: github/codeql-action/upload-sarif@6f2ac81f5cd81fe351a197ba0b00d91d03cd2aee # v4.39.0
+        uses: github/codeql-action/upload-sarif@9b3254085494b55a0f7c4c2b3d2d52cc712ce370 # v4.39.1
        with:
          sarif_file: results.sarif
@@ -36,7 +36,7 @@ jobs:
    runs-on: ubuntu-26.04
    steps:
      - name: Harden Runner
-        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
+        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
        with:
          egress-policy: audit

@@ -65,7 +65,7 @@ jobs:

      # Upload SARIF file generated in previous step
      - name: Upload SARIF file
-        uses: github/codeql-action/upload-sarif@6f2ac81f5cd81fe351a197ba0b00d91d03cd2aee # v4.39.0
+        uses: github/codeql-action/upload-sarif@9b3254085494b55a0f7c4c2b3d2d52cc712ce370 # v4.39.1
        with:
          sarif_file: semgrep.sarif
        if: always()
@@ -16,7 +16,7 @@ jobs:

    steps:
      - name: Harden Runner
-        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
+        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
        with:
          egress-policy: audit

@@ -7,6 +7,25 @@ on:
      - master
      - release/*
  pull_request:
+    # Skip pull requests that change only files no job here reads. The list is checked by
+    # tools/check_path_filters/check_path_filters.py (repository_checks.yml); change both together.
+    paths:
+      - '**'
+      - '!docs/**'
+      - '!**.md'
+      - '!.github/*'
+      - '!.github/ISSUE_TEMPLATE/**'
+      - '!.github/external_ci/**'
+      - '!.github/workflows/**'
+      - '!.reuse/**'
+      - '!LICENSES/**'
+      - '!CITATION.cff'
+      - '!REUSE.toml'
+      # read by tools/check_build_options in the ci_meson_install job (ubuntu.yml)
+      - 'docs/mkdocs/docs/integration/package_managers.md'
+      # built by the swiftpm job (macos.yml)
+      - 'docs/mkdocs/docs/integration/swift/**'
+      - '.github/workflows/ubuntu.yml'
  workflow_dispatch:

 permissions:
@@ -80,7 +99,7 @@ jobs:
    runs-on: ubuntu-26.04
    steps:
      - name: Harden Runner
-        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
+        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
        with:
          egress-policy: audit

@@ -109,10 +128,10 @@ jobs:
    runs-on: ubuntu-26.04
    strategy:
      matrix:
-        target: [ci_test_single_header, ci_cppcheck, ci_cpplint, ci_reproducible_tests, ci_non_git_tests, ci_offline_testdata, ci_reuse_compliance, ci_test_valgrind]
+        target: [ci_test_single_header, ci_cppcheck, ci_cpplint, ci_reproducible_tests, ci_non_git_tests, ci_offline_testdata, ci_test_valgrind]
    steps:
      - name: Harden Runner
-        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
+        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
        with:
          egress-policy: audit

@@ -178,7 +197,7 @@ jobs:
    runs-on: ubuntu-26.04
    steps:
      - name: Harden Runner
-        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
+        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
        with:
          egress-policy: audit

@@ -433,7 +452,7 @@ jobs:
    runs-on: ubuntu-26.04
    steps:
      - name: Harden Runner
-        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
+        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
        with:
          egress-policy: audit

@@ -449,31 +468,6 @@ jobs:
      - name: Build
        run: cmake --build build

-  ci_test_documentation:
-    runs-on: ubuntu-26.04
-    strategy:
-      matrix:
-        target: [ci_test_examples, ci_test_build_documentation, ci_test_documentation_mermaid]
-    steps:
-      - name: Harden Runner
-        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
-        with:
-          egress-policy: audit
-
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
-        with:
-          persist-credentials: false
-          # the git-revision-date-localized plugin needs the history; a shallow clone makes the strict build fail
-          fetch-depth: ${{ matrix.target == 'ci_test_build_documentation' && '0' || '1' }}
-      - uses: actions/setup-node@949feb2413d6458794dcd2491c4babbbce0c15c1 # v7.1.0
-        if: matrix.target == 'ci_test_documentation_mermaid'
-        with:
-          node-version: 24
-      - name: Run CMake
-        run: cmake -S . -B build -DJSON_CI=On
-      - name: Build
-        run: cmake --build build --target ${{ matrix.target }}
-
  # Native Linux ARM64 runner with the latest GCC. The ubuntu-24.04-arm label is
  # only available for public repositories.
  ci_test_arm64:
@@ -7,6 +7,25 @@ on:
      - master
      - release/*
  pull_request:
+    # Skip pull requests that change only files no job here reads. The list is checked by
+    # tools/check_path_filters/check_path_filters.py (repository_checks.yml); change both together.
+    paths:
+      - '**'
+      - '!docs/**'
+      - '!**.md'
+      - '!.github/*'
+      - '!.github/ISSUE_TEMPLATE/**'
+      - '!.github/external_ci/**'
+      - '!.github/workflows/**'
+      - '!.reuse/**'
+      - '!LICENSES/**'
+      - '!CITATION.cff'
+      - '!REUSE.toml'
+      # read by tools/check_build_options in the ci_meson_install job (ubuntu.yml)
+      - 'docs/mkdocs/docs/integration/package_managers.md'
+      # built by the swiftpm job (macos.yml)
+      - 'docs/mkdocs/docs/integration/swift/**'
+      - '.github/workflows/windows.yml'
  workflow_dispatch:

 permissions:
@@ -28,7 +47,7 @@ jobs:
        with:
          persist-credentials: false
      - name: Set up MinGW
-        uses: egor-tensin/setup-mingw@41b837e47d7f85214629d255b9c4bc3fcbe9fd63 # v3.0
+        uses: egor-tensin/setup-mingw@d54f5ef0ce585bd3fbb1f8a71b5b254f59dbf931 # v3.0
        with:
          platform: ${{ matrix.architecture }}
          version: 12.2.0 # https://github.com/egor-tensin/setup-mingw/issues/14
@@ -153,7 +172,7 @@ jobs:
      - name: Install Clang
        run: curl -fsSL -o LLVM${{ matrix.version }}.exe https://github.com/llvm/llvm-project/releases/download/llvmorg-${{ matrix.version }}/LLVM-${{ matrix.version }}-win64.exe ; 7z x LLVM${{ matrix.version }}.exe -y -o"C:/Program Files/LLVM"
      - name: Set up MinGW
-        uses: egor-tensin/setup-mingw@41b837e47d7f85214629d255b9c4bc3fcbe9fd63 # v3.0
+        uses: egor-tensin/setup-mingw@d54f5ef0ce585bd3fbb1f8a71b5b254f59dbf931 # v3.0
        with:
          platform: x64
          version: 12.2.0 # https://github.com/egor-tensin/setup-mingw/issues/14
@@ -1408,9 +1408,9 @@ THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR I
 - The class contains a port of the shortest double-to-decimal conversion of [Żmij](https://github.com/vitaut/zmij) by Victor Zverovich, including the conversion of the digits to text by Xiang JunBo and the SIMD instruction sequence of Dougall Johnson, which is licensed under the [MIT License](https://opensource.org/licenses/MIT) (see above). Copyright &copy; 2025 [Victor Zverovich](https://github.com/vitaut)
 - The class contains a copy of [Hedley](https://nemequ.github.io/hedley/) from Evan Nemerson which is licensed as [CC0-1.0](https://creativecommons.org/publicdomain/zero/1.0/).
 - The class contains parts of [Google Abseil](https://github.com/abseil/abseil-cpp) which is licensed under the [Apache 2.0 License](https://opensource.org/licenses/Apache-2.0).
- The class contains an adapted version of the Eisel-Lemire algorithm, its table of powers of five, and its digit comparison for long numbers from [fast_float](https://github.com/fastfloat/fast_float) by Daniel Lemire and contributors, which is available under the [MIT License](https://opensource.org/licenses/MIT) (used here), the Apache 2.0 License, and the Boost Software License. Copyright &copy; 2021 The fast_float authors
+- The class contains an adapted version of the Eisel-Lemire algorithm, its table of powers of five, its digit comparison for long numbers, and its parsing of eight digits at a time from [fast_float](https://github.com/fastfloat/fast_float) by Daniel Lemire and contributors, which is available under the [MIT License](https://opensource.org/licenses/MIT) (used here), the Apache 2.0 License, and the Boost Software License. Copyright &copy; 2021 The fast_float authors
 - The view's parser (`<nlohmann/json_view.hpp>`) contains techniques and code adapted from [yyjson](https://github.com/ibireme/yyjson) by YaoYuan, which is licensed under the [MIT License](https://opensource.org/licenses/MIT) (see above): table-driven decoding of `\u` escapes and fixed-offset unrolled checks.
- The view's parser (`<nlohmann/json_view.hpp>`) validates non-ASCII strings with the vector UTF-8 check of [simdjson](https://github.com/simdjson/simdjson) by Daniel Lemire, Geoff Langdale, John Keiser, and contributors (its "lookup4" algorithm and tables, after J. Keiser and D. Lemire, "Validating UTF-8 In Less Than One Instruction Per Byte", 2021), which is available under the [MIT License](https://opensource.org/licenses/MIT) (used here) and the Apache 2.0 License. Copyright &copy; 2018-2025 The simdjson authors
+- The class's lexer and the view's parser (`<nlohmann/json_view.hpp>`) validate non-ASCII strings with the vector UTF-8 check of [simdjson](https://github.com/simdjson/simdjson) by Daniel Lemire, Geoff Langdale, John Keiser, and contributors (its "lookup4" algorithm and tables, after J. Keiser and D. Lemire, "Validating UTF-8 In Less Than One Instruction Per Byte", 2021), which is available under the [MIT License](https://opensource.org/licenses/MIT) (used here) and the Apache 2.0 License. Copyright &copy; 2018-2025 The simdjson authors

 <img align="right" src="https://git.fsfe.org/reuse/reuse-ci/raw/branch/master/reuse-horizontal.png" alt="REUSE Software">

@@ -63,6 +63,15 @@ called:
 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 skipped completely, or replaced by `null` if it is the top-level value.

+## Notes
+
+For a `parse_event_t::key` event, `parsed` holds the decoded object name, with the same guarantees as the `val`
+parameter of [`json_sax::key`](../json_sax/key.md#notes): all escape sequences are decoded and `\uXXXX` escapes are
+stored as UTF-8, so different spellings of the same name yield identical strings; the name is validated completely
+before the callback is called, so a name with an invalid escape sequence or ill-formed UTF-8 causes a parse error and
+no `key` event; no Unicode normalization or case conversion is applied; and a name that occurs several times in the
+same object yields one `key` event per occurrence.
+
 ## Examples

 ??? example "Example: skip an object key while parsing"
@@ -69,6 +69,19 @@ Duplicate member names inside an operation object are resolved by the parser bef
 is kept, see [`object_t`](object_t.md#behavior)), so `#!json {"op": "add", "op": "remove", "path": "/a"}` is a
 `remove` operation.

+The JSON patch may be the JSON value itself (`#!cpp j.patch_inplace(j)`): the operations are then read from a copy of
+the patch made before the first operation is applied, so the result is the same as that of
+`#!cpp j = j.patch(j)`, and the exception safety is the same as above.
+
+If [`JSON_DIAGNOSTICS`](../macros/json_diagnostics.md) is enabled, the same holds for a JSON patch stored inside the
+JSON value (e.g., `#!cpp j.patch_inplace(j["patch"])`): it is detected via the parent pointers.
+
+!!! danger "Undefined behavior"
+
+    Without [`JSON_DIAGNOSTICS`](../macros/json_diagnostics.md), the JSON patch must not be a value stored inside the
+    JSON value (e.g., `#!cpp j.patch_inplace(j["patch"])`), as the operations may change or destroy it while it is
+    read. Pass a copy (`#!cpp j.patch_inplace(json(j["patch"]))`) or use [`patch`](patch.md) instead.
+
 ## Examples

 ??? example "Example: apply a JSON patch in place"
@@ -122,3 +135,5 @@ is kept, see [`object_t`](object_t.md#behavior)), so `#!json {"op": "add", "op":
 - Throws [`parse_error.109`](../../home/exceptions.md#jsonexceptionparse_error109) instead of
  [`out_of_range.404`](../../home/exceptions.md#jsonexceptionout_of_range404) for a one-character array index that is
  not a digit (e.g., `/x`) in version 3.13.0, as it already did for longer ones.
+- Applying a JSON value as patch to itself (or, with `JSON_DIAGNOSTICS`, to a value stored inside it) no longer results
+  in undefined behavior in version 3.13.0.
@@ -32,9 +32,24 @@ uses, so the result matches it exactly — including, for an object, that a repe
 last value. The replay is iterative, so it is not limited by the call stack the way a naive recursive conversion
 would be; the JSON nesting depth is limited only by available memory, as for `BasicJsonType::parse()` itself.

-Unlike parsing with [`JSON_DIAGNOSTIC_POSITIONS`](../macros/json_diagnostic_positions.md) enabled, the values
-produced by `materialize()` do not carry source positions. The index has the start offset of every value, but not the
-end of arrays, objects, and escaped strings, which the positions also need.
+With [`JSON_DIAGNOSTIC_POSITIONS`](../macros/json_diagnostic_positions.md) enabled, the values get the source
+positions [`BasicJsonType::parse()`](../basic_json/parse.md) would give them, also for the subtree of a view (the
+positions are those in the document's whole source text), and exceptions about them name the same bytes. For values of
+an [editable document](../json_editable_document.md), positions are all-or-nothing, and [`start_pos()`](../basic_json/start_pos.md)
+and [`end_pos()`](../basic_json/end_pos.md) return `std::string::npos` for
+
+- a value written by an edit (a copy of an array or object of the document is also new; copies of its scalars keep
+  their positions),
+- an array or object whose elements were changed (its elements keep theirs), and
+- an array or object whose last element has no positions (its end is found from that element).
+
+This differs from a `basic_json` value, whose positions are not updated when it is changed: they stay as they were
+parsed, even if they no longer match the value (see [`start_pos()`](../basic_json/start_pos.md)).
+
+Documents [loaded](../basic_json_document/load.md) from an image have the positions of the saved document. Its strings
+with escapes have positions only if the document was parsed with `JSON_DIAGNOSTIC_POSITIONS`: the position of their
+opening quote is recorded while parsing, and `save()` and `load()` keep it whether or not they are compiled with the
+macro.

 Calling `materialize()` on the same view repeatedly builds a new, independent `BasicJsonType` value each time; it
 never caches the result.
@@ -62,8 +77,7 @@ never caches the result.

 - [`root`](../basic_json_document/root.md) - the view of a document's root value
 - [`BasicJsonType::parse`](../basic_json/parse.md) - build a `BasicJsonType` value directly from a JSON text
- [`JSON_DIAGNOSTIC_POSITIONS`](../macros/json_diagnostic_positions.md) - source positions on parsed values (not
-  produced by `materialize()`)
+- [`JSON_DIAGNOSTIC_POSITIONS`](../macros/json_diagnostic_positions.md) - source positions on parsed values
 - [Zero-copy JSON views](../../features/json_view.md#getting-values-out-without-copying) - when to build a basic_json value from a view

 ## Version history
@@ -18,7 +18,8 @@ json_pointer& operator/=(std::size_t array_idx)
 ## Parameters

 `ptr` (in)
-:    JSON pointer to append
+:    JSON pointer to append; may be the JSON pointer itself (`#!cpp p /= p`), which then appends a copy of its
+     reference tokens

 `token` (in)
 :    reference token to append
@@ -69,6 +70,7 @@ json_pointer& operator/=(std::size_t array_idx)

 ## Version history

-1. Added in version 3.6.0.
+1. Added in version 3.6.0. Appending a JSON pointer to itself no longer results in undefined behavior in version
+   3.13.0.
 2. Added in version 3.6.0. Changed type of `token` to `string_t` in version 3.11.0.
 3. Added in version 3.6.0.
@@ -19,6 +19,23 @@ Whether parsing should proceed.

 It is safe to move the passed object key value.

+When parsing JSON text, `val` is the decoded object name, not its spelling in the input:
+
+- All escape sequences (`\"`, `\\`, `\/`, `\b`, `\f`, `\n`, `\r`, `\t`, `\uXXXX`, and surrogate pairs) are
+  decoded, and `\uXXXX` escapes are stored as UTF-8. Different spellings of the same name, such as `#!json "/"`
+  and `#!json "\/"`, or `#!json "\u00e9"` and `#!json "\u00E9"`, yield identical strings. An escaped `\u0000` yields
+  an embedded NUL byte.
+- The name is scanned and validated completely before `key` is called. If it contains an invalid escape sequence, an
+  unpaired surrogate, a control character, or ill-formed UTF-8, the parse fails with a
+  [`parse_error`](../../home/exceptions.md#parse-errors), and `key` is not called for it.
+- No Unicode normalization or case conversion is applied: names that differ in any byte are different strings.
+- `key` is called before the following `:` is read, so a parse error may still follow for the same member.
+- A name that occurs several times in the same object is passed once per occurrence.
+
+For the binary formats, object keys contain no escape sequences. For CBOR, MessagePack, UBJSON, and BSON, `val` holds
+the bytes stored in the input, and [`sax_parse`](../basic_json/sax_parse.md) passes them unchanged, without checking them
+for valid UTF-8. BON8 encodes characters itself, so an ill-formed name is a parse error and `key` is not called for it.
+
 ## Examples

 ??? example
@@ -45,3 +62,7 @@ It is safe to move the passed object key value.
 ## Version history

 - Added in version 3.2.0.
+- The behavior described in the notes above (decoded names, validation before `key` is called, no normalization, `key`
+  before the `:` check, one call per duplicate, bytes of binary formats passed unchanged) is the same in all versions
+  from 3.2.0 on, and for the `key` event of a [parser callback](../basic_json/parser_callback_t.md) from 3.0.0 on. BSON
+  is only supported from version 3.4.0, and BON8 only from version 3.13.0.
@@ -113,6 +113,7 @@ When the macro is not defined, the library will define it to its default value.

 - [:simple-cmake: JSON_Diagnostic_Positions](../../integration/cmake.md#json_diagnostic_positions) - CMake option to control the macro
 - [`JSON_DIAGNOSTICS`](json_diagnostics.md) - macro to control extended diagnostics
+- [`materialize()`](../basic_json_view/materialize.md) - values of a JSON view, with the same positions
 - [Parsing and Exceptions](../../features/parsing/parse_exceptions.md) - handling parse errors and locating them in the input

 ## Version history
@@ -149,10 +149,12 @@ document: `#!cpp auto v = json_document::parse(text).root();` does not compile.
  end must still fit.
 - **A stream is always read to its end.** There is no partial/streaming read of an `#!cpp std::istream`: the stream
  is read to its end into a buffer the document owns, and parsing starts after that.
- **No source positions on `materialize()`.** Even with
+- **Fewer source positions after edits.** With
  [`JSON_DIAGNOSTIC_POSITIONS`](../api/macros/json_diagnostic_positions.md) enabled,
-  [`materialize()`](../api/basic_json_view/materialize.md) does not set them. The index has the start offset of every
-  value, but not the end of arrays, objects, and escaped strings, which the positions also need.
+  [`materialize()`](../api/basic_json_view/materialize.md) sets the same positions as `#!cpp basic_json::parse()`.
+  In an [editable document](../api/json_editable_document.md), a value written by an edit has none, and neither has
+  an array or object whose elements changed or whose last element has none; a `basic_json` value keeps its positions
+  when it is changed. See [`materialize()`](../api/basic_json_view/materialize.md#notes).
 - **Objects iterate in document order.** [`begin()`](../api/basic_json_view/begin.md)/
  [`end()`](../api/basic_json_view/end.md) and [`items()`](../api/basic_json_view/items.md) visit an object's
  members in the order they appear in the source text. `basic_json`'s default `object_t` is a `std::map`, which
@@ -64,6 +64,9 @@ bool parse_error(std::size_t position, const std::string& last_token, const json

 The return value of each function determines whether parsing should proceed.

+Object keys are passed to `key` decoded and validated: escape sequences are already resolved, so different spellings of
+the same name yield the same string. See [`key`](../../api/json_sax/key.md#notes) for the exact guarantees.
+
 ## Stepping through the events

 The events for a small input, step by step, and what two different handlers do with them. Press *Play* or step with *Next*:
@@ -203,7 +203,7 @@ packet-beta
 | 2-3   | `extra` | `uint16_t` | numbers: the number of integer digits (low byte) and fraction digits (high byte), 255 for more; objects: the number of their key hash index (1-based), or 0; otherwise 0 |
 | 4-7   | `off`   | `uint32_t` | where the value starts: the first byte after a string's opening quote (or its position in the buffer of decoded strings), the first byte of a number or literal, the bracket of an array or object |
 | 8-11  | `len`   | `uint32_t` | strings: the length after decoding; floats and literals: the length of the token; arrays and objects: the number of elements |
-| 12-15 | `next`  | `uint32_t` | arrays and objects: the number of nodes of the subtree, including the node itself                                              |
+| 12-15 | `next`  | `uint32_t` | arrays and objects: the number of nodes of the subtree, including the node itself; strings with escapes: the position of the opening quote in the source plus one if the document was parsed with [`JSON_DIAGNOSTIC_POSITIONS`](../api/macros/json_diagnostic_positions.md), or 0 if it was not; all other values: 0 |

 <p class="nj-table-caption" markdown>Fields of a node, by their byte offset within the 16-byte node. Integers use bytes 8-15 differently, see below.</p>

@@ -218,6 +218,12 @@ packet-beta
  step from element to element this way and skip whole subtrees in constant time.
 - **Offsets** are 32 bits wide, so a document is limited to 4294967279 bytes, 4 GiB minus 16 bytes (a margin below
  2^32 for positions one scanner step past the end of the text; `out_of_range.416`).
+- **Source positions** ([`JSON_DIAGNOSTIC_POSITIONS`](../api/macros/json_diagnostic_positions.md)) are derived by
+  [`materialize()`](../api/basic_json_view/materialize.md) and cost almost nothing while parsing: the only work is
+  storing the offset of the opening quote of a string with escapes in its `next`, which is otherwise unused. A
+  scalar's range follows from `off` and its length, a string with escapes is scanned from its opening quote (`next`) to the closing one,
+  and the end of an array or object is found by scanning from the end of its last element over whitespace, comments,
+  and a trailing comma. `materialize()` hands these positions to the SAX builder of `parse()` in place of its lexer.
 - **Large objects** (128 members or more) get a hash index for their keys after parsing
  ([`detail/view/object_index.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/view/object_index.hpp)):
  an open-addressing table whose slots hold the distance from the object's node to a key's node, so that a lookup does
@@ -277,7 +283,7 @@ Images ([`save`](../api/basic_json_document/save.md) and [`load`](../api/basic_j
 the nodes as they are: a 64-byte header (the magic bytes `NJVI`, a format version, the sizes, and reserved bytes that
 must be zero), the nodes, the text, and the decoded strings. An edited document is first written in document order, as
 the parser would have written it (without links), and the numbers of the hash indexes are cleared, since `load`
-rebuilds the indexes. So a change of the node layout is a change of the image format: it must raise `image_version`,
+rebuilds the indexes. The flag *new* is kept, as these values have no position in the text. So a change of the node layout is a change of the image format: it must raise `image_version`,
 and `load` then rejects images of other versions (`parse_error.116`) instead of misreading them.

 ## Input adapters
@@ -22,8 +22,8 @@ The class contains a port of the shortest double-to-decimal conversion of [Żmij

 The class contains a copy of [Hedley](https://nemequ.github.io/hedley/) from Evan Nemerson which is licensed as [CC0-1.0](https://creativecommons.org/publicdomain/zero/1.0/).

-The class contains an adapted version of the Eisel-Lemire algorithm, its table of powers of five, and its digit comparison for long numbers from [fast_float](https://github.com/fastfloat/fast_float) by Daniel Lemire and contributors, which is available under the [MIT License](https://opensource.org/licenses/MIT) (used here), the Apache 2.0 License, and the Boost Software License. Copyright &copy; 2021 The fast_float authors
+The class contains an adapted version of the Eisel-Lemire algorithm, its table of powers of five, its digit comparison for long numbers, and its parsing of eight digits at a time from [fast_float](https://github.com/fastfloat/fast_float) by Daniel Lemire and contributors, which is available under the [MIT License](https://opensource.org/licenses/MIT) (used here), the Apache 2.0 License, and the Boost Software License. Copyright &copy; 2021 The fast_float authors

 The view's parser (`<nlohmann/json_view.hpp>`) contains techniques and code adapted from [yyjson](https://github.com/ibireme/yyjson) by YaoYuan, which is licensed under the [MIT License](https://opensource.org/licenses/MIT) (see above): table-driven decoding of `\u` escapes and fixed-offset unrolled checks.

-The view's parser (`<nlohmann/json_view.hpp>`) validates non-ASCII strings with the vector UTF-8 check of [simdjson](https://github.com/simdjson/simdjson) by Daniel Lemire, Geoff Langdale, John Keiser, and contributors (its "lookup4" algorithm and tables, after J. Keiser and D. Lemire, "Validating UTF-8 In Less Than One Instruction Per Byte", 2021), which is available under the [MIT License](https://opensource.org/licenses/MIT) (used here) and the Apache 2.0 License. Copyright &copy; 2018-2025 The simdjson authors
+The class's lexer and the view's parser (`<nlohmann/json_view.hpp>`) validate non-ASCII strings with the vector UTF-8 check of [simdjson](https://github.com/simdjson/simdjson) by Daniel Lemire, Geoff Langdale, John Keiser, and contributors (its "lookup4" algorithm and tables, after J. Keiser and D. Lemire, "Validating UTF-8 In Less Than One Instruction Per Byte", 2021), which is available under the [MIT License](https://opensource.org/licenses/MIT) (used here) and the Apache 2.0 License. Copyright &copy; 2018-2025 The simdjson authors
@@ -19,6 +19,11 @@
 #include <type_traits> // conditional


+// The shortest-digit conversion of doubles (see zmij.hpp) and the writing of
+// its digits, including the conversion of the digits to text by Xiang JunBo
+// and the SIMD instruction sequence by Dougall Johnson, are ported from Zmij
+// by Victor Zverovich (https://github.com/vitaut/zmij, MIT license).
+//
 // SSE2 (every x86-64 CPU) and NEON (every 64-bit Arm CPU) convert the 16
 // digits of a double at once (unless JSON_NO_SIMD selects the portable code)
 #if !defined(JSON_NO_SIMD) && (defined(__x86_64__) || (defined(_M_X64) && !defined(_M_ARM64EC)))
@@ -230,7 +230,10 @@ struct diagnostic_positions
        {
            // Lexer has read the first character of the container, so
            // subtract 1 from the position to get the correct start position.
-            v.start_position = lexer->get_chars_read_total() - 1;
+            // (npos: a value without a source position, see materialize() of
+            // json_view)
+            const std::size_t read = lexer->get_chars_read_total();
+            v.start_position = read == std::string::npos ? std::string::npos : read - 1;
        }
    }

@@ -245,6 +248,12 @@ struct diagnostic_positions
        {
            // Lexer's position is past the closing brace or bracket, so set that as the end position.
            v.end_position = lexer->get_chars_read_total();
+            if (v.end_position == std::string::npos)
+            {
+                // a range has both ends or none (exception::diagnostics()
+                // prints only complete ones)
+                v.start_position = std::string::npos;
+            }
        }
    }

@@ -261,6 +270,12 @@ struct diagnostic_positions
            // The start position will be set below based on the length of the string representation
            // of the value.
            v.end_position = lexer->get_chars_read_total();
+            if (v.end_position == std::string::npos)
+            {
+                // a value without a source position
+                v.start_position = std::string::npos;
+                return;
+            }

            switch (v.type())
            {
@@ -473,8 +488,12 @@ read up to it.
@tparam Collect  whether to collect the values of containers of unknown size on
                 a stack (only for a caller that does not use the value after a
                 parse error)
+@tparam LexerType  the type of the lexer that reports the source positions
+                   (JSON_DIAGNOSTIC_POSITIONS); only diagnostic_positions uses
+                   it, so any type with its three functions works (as
+                   materialize() of json_view uses it)
 */
-template<typename BasicJsonType, typename InputAdapterType, bool Collect = false>
+template<typename BasicJsonType, typename InputAdapterType, bool Collect = false, typename LexerType = lexer<BasicJsonType, InputAdapterType>>
 class json_sax_dom_parser : public json_sax_dom_error_state
 {
  public:
@@ -483,7 +502,7 @@ class json_sax_dom_parser : public json_sax_dom_error_state
    using number_float_t = typename BasicJsonType::number_float_t;
    using string_t = typename BasicJsonType::string_t;
    using binary_t = typename BasicJsonType::binary_t;
-    using lexer_t = lexer<BasicJsonType, InputAdapterType>;
+    using lexer_t = LexerType;

    /*!
    @param[in,out] r  reference to a JSON value that is manipulated while
@@ -44,6 +44,13 @@
 // use std::from_chars or std::strtold. They are free functions so the lexer
 // stays focused on scanning (see lexer::convert_number()) and so that other
 // parsers of JSON text can convert tokens exactly like it does.
+//
+// The Eisel-Lemire conversion (eisel_lemire()), the digit comparison for the
+// cases it cannot decide, and the eight-digits-at-a-time helpers
+// (is_eight_digits(), parse_eight_digits()) are adapted from fast_float
+// (https://github.com/fastfloat/fast_float, Daniel Lemire and contributors,
+// available under the MIT, Apache 2.0, and Boost Software licenses; used here
+// under the MIT license). The table of powers of five is in pow5_table.hpp.

 NLOHMANN_JSON_NAMESPACE_BEGIN
 namespace detail
@@ -56,8 +56,8 @@ using parser_callback_t =
 template<typename SAX>
 struct sax_ignores_number_text : std::false_type {};

-template<typename BasicJsonType, typename InputAdapterType, bool Collect>
-struct sax_ignores_number_text<json_sax_dom_parser<BasicJsonType, InputAdapterType, Collect>> : std::true_type {};
+template<typename BasicJsonType, typename InputAdapterType, bool Collect, typename LexerType>
+struct sax_ignores_number_text<json_sax_dom_parser<BasicJsonType, InputAdapterType, Collect, LexerType>> : std::true_type {};

 template<typename BasicJsonType, typename InputAdapterType>
 struct sax_ignores_number_text<json_sax_dom_callback_parser<BasicJsonType, InputAdapterType>> : std::true_type {};
@@ -30,6 +30,13 @@
 // NLOHMANN_JSON_NO_TARGET_ATTRIBUTE (for compilers that ignore the target
 // attribute and then reject the SSSE3 intrinsics) keeps the check portable
 // without disabling the SSE2 code.
+//
+// The vector UTF-8 check (utf8_lookup4) is adapted from simdjson
+// (https://github.com/simdjson/simdjson, Daniel Lemire, Geoff Langdale, John
+// Keiser, and contributors, available under the Apache 2.0 and MIT licenses;
+// used here under the MIT license): the "lookup4" algorithm and tables of
+// J. Keiser and D. Lemire, "Validating UTF-8 In Less Than One Instruction Per
+// Byte" (2021).
 #if !defined(JSON_NO_SIMD) && defined(__aarch64__) && (defined(__GNUC__) || defined(__clang__)) && defined(__BYTE_ORDER__) && defined(__ORDER_LITTLE_ENDIAN__) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
    #include <arm_neon.h>
    #define JSON_SCAN_NEON 1
@@ -266,6 +266,13 @@ class json_pointer
    /// @sa https://json.nlohmann.me/api/json_pointer/operator_slasheq/
    json_pointer& operator/=(const json_pointer& ptr)
    {
+        // insert() must not be given iterators into the vector it inserts
+        // into: append a copy when a pointer is appended to itself
+        if (JSON_HEDLEY_UNLIKELY(&ptr == this))
+        {
+            return *this /= json_pointer(ptr);
+        }
+
        reference_tokens.insert(reference_tokens.end(),
                                ptr.reference_tokens.begin(),
                                ptr.reference_tokens.end());
@@ -173,31 +173,16 @@ class builder
        }
        if (p[1] == '/')
        {
-            p += 2;
-            // (as in parse(), a null byte is the end of the input, so it is
-            // left for the caller to see)
-            while (p != m_end && *p != '\n' && *p != '\r' && !(NulIsEnd && *p == 0))
-            {
-                ++p;
-            }
-            return p;
+            return skip_line_comment<NulIsEnd>(p + 2, m_end);
        }
        if (p[1] == '*')
        {
-            p += 2;
-            for (;;)
+            p = find_block_comment_end<NulIsEnd>(p + 2, m_end);
+            if (p == m_end || *p != '*')
            {
-                if (p == m_end || (NulIsEnd && *p == 0))
-                {
-                    return fail_at(error_code::comment_unterminated, p);
-                }
-                if (*p == '*' && p + 1 != m_end && p[1] == '/')
-                {
-                    p += 2;
-                    return p;
-                }
-                ++p;
+                return fail_at(error_code::comment_unterminated, p);
            }
+            return p + 2;
        }
        ++p;
        return fail_at(error_code::comment_start, p);
@@ -1193,7 +1178,14 @@ indent_done:
                return false;
            }
            p = r.p;
-            push_node(node_kind::string, node_flags::escaped, 0, r.start, r.len);
+#if JSON_DIAGNOSTIC_POSITIONS
+            // the decoded string is in the arena: next keeps the source offset
+            // of the opening quote plus one (0: unknown) for materialize()
+            const std::uint64_t second = static_cast<std::uint64_t>(r.len) | (static_cast<std::uint64_t>(s - b) << 32);
+#else
+            const std::uint64_t second = r.len;
+#endif
+            push_node(node_kind::string, node_flags::escaped, 0, r.start, second);
            return true;
        }
    };
@@ -26,6 +26,7 @@
 #include <nlohmann/detail/view/lookup.hpp>
 #include <nlohmann/detail/view/macro_scope.hpp>
 #include <nlohmann/detail/view/node.hpp>
+#include <nlohmann/detail/view/scan.hpp>
 #include <nlohmann/detail/view/view_mode.hpp>

 NLOHMANN_JSON_NAMESPACE_BEGIN
@@ -46,10 +47,9 @@ struct first_true<false, Conditions...> : std::integral_constant < int, 1 + firs
 /// (type_error.316 with the same message), so that an editable document
 /// only holds valid UTF-8: the error is at the first byte that no
 /// well-formed sequence can continue with (Unicode, Table 3-7).
-inline void check_utf8(const char* s, std::size_t n)
+NLOHMANN_VIEW_ALWAYS_INLINE void check_utf8_bytewise(const unsigned char* p, std::size_t n, std::size_t i)
 {
-    const auto* const p = reinterpret_cast<const unsigned char*>(s); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-    for (std::size_t i = 0; i < n;)
+    while (i < n)
    {
        const unsigned char c = p[i];
        if (c < 0x80)
@@ -79,6 +79,43 @@ inline void check_utf8(const char* s, std::size_t n)
    }
 }

+/// The long-string path of check_utf8(): skips well-formed runs with the
+/// parser's string scan (which stops at a quote, a backslash, or a control
+/// character, all legal here, and at ill-formed UTF-8); the byte-wise check
+/// runs only from where the scan found ill-formed UTF-8, to report it.
+NLOHMANN_VIEW_NOINLINE inline void check_utf8_scan(const unsigned char* p, std::size_t n)
+{
+    const unsigned char* const e = p + n;
+    const unsigned char* q = p;
+    for (;;)
+    {
+        q = scan_string_run<true>(q, e);
+        if (q == e)
+        {
+            return;
+        }
+        if (*q >= 0x80)
+        {
+            check_utf8_bytewise(p, n, static_cast<std::size_t>(q - p));
+            return; // not reached: the scan stopped at ill-formed UTF-8
+        }
+        ++q; // a quote, backslash, or control character
+    }
+}
+
+inline void check_utf8(const char* s, std::size_t n)
+{
+    const auto* const p = reinterpret_cast<const unsigned char*>(s); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+    if (NLOHMANN_VIEW_UNLIKELY(n >= 32))
+    {
+        check_utf8_scan(p, n);
+        return;
+    }
+    // short strings: the vector scan costs more than it saves; (the loop is
+    // inlined with a constant start, so this path is the plain byte-wise check)
+    check_utf8_bytewise(p, n, 0);
+}
+
 /*!
@brief the edits of an editable basic_json_document

@@ -80,7 +80,8 @@ constexpr std::uint64_t image_limit = 0xFFFFFFF0u;
 /// Copy the current structure of an edited document into nodes in document
 /// order, as the parser would have written them. Text written by edits is
 /// appended to text_tail (number tokens) and arena_tail (strings); floats that
-/// are not finite become null, as dump() writes them.
+/// are not finite become null, as dump() writes them. Nodes keep the flag
+/// is_new: they have no source position (JSON_DIAGNOSTIC_POSITIONS).
 inline void compact_nodes(const document_data& d, std::size_t arena_size, std::vector<node>& out, std::string& text_tail, std::string& arena_tail)
 {
    struct frame
@@ -103,16 +104,18 @@ inline void compact_nodes(const document_data& d, std::size_t arena_size, std::v
            arena_tail.append(d.str(s), s.len);
            r.flags = node_flags::escaped;
        }
+        r.flags = static_cast<std::uint8_t>(r.flags | (s.flags & node_flags::is_new));
        return r;
    };
    const auto copy_node = [&](const node * v)
    {
        node r = *v;
+        const auto is_new = static_cast<std::uint8_t>(v->flags & node_flags::is_new);
        switch (static_cast<value_t>(v->kind))
        {
            case value_t::object:
            case value_t::array:
-                r.flags = 0;
+                r.flags = is_new;
                r.extra = 0;
                r.off = (v->flags & (node_flags::moved | node_flags::is_new)) != 0 ? 0 : v->off;
                r.len = 0;  // counted below
@@ -129,7 +132,7 @@ inline void compact_nodes(const document_data& d, std::size_t arena_size, std::v
                    r.off = static_cast<std::uint32_t>(d.size + text_tail.size());
                    text_tail.append(d.str(*v), number_length(*v));
                }
-                r.flags = 0;
+                r.flags = is_new;
                break;
            case value_t::number_float:
                if ((v->flags & node_flags::storage) == node_flags::edited)
@@ -139,22 +142,23 @@ inline void compact_nodes(const document_data& d, std::size_t arena_size, std::v
                    {
                        r = node{}; // nan and infinity: null, as dump() writes them
                        r.kind = node_kind::null;
+                        r.flags = is_new;
                        break;
                    }
                    r.off = static_cast<std::uint32_t>(d.size + text_tail.size());
                    text_tail.append(t, v->len);
                    r.extra = 0xFFFFu; // the digit layout is not recorded
                }
-                r.flags = 0;
+                r.flags = is_new;
                break;
            case value_t::boolean:
-                r.flags = static_cast<std::uint8_t>(v->flags & node_flags::is_true);
+                r.flags = static_cast<std::uint8_t>(v->flags & (node_flags::is_true | node_flags::is_new));
                break;
            case value_t::null:
            case value_t::binary:
            case value_t::discarded:
            default:
-                r.flags = 0;
+                r.flags = is_new;
                break;
        }
        out.push_back(r);
@@ -254,6 +258,81 @@ struct number_token
    bool is_float; ///< a fraction or an exponent
 };

+/// advance over ASCII digits, eight bytes at a time
+inline const unsigned char* digit_run(const unsigned char* p, const unsigned char* e) noexcept
+{
+    constexpr std::uint64_t ones = 0x0101010101010101ull;
+    while (e - p >= 8)
+    {
+        // (the digits become 0..9; a byte above 9, or with bit 7 set, is no digit. A carry
+        // out of a byte with bit 7 set only affects the bytes above, after the first one
+        // that count_trailing_zeros finds.)
+        const std::uint64_t x = read_eight_bytes(p) ^ (ones * 0x30u);
+        const std::uint64_t not_digit = ((x + (ones * 0x76u)) | x) & (ones * 0x80u);
+        if (not_digit != 0)
+        {
+            return p + (static_cast<std::size_t>(count_trailing_zeros(not_digit)) / 8);
+        }
+        p += 8;
+    }
+    while (p != e && is_digit(*p))
+    {
+        ++p;
+    }
+    return p;
+}
+
+/// whether the n bytes at p are ASCII digits (n > 0)
+inline bool all_digits(const unsigned char* p, std::size_t n) noexcept
+{
+    const auto digits = [](const unsigned char* q)
+    {
+        constexpr std::uint64_t ones = 0x0101010101010101ull;
+        const std::uint64_t x = read_eight_bytes(q) ^ (ones * 0x30u);
+        return (((x + (ones * 0x76u)) | x) & (ones * 0x80u)) == 0;
+    };
+    if (n >= 8)
+    {
+        for (std::size_t i = 0; i + 8 < n; i += 8)
+        {
+            if (!digits(p + i))
+            {
+                return false;
+            }
+        }
+        return digits(p + n - 8); // (overlapping the bytes before: they are digits)
+    }
+    for (std::size_t i = 0; i < n; ++i)
+    {
+        if (!is_digit(p[i]))
+        {
+            return false;
+        }
+    }
+    return true;
+}
+
+/// Whether a float token has the shape that the parser records for most of
+/// them: [-]digits.digits, with the numbers of digits of the node's layout
+/// (extra). Then the token is a number of that layout, and the general scan
+/// that follows is not needed.
+inline bool plain_float_token(const unsigned char* s, std::size_t len, std::uint16_t extra) noexcept
+{
+    const std::size_t int_digits = extra & 0xFFu;
+    const std::size_t frac_digits = extra >> 8u;
+    if (int_digits == 0 || int_digits >= 255 || frac_digits == 0 || frac_digits >= 255 || len == 0)
+    {
+        return false;
+    }
+    const std::size_t negative = *s == '-' ? 1 : 0;
+    if (len != negative + int_digits + 1 + frac_digits)
+    {
+        return false;
+    }
+    const unsigned char* const p = s + negative;
+    return !(int_digits > 1 && *p == '0') && p[int_digits] == '.' && all_digits(p, int_digits) && all_digits(p + int_digits + 1, frac_digits);
+}
+
 /// whether [s, s + len) is a JSON number (the grammar the parser accepts)
 inline bool scan_number_token(const unsigned char* s, std::size_t len, number_token& t)
 {
@@ -272,11 +351,7 @@ inline bool scan_number_token(const unsigned char* s, std::size_t len, number_to
    }
    else if (*p >= '1' && *p <= '9')
    {
-        do
-        {
-            ++p;
-        }
-        while (p != e && is_digit(*p));
+        p = digit_run(p + 1, e);
    }
    else
    {
@@ -288,10 +363,7 @@ inline bool scan_number_token(const unsigned char* s, std::size_t len, number_to
    if (p != e && *p == '.')
    {
        const unsigned char* const f0 = ++p;
-        while (p != e && is_digit(*p))
-        {
-            ++p;
-        }
+        p = digit_run(p, e);
        if (p == f0)
        {
            return false;
@@ -402,10 +474,15 @@ struct float_range
 template<typename Check>
 bool check_distinct_ranges(std::vector<byte_range>& ranges, Check check)
 {
-    std::sort(ranges.begin(), ranges.end(), [](const byte_range & a, const byte_range & b)
+    // (save() writes the ranges in the order of the nodes, which is sorted already)
+    const auto before = [](const byte_range & a, const byte_range & b)
    {
        return a.off != b.off ? a.off < b.off : a.len < b.len;
-    });
+    };
+    if (!std::is_sorted(ranges.begin(), ranges.end(), before))
+    {
+        std::sort(ranges.begin(), ranges.end(), before);
+    }
    std::size_t end = 0;
    for (std::size_t i = 0; i < ranges.size(); ++i)
    {
@@ -427,7 +504,8 @@ bool check_distinct_ranges(std::vector<byte_range>& ranges, Check check)
 /// record layouts that match it), tokens must not overlap.
 inline bool check_float_ranges(std::vector<float_range>& ranges, const unsigned char* text)
 {
-    std::sort(ranges.begin(), ranges.end(), [](const float_range & a, const float_range & b)
+    // (save() writes the tokens in the order of the nodes, which is sorted already)
+    const auto before = [](const float_range & a, const float_range & b)
    {
        if (a.off != b.off)
        {
@@ -438,7 +516,11 @@ inline bool check_float_ranges(std::vector<float_range>& ranges, const unsigned
            return a.len < b.len;
        }
        return a.extra < b.extra;
-    });
+    };
+    if (!std::is_sorted(ranges.begin(), ranges.end(), before))
+    {
+        std::sort(ranges.begin(), ranges.end(), before);
+    }
    std::size_t end = 0;
    std::size_t i = 0;
    while (i < ranges.size())
@@ -448,14 +530,18 @@ inline bool check_float_ranges(std::vector<float_range>& ranges, const unsigned
        {
            return false;
        }
-        number_token t{};
        const unsigned char* const s = text + r.off;
-        if (!scan_number_token(s, r.len, t) || !float_token_finite(s, r.len, t))
+        std::uint16_t layout = r.extra;
+        if (!plain_float_token(s, r.len, r.extra))
        {
-            return false;
+            number_token t{};
+            if (!scan_number_token(s, r.len, t) || !float_token_finite(s, r.len, t))
+            {
+                return false;
+            }
+            // the digit layout the parser records (or "many", as compaction writes it)
+            layout = float_layout(t);
        }
-        // the digit layout the parser records (or "many", as compaction writes it)
-        const std::uint16_t layout = float_layout(t);
        for (; i < ranges.size() && ranges[i].off == r.off && ranges[i].len == r.len; ++i)
        {
            if (ranges[i].extra != layout && ranges[i].extra != 0xFFFFu)
@@ -515,13 +601,15 @@ inline bool check_image(const node* nodes, std::size_t count, const unsigned cha
    std::vector<float_range> floats;
    const auto check_string = [&](const node & n) -> bool
    {
-        if ((n.flags & ~node_flags::escaped) != 0 || n.extra != 0)
+        if ((n.flags & ~(node_flags::escaped | node_flags::is_new)) != 0 || n.extra != 0)
        {
            return false;
        }
        const bool decoded = (n.flags & node_flags::escaped) != 0;
        const std::size_t limit = decoded ? arena_size : text_size;
-        if (n.off > limit || n.len > limit - n.off)
+        // (next: the source offset of a decoded string's opening quote plus
+        // one, or 0; see node)
+        if (n.off > limit || n.len > limit - n.off || n.next > text_size)
        {
            return false;
        }
@@ -593,13 +681,13 @@ inline bool check_image(const node* nodes, std::size_t count, const unsigned cha
        {
            case value_t::null:
                // (the offset of a literal is read to size the output of dump())
-                if (n.flags != 0 || n.extra != 0 || n.off > text_size)
+                if ((n.flags & ~node_flags::is_new) != 0 || n.extra != 0 || n.off > text_size)
                {
                    return false;
                }
                break;
            case value_t::boolean:
-                if ((n.flags & ~node_flags::is_true) != 0 || n.extra != 0 || n.off > text_size)
+                if ((n.flags & ~(node_flags::is_true | node_flags::is_new)) != 0 || n.extra != 0 || n.off > text_size)
                {
                    return false;
                }
@@ -613,7 +701,7 @@ inline bool check_image(const node* nodes, std::size_t count, const unsigned cha
            case value_t::number_integer:
            case value_t::number_unsigned:
            case value_t::number_float:
-                if (n.flags != 0 || !number_in_bounds(n))
+                if ((n.flags & ~node_flags::is_new) != 0 || !number_in_bounds(n))
                {
                    return false;
                }
@@ -635,7 +723,7 @@ inline bool check_image(const node* nodes, std::size_t count, const unsigned cha
            case value_t::object:
            {
                const std::size_t limit = stack.empty() ? count : stack.back().end;
-                if (n.flags != 0 || n.extra != 0 || n.next == 0 || n.next > limit - i || n.off > text_size)
+                if ((n.flags & ~node_flags::is_new) != 0 || n.extra != 0 || n.next == 0 || n.next > limit - i || n.off > text_size)
                {
                    return false;
                }
@@ -19,6 +19,7 @@
 #include <nlohmann/detail/view/macro_scope.hpp>
 #include <nlohmann/detail/view/node.hpp>
 #include <nlohmann/detail/view/number.hpp>
+#include <nlohmann/detail/view/scan.hpp>

 NLOHMANN_JSON_NAMESPACE_BEGIN
 namespace detail
@@ -26,6 +27,189 @@ namespace detail
 namespace view
 {

+#if JSON_DIAGNOSTIC_POSITIONS
+/*!
+@brief the source positions of the values materialize() replays
+
+Stands in for the lexer of json_sax_dom_parser, which reads the positions of
+the values it stores from these three functions (diagnostic_positions). npos
+is a value without a source position. One position_source serves a whole
+materialize() call: before each value is handed to the handler, the range of
+that value is set (or cleared), overwriting that of the value before.
+*/
+struct position_source
+{
+    /// the token, of which diagnostic_positions only reads the length
+    struct token
+    {
+        std::size_t length;
+        std::size_t size() const noexcept
+        {
+            return length;
+        }
+    };
+
+    std::size_t start = std::string::npos; ///< the first byte of the next value
+    std::size_t end = std::string::npos;   ///< one past the next value (start_object/start_array: one past the bracket)
+
+    std::size_t get_chars_read_total() const noexcept
+    {
+        return end;
+    }
+    std::size_t get_token_start_position() const noexcept
+    {
+        return start;
+    }
+    token get_string() const noexcept
+    {
+        return token{end - start};
+    }
+
+    /// the range [first, last), or none if either is npos
+    void set(std::size_t first, std::size_t last) noexcept
+    {
+        if (first == std::string::npos || last == std::string::npos)
+        {
+            clear();
+            return;
+        }
+        start = first;
+        end = last;
+    }
+
+    /// no range: the next value has no source position
+    void clear() noexcept
+    {
+        start = std::string::npos;
+        end = std::string::npos;
+    }
+
+    /// one past the closing quote of the string whose opening quote is at
+    /// src[quote], or npos (the scan is bounded by size, as images can be
+    /// loaded without a check)
+    static std::size_t string_end(const char* src, std::size_t size, std::size_t quote) noexcept
+    {
+        for (std::size_t i = quote + 1; i < size; ++i)
+        {
+            if (src[i] == '\\')
+            {
+                ++i;
+            }
+            else if (src[i] == '"')
+            {
+                return i + 1;
+            }
+        }
+        return std::string::npos;
+    }
+
+    /// one past the closing bracket of the array or object whose last element
+    /// ends at src[pos] (or whose opening bracket is at src[pos - 1]), or npos;
+    /// in between, there can only be whitespace, comments, and a trailing comma
+    /// (the source was validated when it was parsed)
+    static std::size_t container_end(const char* src, std::size_t size, std::size_t pos) noexcept
+    {
+        const auto* const b = reinterpret_cast<const unsigned char*>(src); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast): the text as bytes, as the builder reads it
+        const unsigned char* const e = b + size;
+        while (pos < size)
+        {
+            switch (src[pos])
+            {
+                case ' ':
+                case '\t':
+                case '\n':
+                case '\r':
+                case ',':
+                    ++pos;
+                    break;
+                case ']':
+                case '}':
+                    return pos + 1;
+                case '/':
+                    if (pos + 1 < size && src[pos + 1] == '/')
+                    {
+                        pos = static_cast<std::size_t>(skip_line_comment(b + pos + 2, e) - b);
+                        break;
+                    }
+                    if (pos + 1 < size && src[pos + 1] == '*')
+                    {
+                        // (unterminated: pos is size, which ends the loop)
+                        pos = static_cast<std::size_t>(find_block_comment_end(b + pos + 2, e) - b) + 2;
+                        break;
+                    }
+                    return std::string::npos;
+                default:
+                    return std::string::npos;
+            }
+        }
+        return std::string::npos;
+    }
+
+    /// the range of the scalar n of document d
+    void set_scalar(const document_data& d, const node& n) noexcept
+    {
+        if ((n.flags & node_flags::is_new) != 0)
+        {
+            clear();
+            return;
+        }
+        std::size_t first = std::string::npos;
+        std::size_t last = std::string::npos;
+        switch (n.kind)
+        {
+            case node_kind::string:
+                if ((n.flags & node_flags::storage) == 0)
+                {
+                    // off is the first byte after the opening quote
+                    if (n.off != 0)
+                    {
+                        first = n.off - 1;
+                        last = n.off + std::size_t{n.len} + 1;
+                    }
+                }
+                else if ((n.flags & node_flags::storage) == node_flags::escaped && n.next != 0)
+                {
+                    // next is the offset of the opening quote plus one
+                    first = n.next - 1;
+                    last = string_end(d.base[0], d.size, first);
+                }
+                break;
+            case node_kind::number_integer:
+            case node_kind::number_unsigned:
+            case node_kind::number_float:
+                if ((n.flags & node_flags::storage) == 0)
+                {
+                    first = n.off;
+                    last = n.off + number_length(n);
+                }
+                break;
+            case node_kind::boolean:
+                first = n.off;
+                last = n.off + ((n.flags & node_flags::is_true) != 0 ? 4u : 5u);
+                break;
+            case node_kind::null:
+                first = n.off;
+                last = n.off + 4u;
+                break;
+            case node_kind::object:
+            case node_kind::array:
+            case node_kind::link:
+            default:
+                break;
+        }
+        // (a crafted image can point past the text)
+        if (last == std::string::npos || last > d.size)
+        {
+            clear();
+        }
+        else
+        {
+            set(first, last);
+        }
+    }
+};
+#endif
+
 /*!
@brief the basic_json value of the subtree at n

@@ -33,14 +217,24 @@ The subtree is replayed into the SAX handler that parse() uses to build its
 values, so the result is the value parse() would produce: duplicate keys keep
 the last value, and with JSON_DIAGNOSTICS the parent pointers are set. It is
 iterative, so the nesting depth is limited by memory only, as for parse().
-Without a lexer the handler records no source positions
-(JSON_DIAGNOSTIC_POSITIONS).
+
+With JSON_DIAGNOSTIC_POSITIONS, the values get their source positions as with
+parse(): position_source stands in for the lexer. Values written by edits have
+none (npos), and neither has an array or object whose elements changed, or
+whose last element has none (the end of its closing bracket is found by
+scanning from the end of the last element).
 */
 template<typename BasicJsonType, bool Editable>
 BasicJsonType materialize(const document_data& d, const node* n)
 {
    using string_t = typename BasicJsonType::string_t;
-    using sax_t = json_sax_dom_parser<BasicJsonType, iterator_input_adapter<const char*>, true>;
+    using input_t = iterator_input_adapter<const char*>;
+#if JSON_DIAGNOSTIC_POSITIONS
+    using lexer_t = position_source;
+#else
+    using lexer_t = lexer<BasicJsonType, input_t>; // (the default: unused, as no lexer is passed)
+#endif
+    using sax_t = json_sax_dom_parser<BasicJsonType, input_t, true, lexer_t>;
    using nav = navigation<Editable>;

    // the open containers: their next element (or key of the next member),
@@ -52,9 +246,15 @@ BasicJsonType materialize(const document_data& d, const node* n)
        const node* pos;
        const node* end;
        bool object;
+#if JSON_DIAGNOSTIC_POSITIONS
+        std::size_t start;    ///< the opening bracket (npos: unknown)
+        std::size_t last_end; ///< the end of the last element read (npos: unknown)
+#endif
    };

+#if !JSON_DIAGNOSTIC_POSITIONS
    // a scalar needs neither the handler nor the stack of open containers
+    // (with positions, it goes through the handler, which sets them)
    switch (static_cast<value_t>(n->kind))
    {
        case value_t::string:
@@ -76,10 +276,16 @@ BasicJsonType materialize(const document_data& d, const node* n)
        default:
            break;
    }
+#endif

    BasicJsonType result;
+#if JSON_DIAGNOSTIC_POSITIONS
+    position_source positions;
+    sax_t sax(result, true, &positions);
+#else
    sax_t sax(result, true);
-    const string_t no_token{};
+#endif
+    const string_t no_token {};
    // (shallow subtrees on the stack: a call for a small value then allocates only for the value)
    std::array<frame, 16> shallow; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): filled as containers open
    std::vector<frame> deep{};
@@ -94,6 +300,16 @@ BasicJsonType materialize(const document_data& d, const node* n)
    std::size_t depth = 0;
    for (;;)
    {
+#if JSON_DIAGNOSTIC_POSITIONS
+        if (!is_container(*n))
+        {
+            positions.set_scalar(d, *n);
+            if (depth != 0)
+            {
+                open[depth - 1].last_end = positions.end;
+            }
+        }
+#endif
        // false positive: n comes from nav::value(), which never returns null for a valid index
        // @infer-ignore NULLPTR_DEREFERENCE
        switch (static_cast<value_t>(n->kind))
@@ -102,6 +318,17 @@ BasicJsonType materialize(const document_data& d, const node* n)
            case value_t::array:
            {
                const bool object = n->kind == node_kind::object;
+#if JSON_DIAGNOSTIC_POSITIONS
+                // (moved containers are also new)
+                if ((n->flags & node_flags::is_new) != 0 || n->off >= d.size)
+                {
+                    positions.clear();
+                }
+                else
+                {
+                    positions.set(std::size_t{n->off}, std::size_t{n->off} + 1);
+                }
+#endif
                if (object)
                {
                    sax.start_object(n->len);
@@ -118,7 +345,13 @@ BasicJsonType materialize(const document_data& d, const node* n)
                    open = deep.data();
                    capacity = deep.size();
                }
-                open[depth++] = frame{nav::first(d, n), nav::end(d, n), object};
+                // (with positions: until an element is read, the container's
+                // own bracket is the last thing read)
+                open[depth++] = frame{nav::first(d, n), nav::end(d, n), object
+#if JSON_DIAGNOSTIC_POSITIONS
+                                      , positions.start, positions.end
+#endif
+                                     };
                break;
            }
            case value_t::string:
@@ -159,6 +392,31 @@ BasicJsonType materialize(const document_data& d, const node* n)
            frame& f = open[depth - 1];
            if (f.pos == f.end)
            {
+#if JSON_DIAGNOSTIC_POSITIONS
+                if (f.start == std::string::npos || f.last_end == std::string::npos)
+                {
+                    positions.clear();
+                }
+                else
+                {
+                    const std::size_t end = position_source::container_end(d.base[0], d.size, f.last_end);
+                    if (end == std::string::npos)
+                    {
+                        positions.clear();
+                    }
+                    else
+                    {
+                        // the closing bracket, as the lexer reports it (end_object()
+                        // and end_array() only read its end; the start of the
+                        // container was set when it was opened)
+                        positions.set(end - 1, end);
+                    }
+                }
+                if (depth > 1)
+                {
+                    open[depth - 2].last_end = positions.end;
+                }
+#endif
                if (f.object)
                {
                    sax.end_object();
@@ -69,7 +69,7 @@ struct node
    std::uint16_t extra; ///< numbers: integer digits (low byte) and fraction digits (high byte), 255 = "many"; objects: number of the object's key hash index (1-based, 0 = none); otherwise 0
    std::uint32_t off;   ///< source offset (string content, number token, literal, bracket); arena offset if escaped/edited; number of the element sequence if moved
    std::uint32_t len;   ///< string: decoded bytes; float: token bytes; array/object: element count
-    std::uint32_t next;  ///< array/object: number of nodes of the subtree (its extent in the enclosing sequence)
+    std::uint32_t next;  ///< array/object: number of nodes of the subtree (its extent in the enclosing sequence); escaped string: source offset of the opening quote plus one (JSON_DIAGNOSTIC_POSITIONS; 0: unknown)
 };
 static_assert(sizeof(node) == 16, "node must stay 16 bytes");

@@ -19,7 +19,6 @@
 #include <nlohmann/detail/view/macro_scope.hpp>
 #include <nlohmann/detail/view/node.hpp>
 #include <nlohmann/detail/view/scan.hpp>
-#include <nlohmann/detail/view/simd.hpp>

 NLOHMANN_JSON_NAMESPACE_BEGIN
 namespace detail
@@ -104,56 +103,12 @@ NLOHMANN_VIEW_NOINLINE FloatType float_value(const char* first, const node& n)
    return convert_float<FloatType>(first, last, dot, mantissa_end);
 }

-#if NLOHMANN_VIEW_VECTOR
-/*!
-@brief the value of the first 16 digits of a run of digits with a point after
-int_digits of them (or none, if int_digits >= 16)
-
-The 17 bytes at p are read at once: the bytes after the point move down by one,
-then pairs, quadruples, and octets of digits are combined by multiplications
-(after simdjson). The bytes [p, p + 32) must be readable. Bytes that are not
-digits (only in a damaged image loaded with image_check::bounds) give a wrong
-value, but no undefined behavior.
-*/
-NLOHMANN_VIEW_ALWAYS_INLINE std::uint64_t sixteen_digits(const unsigned char* p, unsigned int_digits) noexcept
-{
-#if NLOHMANN_VIEW_NEON
-    const uint8x16_t low = vld1q_u8(p);
-    const uint8x16_t index = vcombine_u8(vcreate_u8(0x0706050403020100u), vcreate_u8(0x0F0E0D0C0B0A0908u));
-    const uint8x16_t before_point = vcltq_u8(index, vdupq_n_u8(static_cast<std::uint8_t>(int_digits)));
-    const uint8x16_t digits = vsubq_u8(vbslq_u8(before_point, low, vextq_u8(low, vld1q_u8(p + 16), 1)), vdupq_n_u8('0'));
-    const uint16x8_t twos = vpaddlq_u8(vmulq_u8(digits, vreinterpretq_u8_u16(vdupq_n_u16(0x010A))));
-    const uint32x4_t fours = vpaddlq_u16(vmulq_u16(twos, vreinterpretq_u16_u32(vdupq_n_u32(0x00010064))));
-    const uint64x2_t eights = vpaddlq_u32(vmulq_u32(fours, vreinterpretq_u32_u64(vdupq_n_u64(0x0000000100002710u))));
-    return (vgetq_lane_u64(eights, 0) * 100000000u) + vgetq_lane_u64(eights, 1);
-#else
-    // NOLINTBEGIN(portability-simd-intrinsics)
-    const __m128i low = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(p))); // NOLINT(bugprone-casting-through-void)
-    const __m128i high = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(p + 16))); // NOLINT(bugprone-casting-through-void)
-    const __m128i before_point = _mm_cmpgt_epi8(_mm_set1_epi8(static_cast<char>(int_digits)), _mm_setr_epi8(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15));
-    const __m128i moved = _mm_or_si128(_mm_srli_si128(low, 1), _mm_slli_si128(high, 15));
-    const __m128i digits = _mm_sub_epi8(_mm_or_si128(_mm_and_si128(before_point, low), _mm_andnot_si128(before_point, moved)), _mm_set1_epi8('0'));
-    // (16-bit lanes: SSE2 has no multiply-add of bytes)
-    const __m128i tens = _mm_setr_epi16(10, 1, 10, 1, 10, 1, 10, 1);
-    const __m128i twos = _mm_packs_epi32(_mm_madd_epi16(_mm_unpacklo_epi8(digits, _mm_setzero_si128()), tens),
-                                         _mm_madd_epi16(_mm_unpackhi_epi8(digits, _mm_setzero_si128()), tens));
-    const __m128i fours = _mm_madd_epi16(twos, _mm_setr_epi16(100, 1, 100, 1, 100, 1, 100, 1));
-    const __m128i eights = _mm_madd_epi16(_mm_packs_epi32(fours, fours), _mm_setr_epi16(10000, 1, 10000, 1, 10000, 1, 10000, 1));
-    const auto upper = static_cast<std::uint32_t>(_mm_cvtsi128_si32(eights));
-    const auto lower = static_cast<std::uint32_t>(_mm_cvtsi128_si32(_mm_srli_si128(eights, 4)));
-    // NOLINTEND(portability-simd-intrinsics)
-    return (std::uint64_t{upper} * 100000000u) + lower;
-#endif
-}
-#endif
-
 /*!
@brief the digits of a float token with at most 19 digits, from its layout

 The digit layout recorded while parsing says where the integer digits, the
 fraction digits, and the exponent are, so the digits are read eight at a
-time without scanning (with SIMD, a token of 16 to 19 digits sixteen at a
-time).
+time without scanning.

@param[in] p  first character of the token
@param[in] e  end of the token
@@ -163,34 +118,15 @@ NLOHMANN_VIEW_ALWAYS_INLINE float_significand layout_decimal(const unsigned char
 {
    const bool negative = *p == '-';
    p += negative ? 1 : 0;
-    std::uint64_t w = 0;
+    std::uint64_t w = parse_upto19(p, int_digits, limit);
+    p += int_digits;
    std::int64_t q = 0;
-#if NLOHMANN_VIEW_VECTOR
-    const unsigned count = int_digits + frac_digits;
-    if (count >= 16 && limit - p >= 32)
+    if (frac_digits != 0)
    {
-        // (the point, if any, follows the integer digits; the digits after
-        // the first 16 are at most three)
-        w = sixteen_digits(p, int_digits);
-        for (unsigned i = 16; i < count; ++i)
-        {
-            w = (w * 10) + static_cast<std::uint64_t>(p[i + (i >= int_digits ? 1 : 0)] - '0');
-        }
-        p += count + (frac_digits != 0 ? 1 : 0);
+        w = (w * int_pow10(frac_digits)) + parse_upto19(p + 1, frac_digits, limit);
+        p += 1 + frac_digits;
        q = -static_cast<std::int64_t>(frac_digits);
    }
-    else /* NOLINT(readability/braces) */
-#endif
-    {
-        w = parse_upto19(p, int_digits, limit);
-        p += int_digits;
-        if (frac_digits != 0)
-        {
-            w = (w * int_pow10(frac_digits)) + parse_upto19(p + 1, frac_digits, limit);
-            p += 1 + frac_digits;
-            q = -static_cast<std::int64_t>(frac_digits);
-        }
-    }
    if (p != e)
    {
        // [eE][+-]digits; huge exponents saturate (the parser rejected
@@ -225,22 +161,12 @@ NLOHMANN_VIEW_ALWAYS_INLINE float_significand layout_decimal(const unsigned char
 The result is correctly rounded by the lexer's conversion
 (detail::decimal_to_float(): Clinger's fast path where both operands are
 exact, else the Eisel-Lemire algorithm, which needs no fallback for up to 19
-digits), so it is the value parse() produces. Tokens of 16 or more digits go
-to Eisel-Lemire directly: the fast path takes few of them (none of 17 digits),
-and its check is a branch that data like GeoJSON coordinates mispredicts.
+digits), so it is the value parse() produces.
 */
 template<typename FloatType>
 NLOHMANN_VIEW_ALWAYS_INLINE FloatType layout_float(const unsigned char* p, const unsigned char* e, unsigned int_digits, unsigned frac_digits, const unsigned char* limit) noexcept
 {
-    const float_significand d = layout_decimal(p, e, int_digits, frac_digits, limit);
-    if (int_digits + frac_digits >= 16)
-    {
-        using format = ieee_binary_format<std::numeric_limits<FloatType>::digits>;
-        native_float_t<FloatType> value{};
-        float_from_bits(eisel_lemire<format>(d.exponent, d.w) | (d.negative ? (std::uint64_t{1} << format::sign_bit()) : 0u), value);
-        return value;
-    }
-    return decimal_to_float<FloatType>(d);
+    return decimal_to_float<FloatType>(layout_decimal(p, e, int_digits, frac_digits, limit));
 }

 /// the value of a float set by an edit: its token (the shortest round-trip
@@ -259,80 +185,6 @@ NLOHMANN_VIEW_NOINLINE FloatType edited_float(const char* token, const node& n)
    return float_value<FloatType>(token, n);
 }

-#if NLOHMANN_VIEW_VECTOR
-/// eisel_lemire() for the token w * 10^q of coordinate_float()
-template<typename Format>
-NLOHMANN_VIEW_ALWAYS_INLINE std::uint64_t coordinate_bits(std::int64_t q, std::uint64_t w, Format /*format*/) noexcept
-{
-    return eisel_lemire<Format>(q, w);
-}
-
-/*!
-@brief (binary64) eisel_lemire() without the cases that tokens of 16 or 17
-digits with 5 or more after the point cannot reach: a value of 0, a
-subnormal, an infinity, or a tie (q < -4)
-*/
-NLOHMANN_VIEW_ALWAYS_INLINE std::uint64_t coordinate_bits(std::int64_t q, std::uint64_t w, ieee_binary_format<53> format) noexcept
-{
-    if (NLOHMANN_VIEW_UNLIKELY(w == 0 || q > -5))
-    {
-        return eisel_lemire<ieee_binary_format<53>>(q, w);
-    }
-    static_cast<void>(format);
-    const int lz = count_leading_zeros(w);
-    const std::uint64_t normalized = w << static_cast<unsigned>(lz);
-    const auto index = static_cast<std::size_t>(2 * (q - pow5_128_smallest_power));
-    const uint128_parts product = full_multiplication(normalized, pow5_128()[index]);
-    std::uint64_t high = product.high;
-    if (NLOHMANN_VIEW_UNLIKELY((high & 0x1FFu) == 0x1FFu))
-    {
-        // (the lower bits may carry into the result)
-        const std::uint64_t second = full_multiplication(normalized, pow5_128()[index + 1]).high;
-        high += product.low + second < product.low ? 1u : 0u;
-    }
-    const auto upperbit = static_cast<unsigned>(high >> 63u);
-    std::uint64_t mantissa = high >> (upperbit + 9);
-    auto power2 = static_cast<std::uint64_t>(((217706 * q) >> 16) + 63 + static_cast<std::int64_t>(upperbit) - lz + 1023);
-    mantissa = (mantissa + (mantissa & 1u)) >> 1u;
-    const bool carry = mantissa >= (std::uint64_t{2} << 52u);
-    mantissa = carry ? (std::uint64_t{1} << 52u) : mantissa;
-    power2 += carry ? 1u : 0u;
-    return (mantissa & ~(std::uint64_t{1} << 52u)) | (power2 << 52u);
-}
-
-/*!
-@brief (binary32 and binary64) the value of a float token of the source with
-16 or 17 digits, a point, and no exponent, the shape of most coordinates
-written with full precision; whether the token of n has this shape
-
-These tokens skip the general layout of layout_decimal(): no digits beyond
-the 17th, no exponent (and Eisel-Lemire directly, as in layout_float()).
-*/
-template<typename FloatType>
-NLOHMANN_VIEW_ALWAYS_INLINE bool coordinate_float(const document_data& d, const node& n, FloatType& value) noexcept
-{
-    const unsigned int_digits = n.extra & 0xFFu;
-    const unsigned frac_digits = n.extra >> 8u;
-    const unsigned count = int_digits + frac_digits;
-    const auto* const first = reinterpret_cast<const unsigned char*>(d.src + n.off); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-    const unsigned negative = first[0] == '-' ? 1u : 0u;
-    if (count - 16u > 1u || frac_digits == 0 || n.len != negative + count + 1 || d.size - n.off < 33)
-    {
-        return false;
-    }
-    const unsigned char* const digits = first + negative;
-    const std::uint64_t w = sixteen_digits(digits, int_digits);
-    // (the 17th digit follows the point)
-    const std::uint64_t w17 = (w * 10) + static_cast<std::uint64_t>(digits[17] - '0');
-    using format = ieee_binary_format<std::numeric_limits<FloatType>::digits>;
-    native_float_t<FloatType> result{};
-    float_from_bits(coordinate_bits(-static_cast<std::int64_t>(frac_digits), count == 17 ? w17 : w, format{}) | (static_cast<std::uint64_t>(negative) << format::sign_bit()), result);
-    value = result;
-    return true;
-}
-
-#endif
-
 /// the value of the float token of a node, as parse() converts it; floats and
 /// doubles with at most 19 digits are converted from the digit layout
 template<typename FloatType>
@@ -348,13 +200,6 @@ FloatType float_value(const document_data& d, const node& n)
 template<typename FloatType>
 FloatType float_value(const document_data& d, const node& n, std::true_type /*binary32 or binary64*/)
 {
-#if NLOHMANN_VIEW_VECTOR
-    FloatType value {};
-    if (coordinate_float(d, n, value))
-    {
-        return value;
-    }
-#endif
    const unsigned int_digits = n.extra & 0xFFu;
    const unsigned frac_digits = n.extra >> 8u;
    if (NLOHMANN_VIEW_LIKELY(int_digits + frac_digits <= 19)) // (255 marks "many")
@@ -172,6 +172,32 @@ NLOHMANN_VIEW_ALWAYS_INLINE const unsigned char* skip_digits(const unsigned char
    return p;
 }

+/// advance over the text of a line comment (after its "//") to the line
+/// break or the end (with NulIsEnd also a null byte, which is left for the
+/// caller to see, as in parse())
+template<bool NulIsEnd = false>
+inline const unsigned char* skip_line_comment(const unsigned char* p, const unsigned char* e) noexcept
+{
+    while (p != e && *p != '\n' && *p != '\r' && !(NulIsEnd && *p == 0))
+    {
+        ++p;
+    }
+    return p;
+}
+
+/// the "*/" that ends a block comment whose text starts at p (after its "/*");
+/// if it is unterminated, the end (with NulIsEnd also a null byte), which is
+/// where the caller reports the error
+template<bool NulIsEnd = false>
+inline const unsigned char* find_block_comment_end(const unsigned char* p, const unsigned char* e) noexcept
+{
+    while (p != e && !(NulIsEnd && *p == 0) && !(*p == '*' && p + 1 != e && p[1] == '/'))
+    {
+        ++p;
+    }
+    return p;
+}
+
 /// powers of ten up to 10^19 as integers
 inline std::uint64_t int_pow10(unsigned k) noexcept
 {
@@ -14,9 +14,7 @@
 #include <cstddef> // size_t
 #include <cstdint> // uint8_t, uint32_t
 #include <cstring> // memcpy, memset
-#include <functional> // less
 #include <limits> // numeric_limits
-#include <memory> // unique_ptr
 #include <type_traits> // integral_constant
 #include <vector> // vector

@@ -386,127 +384,6 @@ struct depth_counter<false>
    }
 };

-/*!
-@brief where the double x nearest to a token w * 10^q lies, for 10^15 <= w <
-10^17 and -17 <= q <= -1 (Eisel-Lemire, then a fixed-point position)
-
-dump() writes the shortest decimal in the rounding interval of x (the closest
-one if there are several, see zmij::to_shortest()). Its digits are those of a
-multiple of 10^g of the token's last digit, with g = dec_exp + 1 - q for x's
-decimal exponent dec_exp: the multiple of 10^g nearest to x if it lies in the
-interval (at most one does), else the multiple of 10^(g - 1) nearest to x
-(see token_digits_1() and token_digits_2()). For g <= 0, the token itself is
-in the interval.
-
-The position is exact in a 64-bit fixed-point number with 56 bits after the
-point (of the token's last digit): x / 10^q = 2c * 5^-q / 2^t for x = c * 2^e2
-and t = q + 1 - e2, with at most 56 bits after the point here, and |x / 10^q -
-w| is at most half the spacing of the doubles, below 12 units. So only the low
-64 bits of 2c * 5^-q are needed. c and e2 come from Eisel-Lemire's product
-directly (as eisel_lemire() rounds it: no tie is possible for q < -4, and its
-second product is added where it can carry into the result).
-
-@param[out] offset  x / 10^q - w + 32, with 56 bits after the point
-@param[out] radius  half the spacing of the doubles at x, likewise (+ 1 if
-                    the interval is closed)
-@return g; 3 if the digits are not decided here (a power of two, whose
-        interval is not symmetric, or out of range)
-*/
-NLOHMANN_VIEW_ALWAYS_INLINE int locate_token(std::uint64_t w, int q, std::uint64_t& offset, std::uint64_t& radius) noexcept
-{
-    const int lz = count_leading_zeros(w);
-    const std::uint64_t normalized = w << static_cast<unsigned>(lz);
-    const auto index = static_cast<std::size_t>(2 * (q - pow5_128_smallest_power));
-    const uint128_parts product = full_multiplication(normalized, pow5_128()[index]);
-    std::uint64_t high = product.high;
-    if (NLOHMANN_VIEW_UNLIKELY((high & 0x1FFu) == 0x1FFu))
-    {
-        // (as eisel_lemire(): the lower bits may carry into the result)
-        const std::uint64_t second = full_multiplication(normalized, pow5_128()[index + 1]).high;
-        high += product.low + second < product.low ? 1u : 0u;
-    }
-    const auto upperbit = static_cast<unsigned>(high >> 63u);
-    const std::uint64_t mantissa = high >> (upperbit + 9);
-    const std::uint64_t c = (mantissa + (mantissa & 1u)) >> 1u;
-    // e2 as eisel_lemire() computes the exponent (log2(10) ~ 217706 / 2^16)
-    const int e2 = static_cast<int>((217706 * static_cast<std::int64_t>(q)) >> 16) + 63 + static_cast<int>(upperbit) - lz - 52;
-    const int t = q + 1 - e2;
-    const int g = ((e2 * 315653) >> 20) + 1 - q; // (dec_exp as in zmij::to_shortest(), for a regular x)
-    static const std::array<std::uint64_t, 17> fives = {{1u, 5u, 25u, 125u, 625u, 3125u, 15625u, 78125u, 390625u, 1953125u, 9765625u, 48828125u, 244140625u, 1220703125u, 6103515625u, 30517578125u, 152587890625u}};
-    const std::uint64_t five = fives[static_cast<std::size_t>(-q)]; // 5^-q
-    const unsigned s = static_cast<unsigned>(56 - t) & 63u;
-    offset = ((2 * c * five) << s) - (w << 56u) + (std::uint64_t{32} << 56u);
-    radius = (five << s) + ((c & 1u) == 0 ? 1u : 0u);
-    // (c = 2^52: a power of two; c = 2^53: rounded up to one. With 8 to 16
-    // fraction digits, as the batch's tokens have, t is in [15, 40] and g at
-    // most 2. x lies halfway between two candidates only if its distance from
-    // the token is a whole unit (g == 2) or a half (g == 1): such tokens are
-    // left to the full conversion)
-    const bool decided = c - ((std::uint64_t{1} << 52u) + 1) < (std::uint64_t{1} << 52u) - 1
-                         && (offset & ((std::uint64_t{1} << 55u) - 1)) != 0;
-    return decided ? g : 3;
-}
-
-/// the distance of a position (see locate_token()) from the biased point 32
-NLOHMANN_VIEW_ALWAYS_INLINE std::uint64_t biased_distance(std::uint64_t position) noexcept
-{
-    constexpr std::uint64_t center = std::uint64_t{32} << 56u;
-    return position >= center ? position - center : center - position;
-}
-
-/*!
-@brief (g == 1) the digits dump() writes for a token, from the position of its
-double (see locate_token()): the multiple of 10 nearest to x if it is in the
-interval, else w rounded to x (an exact tie between two candidates, like
-754570942.33984373, whose double is 754570942.33984375, is excluded by
-locate_token())
-
-With |x - w| at most the radius, which is below half the spacing of the
-candidates, the multiple of 10 nearest to x is w - r10 or the one above it.
-*/
-NLOHMANN_VIEW_ALWAYS_INLINE std::uint64_t token_digits_1(std::uint64_t w, std::uint64_t offset, std::uint64_t radius, std::uint64_t r10) noexcept
-{
-    constexpr std::uint64_t one = std::uint64_t{1} << 56u;
-    const std::uint64_t from = offset + (r10 * one); // x - (w - r10) (+ 32)
-    const bool up = from > 37 * one;                  // (nearer to the multiple above)
-    const bool shorter = biased_distance(from - (up ? 10 * one : 0)) < radius;
-    const std::uint64_t a = w - r10 + (up ? 10u : 0u);
-    const std::uint64_t b = w + ((offset + (one / 2)) >> 56u) - 32;                // w rounded to x
-    return shorter ? a : b;
-}
-
-/*!
-@brief (g == 2) the digits dump() writes for a token, as token_digits_1(): the
-multiple of 100 nearest to x if it is in the interval, else the multiple of 10
-nearest to x
-*/
-NLOHMANN_VIEW_ALWAYS_INLINE std::uint64_t token_digits_2(std::uint64_t w, std::uint64_t offset, std::uint64_t radius, std::uint64_t r10, std::uint64_t r100) noexcept
-{
-    constexpr std::uint64_t one = std::uint64_t{1} << 56u;
-    const std::uint64_t from = offset + (r100 * one);
-    const bool up = from > 82 * one;
-    const bool shorter = biased_distance(from - (up ? 100 * one : 0)) < radius;
-    const std::uint64_t a = w - r100 + (up ? 100u : 0u);
-    // x - (w - r10), in [-12, 21]: the multiple of 10 nearest to x is that one,
-    // or one or two above, or one below
-    const std::uint64_t y = offset + (r10 * one);
-    const std::uint64_t steps = (y > 37 * one ? 1u : 0u) + (y > 47 * one ? 1u : 0u);
-    const bool down = y < 27 * one;
-    const std::uint64_t b = w - r10 + (10 * steps) - (down ? 10u : 0u);
-    return shorter ? a : b;
-}
-
-/// the four ASCII digits of x < 10^4, the first in the lowest byte (as
-/// little-endian memory holds them)
-NLOHMANN_VIEW_ALWAYS_INLINE std::uint32_t four_digit_text(std::uint32_t x) noexcept
-{
-    const std::uint32_t ab = (x * 5243u) >> 19u; // x / 100
-    std::uint32_t v = ab | ((x - (ab * 100u)) << 16u);
-    const std::uint32_t a = ((v * 103u) >> 10u) & 0x000F000Fu; // / 10 per 16-bit lane
-    v = a | ((v - (a * 10u)) << 8u);
-    return v + 0x30303030u;
-}
-
 /// how the view's dump() writes a value
 struct dump_style
 {
@@ -834,7 +711,6 @@ class view_serializer
        std::array<frame, 32> buffer; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
        std::vector<frame> heap;
        small_stack<frame> stack(buffer.data(), buffer.size(), heap);
-        float_batch batch;
        const char* const src = m_doc.src;
        const char* const src_end = src + m_doc.size;
        char* w = m_out.cursor();
@@ -974,7 +850,7 @@ class view_serializer
                    else if (enabled(fast_double::value))
                    {
                        room(64);
-                        w = write_double_ahead(w, src, n, batch);
+                        w = write_double_at(w, *n);
                    }
                    else
                    {
@@ -999,20 +875,6 @@ class view_serializer
                case value_t::array:
                {
                    const bool object = n->kind == node_kind::object;
-                    // (read-only documents, compact output) a pair of floats,
-                    // like the coordinates of GeoJSON, without a frame
-                    if (enabled(!Editable && !Pretty && !SourceNumbers && fast_double::value) && n->next == 3 && n->len == 2
-                            && n[1].kind == node_kind::number_float && n[2].kind == node_kind::number_float)
-                    {
-                        room(2 * 64);
-                        *w++ = '[';
-                        w = write_double_ahead(w, src, n + 1, batch);
-                        *w++ = ',';
-                        w = write_double_ahead(w, src, n + 2, batch);
-                        *w++ = ']';
-                        n += 2; // (the element before the next node)
-                        break;
-                    }
                    room(8);
                    if (n->len == 0)
                    {
@@ -1122,254 +984,6 @@ class view_serializer
        }
    }

-    /// (float_batch) the mark of digits whose rounding carried beyond the
-    /// token's last four (see mark())
-    static constexpr std::uint64_t carried() noexcept
-    {
-        return std::uint64_t{1} << 63u;
-    }
-
-    /// floats of 16 or 17 digits ahead of the walk, converted together (see
-    /// convert_ahead()), with their digits as mark() keeps them
-    struct float_batch
-    {
-        static constexpr std::size_t capacity() noexcept
-        {
-            return 256;
-        }
-        /// (on the heap, allocated by the first conversion: a frame of more
-        /// than a page made every dump of a small document slower)
-        struct entries
-        {
-            std::array<const node*, 256> at; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
-            std::array<std::uint64_t, 256> digits; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
-        };
-        std::unique_ptr<entries> storage{};
-        const node** at = nullptr;
-        std::uint64_t* digits = nullptr;
-        std::size_t count = 0;
-        std::size_t next = 0;
-        const node* scanned = nullptr; ///< where the last scan of the node array ended
-    };
-
-    /// (doubles) the float at n as dump() writes it, at w (64 bytes of room):
-    /// from the batch if it holds n
-    NLOHMANN_VIEW_ALWAYS_INLINE char* write_double_ahead(char* w, const char* src, const node* n, float_batch& batch)
-    {
-#if NLOHMANN_VIEW_VECTOR && NLOHMANN_VIEW_LITTLE_ENDIAN
-        // (digits 0: not written by the batch; carried(): rounding carried
-        // beyond the last four digits)
-        if (batch.next != batch.count && batch.at[batch.next] == n && batch.digits[batch.next] - 1 < carried() - 1)
-        {
-            return write_token_digits(w, src, *n, batch.digits[batch.next++]);
-        }
-        return write_double_beside(w, n, batch);
-#else
-        static_cast<void>(src);
-        static_cast<void>(batch);
-        return write_double_at(w, *n);
-#endif
-    }
-
-#if NLOHMANN_VIEW_VECTOR && NLOHMANN_VIEW_LITTLE_ENDIAN
-    /// write_double_ahead() for a float that is not the batch's next one (out
-    /// of line: the walk is faster with less code in its loop)
-    NLOHMANN_VIEW_NOINLINE char* write_double_beside(char* w, const node* n, float_batch& batch)
-    {
-        // (an editable document's walk can skip nodes of the array)
-        const std::less<const node*> before{}; // NOLINT(modernize-use-transparent-functors) C++11 has no std::less<>
-        while (batch.next != batch.count && before(batch.at[batch.next], n))
-        {
-            ++batch.next;
-        }
-        if ((batch.next != batch.count && batch.at[batch.next] == n) || convert_ahead(n, batch))
-        {
-            const std::uint64_t digits = batch.digits[batch.next++];
-            if ((digits & carried()) != 0)
-            {
-                return write_carried_digits(w, *n, digits & ~carried());
-            }
-            if (digits != 0)
-            {
-                return write_token_digits(w, m_doc.src, *n, digits);
-            }
-        }
-        return write_double_at(w, *n);
-    }
-
-    /*!
-    @brief convert the floats of 16 or 17 digits among the next nodes of the
-    array at once; whether n is the first of them
-
-    Such tokens (like the coordinates of GeoJSON, written with 17 digits) are
-    written as the token with its last four digits replaced
-    (write_token_digits()). Each step (the digits, locate_token(),
-    token_digits_1/2()) is a long chain of dependent operations; one loop per
-    step over many floats lets the processor overlap the floats, which it does
-    not across the steps of one float (on Apple M1, one loop for the digits and
-    locate_token() made the dump of canada.json 12 % slower). Each node of the array
-    is scanned once; a node that the walk does not reach in order (in an
-    editable document) is written without the batch.
-    */
-    NLOHMANN_VIEW_NOINLINE bool convert_ahead(const node* n, float_batch& batch)
-    {
-        const std::less<const node*> before{}; // NOLINT(modernize-use-transparent-functors) C++11 has no std::less<>
-        const node* const last = m_doc.nodes + m_doc.node_count;
-        if (before(n, batch.scanned) || before(n, m_doc.nodes) || !before(n, last))
-        {
-            return false;
-        }
-        const char* const src = m_doc.src;
-        const char* const src_end = src + m_doc.size;
-        const node* const stop = last - n > 1024 ? n + 1024 : last;
-        batch.count = 0;
-        batch.next = 0;
-        // the digits of each token (and its last four from the text)
-        std::array<std::uint64_t, 256> digits;     // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
-        std::array<int, 256> exponent;             // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
-        std::array<std::uint32_t, 256> last_four;  // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
-        const node* p = n;
-        if (!batch.storage)
-        {
-            batch.storage.reset(new typename float_batch::entries); // NOLINT(cppcoreguidelines-owning-memory,modernize-make-unique): C++11
-            batch.at = batch.storage->at.data();
-            batch.digits = batch.storage->digits.data();
-        }
-        for (; p != stop && batch.count != float_batch::capacity(); ++p)
-        {
-            // a token of the source: 16 or 17 digits, at least 8 after the
-            // point, no exponent, 32 bytes to read
-            const unsigned frac_digits = p->extra >> 8u;
-            const unsigned int_digits = p->extra & 0xFFu;
-            const unsigned count = int_digits + frac_digits;
-            if (p->kind == node_kind::number_float && (p->flags & node_flags::storage) == 0
-                    && count - 16u <= 1u && frac_digits >= 8 && src_end - (src + p->off) >= 33)
-            {
-                const auto* const token = reinterpret_cast<const unsigned char*>(src + p->off); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-                const unsigned sign = token[0] == '-' ? 1 : 0;
-                const unsigned char* const first = token + sign;
-                const std::uint64_t w = sixteen_digits(first, int_digits);
-                // (the 17th digit follows the point; a token with an exponent
-                // gets digits outside the range of locate_token(), and is not
-                // written by the batch. A token 0.xxx with 16 significant
-                // digits is: its double is written as "0." and its digits too)
-                const std::uint64_t w17 = (w * 10) + static_cast<std::uint64_t>(first[17] - '0');
-                const std::size_t i = batch.count++;
-                batch.at[i] = p;
-                if (p->len != sign + count + 1)
-                {
-                    digits[i] = 0;
-                }
-                else
-                {
-                    digits[i] = count == 17 ? w17 : w;
-                }
-                exponent[i] = -static_cast<int>(frac_digits);
-                // (byte 0: the last digit, byte 1: the last two, bits 16-29: the last four)
-                std::uint32_t four = 0;
-                std::memcpy(&four, token + p->len - 4, 4);
-                four -= 0x30303030u;
-                const std::uint32_t pairs = ((four & 0x0F0F0F0Fu) * 2561u) >> 8u; // (byte 0, 2: the pairs)
-                last_four[i] = (four >> 24u) | ((pairs >> 16u & 0xFFu) << 8u) | ((((pairs & 0x00FF00FFu) * 6553601u) >> 16u) << 16u);
-            }
-        }
-        batch.scanned = p;
-        // the position of each double, and the floats of either kind
-        std::array<std::uint64_t, 256> offset; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
-        std::array<std::uint64_t, 256> radius; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
-        std::array<std::uint8_t, 256> kind_1;  // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
-        std::array<std::uint8_t, 256> kind_2;  // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
-        std::size_t count_1 = 0;
-        std::size_t count_2 = 0;
-        for (std::size_t i = 0; i != batch.count; ++i)
-        {
-            const std::uint64_t w = digits[i];
-            // (the range excludes the values of bytes that are not digits, only
-            // in a damaged image loaded with image_check::bounds)
-            const int g = w - 1000000000000000u < 99000000000000000u ? locate_token(w, exponent[i], offset[i], radius[i]) : 3;
-            batch.digits[i] = g <= 0 ? (last_four[i] >> 16u) + 1 : 0;
-            kind_1[count_1] = static_cast<std::uint8_t>(i);
-            count_1 += g == 1 ? 1 : 0;
-            kind_2[count_2] = static_cast<std::uint8_t>(i);
-            count_2 += g == 2 ? 1 : 0;
-        }
-        // the digits to write, in one loop per kind (see mark())
-        for (std::size_t k = 0; k != count_1; ++k)
-        {
-            const std::size_t i = kind_1[k];
-            const std::uint64_t s = token_digits_1(digits[i], offset[i], radius[i], last_four[i] & 0xFFu);
-            batch.digits[i] = mark(digits[i], s, last_four[i] >> 16u);
-        }
-        for (std::size_t k = 0; k != count_2; ++k)
-        {
-            const std::size_t i = kind_2[k];
-            const std::uint64_t s = token_digits_2(digits[i], offset[i], radius[i], last_four[i] & 0xFFu, (last_four[i] >> 8u) & 0xFFu);
-            batch.digits[i] = mark(digits[i], s, last_four[i] >> 16u);
-        }
-        return batch.count != 0 && batch.at[0] == n;
-    }
-
-    /*!
-    @brief a float token of 16 or 17 digits as dump() writes it, at w (64 bytes
-    of room), from the digits of its double (see locate_token()) whose
-    rounding carried beyond the token's last four digits
-
-    (like 43.42027299999999 -> 43.420273): the digits go to the writer of
-    Zmij's results as its 15 or 16 leading digits and one more, which omits
-    the trailing zeros.
-    */
-    NLOHMANN_VIEW_NOINLINE char* write_carried_digits(char* w, const node& n, std::uint64_t digits) const noexcept
-    {
-        const int exponent = -(n.extra >> 8u);
-        const std::uint64_t leading = digits / 10;
-        const auto last = static_cast<unsigned char>(digits - (leading * 10));
-        const bool seventeen = digits >= 10000000000000000u;
-        *w = '-';
-        w += m_doc.src[n.off] == '-' ? 1 : 0;
-        return ::nlohmann::detail::dtoa_impl::write_shortest(w, seventeen ? ::nlohmann::detail::zmij::shortest_decimal{leading, exponent, last, last != 0}
-                : ::nlohmann::detail::zmij::shortest_decimal{digits, exponent - 1, 0, false});
-    }
-
-    /// the digits s of a token with the digits w and the last four digits
-    /// r4, as the batch keeps them: the new last four digits + 1 (only those
-    /// are written over the token's), or s marked if it differs from w beyond
-    /// them (0 stays for a float the batch does not write)
-    static std::uint64_t mark(std::uint64_t w, std::uint64_t s, std::uint64_t r4) noexcept
-    {
-        const std::uint64_t last = s - (w - r4);
-        return last < 10000 ? last + 1 : s | carried();
-    }
-
-    /*!
-    @brief a float token of 16 or 17 digits as dump() writes it, at w (64 bytes
-    of room): the token with its last four digits replaced by digits - 1 (see
-    mark(); the others are the token's), and without trailing zeros after the
-    point, but one
-    */
-    char* write_token_digits(char* w, const char* src, const node& n, std::uint64_t digits)
-    {
-        const char* const token = src + n.off;
-        std::memcpy(w, token, 32);
-        char* const end = w + n.len;
-        const std::uint32_t last = four_digit_text(static_cast<std::uint32_t>(digits - 1));
-        std::memcpy(end - 4, &last, 4);
-        // (the token's text before the new digits, from the source: reading
-        // the output back would wait for the stores)
-        std::uint64_t before = 0;
-        std::memcpy(&before, token + n.len - 12, 8);
-        const std::uint32_t last_zeros = last ^ 0x30303030u;
-        const std::uint64_t before_zeros = before ^ 0x3030303030303030u;
-        if (NLOHMANN_VIEW_UNLIKELY(last_zeros == 0 && before_zeros == 0))
-        {
-            return write_double_at(w, n); // (twelve or more trailing zeros)
-        }
-        const unsigned zeros = last_zeros != 0 ? (static_cast<unsigned>(count_leading_zeros(last_zeros)) / 8) - 4
-                               : 4 + (static_cast<unsigned>(count_leading_zeros(before_zeros)) / 8);
-        const unsigned frac_digits = n.extra >> 8u;
-        return end - (zeros < frac_digits ? zeros : frac_digits - 1);
-    }
-#endif
-
    /// a float node as dump() writes it
    void write_float_node(const node& n)
    {
@@ -29,6 +29,13 @@
 // NLOHMANN_VIEW_NO_TARGET_ATTRIBUTE (set by the GCC module interface, where GCC
 // ignores the target attribute and then rejects the SSSE3 intrinsics) keeps the
 // check portable without disabling the SSE2 code.
+//
+// The vector UTF-8 check (utf8_lookup4) is adapted from simdjson
+// (https://github.com/simdjson/simdjson, Daniel Lemire, Geoff Langdale, John
+// Keiser, and contributors, available under the Apache 2.0 and MIT licenses;
+// used here under the MIT license): the "lookup4" algorithm and tables of
+// J. Keiser and D. Lemire, "Validating UTF-8 In Less Than One Instruction Per
+// Byte" (2021).
 #if !defined(JSON_NO_SIMD) && defined(__aarch64__) && (defined(__GNUC__) || defined(__clang__)) && NLOHMANN_VIEW_LITTLE_ENDIAN
    #include <arm_neon.h>
    #define NLOHMANN_VIEW_NEON 1
@@ -159,7 +159,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
    friend class ::nlohmann::detail::binary_writer;
    template<typename BasicJsonType, typename InputType, typename SAX>
    friend class ::nlohmann::detail::binary_reader;
-    template<typename BasicJsonType, typename InputAdapterType, bool Collect>
+    template<typename BasicJsonType, typename InputAdapterType, bool Collect, typename LexerType>
    friend class ::nlohmann::detail::json_sax_dom_parser;
    template<typename BasicJsonType, typename InputAdapterType>
    friend class ::nlohmann::detail::json_sax_dom_binary_parser;
@@ -6950,6 +6950,25 @@ public:
    /// @sa https://json.nlohmann.me/api/basic_json/patch/
    void patch_inplace(const basic_json& json_patch)
    {
+        // the operations below change *this while iterating json_patch: apply
+        // a copy when a value is applied as patch to itself or, with
+        // JSON_DIAGNOSTICS, to a value stored inside it
+        // NOLINTNEXTLINE(misc-const-correctness): only the JSON_DIAGNOSTICS build modifies it
+        bool patch_aliases_this = (&json_patch == this);
+#if JSON_DIAGNOSTICS
+        for (const basic_json* p = json_patch.m_parent; !patch_aliases_this && p != nullptr; p = p->m_parent)
+        {
+            patch_aliases_this = (p == this);
+        }
+#endif
+        if (JSON_HEDLEY_UNLIKELY(patch_aliases_this))
+        {
+            // NOLINTNEXTLINE(performance-unnecessary-copy-initialization): *this is modified below
+            const basic_json json_patch_copy = json_patch;
+            patch_inplace(json_patch_copy);
+            return;
+        }
+
        basic_json& result = *this;
        // the valid JSON Patch operations
        enum class patch_operations {add, remove, replace, move, copy, test, invalid};
@@ -763,8 +763,12 @@ class basic_json_view
    template<typename, view_mode> friend class basic_json_document;
    template<typename, view_mode> friend class basic_json_view;
    template<typename, typename> friend class detail::view::editor;
+    template<typename, typename> friend class detail::view::view_side;
    friend iterator;

+    /// whether the view is one of an editable document
+    static constexpr bool is_editable = Editable;
+
    basic_json_view(const document_data* d, const node* n) noexcept
        : m_doc(d), m_node(n)
    {}
@@ -10970,6 +10970,13 @@ NLOHMANN_JSON_NAMESPACE_END
 // use std::from_chars or std::strtold. They are free functions so the lexer
 // stays focused on scanning (see lexer::convert_number()) and so that other
 // parsers of JSON text can convert tokens exactly like it does.
+//
+// The Eisel-Lemire conversion (eisel_lemire()), the digit comparison for the
+// cases it cannot decide, and the eight-digits-at-a-time helpers
+// (is_eight_digits(), parse_eight_digits()) are adapted from fast_float
+// (https://github.com/fastfloat/fast_float, Daniel Lemire and contributors,
+// available under the MIT, Apache 2.0, and Boost Software licenses; used here
+// under the MIT license). The table of powers of five is in pow5_table.hpp.

 NLOHMANN_JSON_NAMESPACE_BEGIN
 namespace detail
@@ -12078,6 +12085,13 @@ NLOHMANN_JSON_NAMESPACE_END
 // NLOHMANN_JSON_NO_TARGET_ATTRIBUTE (for compilers that ignore the target
 // attribute and then reject the SSSE3 intrinsics) keeps the check portable
 // without disabling the SSE2 code.
+//
+// The vector UTF-8 check (utf8_lookup4) is adapted from simdjson
+// (https://github.com/simdjson/simdjson, Daniel Lemire, Geoff Langdale, John
+// Keiser, and contributors, available under the Apache 2.0 and MIT licenses;
+// used here under the MIT license): the "lookup4" algorithm and tables of
+// J. Keiser and D. Lemire, "Validating UTF-8 In Less Than One Instruction Per
+// Byte" (2021).
 #if !defined(JSON_NO_SIMD) && defined(__aarch64__) && (defined(__GNUC__) || defined(__clang__)) && defined(__BYTE_ORDER__) && defined(__ORDER_LITTLE_ENDIAN__) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
    #include <arm_neon.h>
    #define JSON_SCAN_NEON 1
@@ -15629,7 +15643,10 @@ struct diagnostic_positions
        {
            // Lexer has read the first character of the container, so
            // subtract 1 from the position to get the correct start position.
-            v.start_position = lexer->get_chars_read_total() - 1;
+            // (npos: a value without a source position, see materialize() of
+            // json_view)
+            const std::size_t read = lexer->get_chars_read_total();
+            v.start_position = read == std::string::npos ? std::string::npos : read - 1;
        }
    }

@@ -15644,6 +15661,12 @@ struct diagnostic_positions
        {
            // Lexer's position is past the closing brace or bracket, so set that as the end position.
            v.end_position = lexer->get_chars_read_total();
+            if (v.end_position == std::string::npos)
+            {
+                // a range has both ends or none (exception::diagnostics()
+                // prints only complete ones)
+                v.start_position = std::string::npos;
+            }
        }
    }

@@ -15660,6 +15683,12 @@ struct diagnostic_positions
            // The start position will be set below based on the length of the string representation
            // of the value.
            v.end_position = lexer->get_chars_read_total();
+            if (v.end_position == std::string::npos)
+            {
+                // a value without a source position
+                v.start_position = std::string::npos;
+                return;
+            }

            switch (v.type())
            {
@@ -15872,8 +15901,12 @@ read up to it.
@tparam Collect  whether to collect the values of containers of unknown size on
                 a stack (only for a caller that does not use the value after a
                 parse error)
+@tparam LexerType  the type of the lexer that reports the source positions
+                   (JSON_DIAGNOSTIC_POSITIONS); only diagnostic_positions uses
+                   it, so any type with its three functions works (as
+                   materialize() of json_view uses it)
 */
-template<typename BasicJsonType, typename InputAdapterType, bool Collect = false>
+template<typename BasicJsonType, typename InputAdapterType, bool Collect = false, typename LexerType = lexer<BasicJsonType, InputAdapterType>>
 class json_sax_dom_parser : public json_sax_dom_error_state
 {
  public:
@@ -15882,7 +15915,7 @@ class json_sax_dom_parser : public json_sax_dom_error_state
    using number_float_t = typename BasicJsonType::number_float_t;
    using string_t = typename BasicJsonType::string_t;
    using binary_t = typename BasicJsonType::binary_t;
-    using lexer_t = lexer<BasicJsonType, InputAdapterType>;
+    using lexer_t = LexerType;

    /*!
    @param[in,out] r  reference to a JSON value that is manipulated while
@@ -22515,8 +22548,8 @@ using parser_callback_t =
 template<typename SAX>
 struct sax_ignores_number_text : std::false_type {};

-template<typename BasicJsonType, typename InputAdapterType, bool Collect>
-struct sax_ignores_number_text<json_sax_dom_parser<BasicJsonType, InputAdapterType, Collect>> : std::true_type {};
+template<typename BasicJsonType, typename InputAdapterType, bool Collect, typename LexerType>
+struct sax_ignores_number_text<json_sax_dom_parser<BasicJsonType, InputAdapterType, Collect, LexerType>> : std::true_type {};

 template<typename BasicJsonType, typename InputAdapterType>
 struct sax_ignores_number_text<json_sax_dom_callback_parser<BasicJsonType, InputAdapterType>> : std::true_type {};
@@ -24331,6 +24364,13 @@ class json_pointer
    /// @sa https://json.nlohmann.me/api/json_pointer/operator_slasheq/
    json_pointer& operator/=(const json_pointer& ptr)
    {
+        // insert() must not be given iterators into the vector it inserts
+        // into: append a copy when a pointer is appended to itself
+        if (JSON_HEDLEY_UNLIKELY(&ptr == this))
+        {
+            return *this /= json_pointer(ptr);
+        }
+
        reference_tokens.insert(reference_tokens.end(),
                                ptr.reference_tokens.begin(),
                                ptr.reference_tokens.end());
@@ -32469,6 +32509,11 @@ NLOHMANN_JSON_NAMESPACE_END
 #include <type_traits> // conditional


+// The shortest-digit conversion of doubles (see zmij.hpp) and the writing of
+// its digits, including the conversion of the digits to text by Xiang JunBo
+// and the SIMD instruction sequence by Dougall Johnson, are ported from Zmij
+// by Victor Zverovich (https://github.com/vitaut/zmij, MIT license).
+//
 // SSE2 (every x86-64 CPU) and NEON (every 64-bit Arm CPU) convert the 16
 // digits of a double at once (unless JSON_NO_SIMD selects the portable code)
 #if !defined(JSON_NO_SIMD) && (defined(__x86_64__) || (defined(_M_X64) && !defined(_M_ARM64EC)))
@@ -36910,7 +36955,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
    friend class ::nlohmann::detail::binary_writer;
    template<typename BasicJsonType, typename InputType, typename SAX>
    friend class ::nlohmann::detail::binary_reader;
-    template<typename BasicJsonType, typename InputAdapterType, bool Collect>
+    template<typename BasicJsonType, typename InputAdapterType, bool Collect, typename LexerType>
    friend class ::nlohmann::detail::json_sax_dom_parser;
    template<typename BasicJsonType, typename InputAdapterType>
    friend class ::nlohmann::detail::json_sax_dom_binary_parser;
@@ -43701,6 +43746,25 @@ public:
    /// @sa https://json.nlohmann.me/api/basic_json/patch/
    void patch_inplace(const basic_json& json_patch)
    {
+        // the operations below change *this while iterating json_patch: apply
+        // a copy when a value is applied as patch to itself or, with
+        // JSON_DIAGNOSTICS, to a value stored inside it
+        // NOLINTNEXTLINE(misc-const-correctness): only the JSON_DIAGNOSTICS build modifies it
+        bool patch_aliases_this = (&json_patch == this);
+#if JSON_DIAGNOSTICS
+        for (const basic_json* p = json_patch.m_parent; !patch_aliases_this && p != nullptr; p = p->m_parent)
+        {
+            patch_aliases_this = (p == this);
+        }
+#endif
+        if (JSON_HEDLEY_UNLIKELY(patch_aliases_this))
+        {
+            // NOLINTNEXTLINE(performance-unnecessary-copy-initialization): *this is modified below
+            const basic_json json_patch_copy = json_patch;
+            patch_inplace(json_patch_copy);
+            return;
+        }
+
        basic_json& result = *this;
        // the valid JSON Patch operations
        enum class patch_operations {add, remove, replace, move, copy, test, invalid};
@@ -21,6 +21,10 @@ python3 tests/benchmarks/json_view/compare.py --data <json_test_data directory>
 - The other libraries come from the system: pkg-config, or Homebrew (`brew install yyjson simdjson boost`). With
  `--download`, pinned releases are downloaded instead and checked against their SHA-256. Without Boost headers (or
  with `--no-boost`), the Boost.JSON columns are skipped, and the results say so.
+- `--aligned` additionally builds and runs everything with all functions aligned to 64 bytes (`-mllvm
+  -align-all-functions=6` for Clang, `-falign-functions=64 -falign-loops=64` for GCC), and reports both result
+  tables as "default build" and "aligned build". Code layout alone can move a result by a few percent; a difference
+  that appears in only one of the two tables is a layout artifact. Off by default, which doubles the run time.
 - `--corpus file...` adds files to the corpus benchmark, e.g. those of
  [simdjson-data](https://github.com/simdjson/simdjson-data) or the
  [yyjson benchmark](https://github.com/ibireme/yyjson_benchmark).
@@ -39,7 +43,7 @@ where `json_view` stands on another architecture; they are not meant for publica

 ## What is measured

-`bench_view.cpp` runs four workloads on twitter, citm_catalog, canada, jeopardy, a single tweet (`status`), and a
+`bench_view.cpp` runs these workloads on twitter, citm_catalog, canada, jeopardy, a single tweet (`status`), and a
 JSON-RPC request (`rpc`):

 | workload | what it does |
@@ -48,6 +52,7 @@ JSON-RPC request (`rpc`):
 | traverse | parse, then visit every value, convert every number, touch every string and key |
 | select | parse, then read a few fields per record (e.g. id, user name, and retweet count of each tweet) |
 | dump | serialize a parsed document (compact) |
+| parse+dump | build a fresh document, then serialize it (compact), in one timed call |

 `bench_corpus.cpp` runs parse, traverse, and dump on any list of files, so that no library is tuned to a handful of
 documents. Its dump also writes the numbers as they are in the input: `json_view` with `number_format::source`, and
@@ -72,11 +77,32 @@ call follows an untimed call of the same engine: otherwise the engine after `jso
 cleaning up the tens of thousands of nodes `json::parse` just freed (with glibc, this made `json_view` look 1.7 times
 slower on citm_catalog traverse).

+`json_view` is an index into the source text, not a tree of owning nodes. Its like-for-like peers are yyjson and
+simdjson DOM (immutable, indexed, no per-node allocation). Boost.JSON and `json::parse` build mutable, owning DOMs and
+are reference points for what that costs, not equals; simdjson On-Demand is lazy and forward-only, so it is the other
+way round: it has no random access to pay for. All engines validate UTF-8 and syntax by default.
+
+Number conversion differs: `json_view` converts integers while parsing but converts floating-point numbers lazily,
+when they are read or dumped; yyjson (default flags) and simdjson DOM convert every number while parsing. The cost of
+float conversion therefore appears in the traverse and dump rows for `json_view`, and in the parse row for the others.
+For float-heavy documents (canada), the fair reading is a sum of parse and use: the `traverse` workload already
+includes the parse, and `parse+dump` measures a fresh document and its dump in one timed call; the `dump` row alone
+leaves the conversion in `json_view` and out of the others. Eager conversion at parse time was prototyped as an opt-in
+and measured: canada traverse (with its parse) was 4-7 % faster, but parse+dump 11-30 % slower and parse 36-90 % slower. It was
+dropped, so lazy conversion is the only mode.
+
+`json_view` can also be edited: `json_editable_document` has the same read API, and the `(editable)` rows in
+`bench_view` measure it on the same workloads. They are the fair counterpart of Boost.JSON and `json::parse`, which are
+mutable too; the plain `json_view` rows are the counterpart of yyjson and simdjson DOM, which are not. `bench_edit` adds
+the read-modify-write workloads. Read the tables with that in mind: an immutable-only library is not compared with an
+editable `json_view` unless it says so.
+
 The engines do not all offer the same features, which the numbers should be read with:

 | engine | document | random access | editable | notes |
 |---|---|---|---|---|
 | `json_view` | immutable index into the text | yes | no | a fresh document per parse; "reused" parses into the same document |
+| `json_view` (editable) | index into the text plus edits | yes | yes, in place | `json_editable_document`; keeps member order and number spellings |
 | yyjson | immutable (`yyjson_read`) | yes | via a mutable copy | |
 | simdjson DOM | immutable, parser reused | yes | no | "fresh" uses a new parser per parse |
 | simdjson On-Demand | none: forward-only, lazy | no | no | only traverse and select |
@@ -8,8 +8,9 @@

 // Same-feature-set benchmark: read-only JSON documents with random access.
 //
-//   json_view      nlohmann/json_view.hpp (fresh document per parse / reused)
-//   yyjson         yyjson_read(): immutable document, random access
+//   json_view      nlohmann/json_view.hpp (fresh document per parse / reused;
+//                  "(editable)": json_editable_document, same read API)
+//   yyjson        yyjson_read(): immutable document, random access
 //   simdjson DOM   dom::parser (reused, as recommended; "fresh": a new parser
 //                  per parse): immutable, random access
 // references (different feature sets):
@@ -19,7 +20,11 @@
 //
 // Workloads: parse (build + free), traverse (visit everything, convert every
 // number, touch every string and key), select (a few fields per document),
-// dump (compact serialization of the parsed document).
+// dump (compact serialization of the parsed document), and parse+dump (a fresh
+// document, then its dump, in one timed call). json_view converts floating-point
+// numbers lazily (when read or dumped), yyjson and simdjson DOM while parsing:
+// for float-heavy documents, traverse (which includes the parse) and parse+dump
+// are the fair reading of the parse and dump rows.
 // All engines run interleaved in every round, each timed call after an untimed
 // one of the same engine; the best round is reported.
 #include <nlohmann/json_view.hpp>
@@ -43,6 +48,8 @@

 using nlohmann::json;
 using nlohmann::json_document;
+using nlohmann::json_editable_document;
+using nlohmann::json_editable_view;
 using nlohmann::json_view;

 static volatile double g_sink;
@@ -55,7 +62,8 @@ struct stats

 // ---------------- traversal ----------------

-static void walk(json_view v, stats& st)
+template<class V>
+static void walk_view(V v, stats& st)
 {
    ++st.nodes;
    switch (v.type())
@@ -64,32 +72,42 @@ static void walk(json_view v, stats& st)
            for (auto it = v.begin(); it != v.end(); ++it)
            {
                st.str += it.key().size();
-                walk(*it, st);
+                walk_view<V>(*it, st);
            }
            break;
        case json::value_t::array:
-            for (const json_view e : v)
+            for (const V e : v)
            {
-                walk(e, st);
+                walk_view<V>(e, st);
            }
            break;
        case json::value_t::string:
            st.str += v.get_string().size();
            break;
        case json::value_t::number_integer:
-            st.num += static_cast<double>(v.get<std::int64_t>());
+            st.num += static_cast<double>(v.template get<std::int64_t>());
            break;
        case json::value_t::number_unsigned:
-            st.num += static_cast<double>(v.get<std::uint64_t>());
+            st.num += static_cast<double>(v.template get<std::uint64_t>());
            break;
        case json::value_t::number_float:
-            st.num += v.get<double>();
+            st.num += v.template get<double>();
            break;
        default:
            break;
    }
 }

+static void walk(json_view v, stats& st)
+{
+    walk_view<json_view>(v, st);
+}
+
+static void walk(json_editable_view v, stats& st)
+{
+    walk_view<json_editable_view>(v, st);
+}
+
 static void walk(const json& j, stats& st)
 {
    ++st.nodes;
@@ -300,20 +318,21 @@ static void walk(const boost::json::value& v, stats& st)
 // status (one tweet): id, user.screen_name, retweet_count
 // rpc: method, params.minuend, id

-static double pick(const std::string& name, json_view r)
+template<class V>
+static double pick_view(const std::string& name, V r)
 {
    double acc = 0;
    if (name == "twitter" || name == "status")
    {
-        auto one = [&](json_view s)
+        auto one = [&](V s)
        {
-            acc += static_cast<double>(s["id"].get<std::uint64_t>());
+            acc += static_cast<double>(s["id"].template get<std::uint64_t>());
            acc += static_cast<double>(s["user"]["screen_name"].get_string().size());
-            acc += static_cast<double>(s["retweet_count"].get<std::int64_t>());
+            acc += static_cast<double>(s["retweet_count"].template get<std::int64_t>());
        };
        if (name == "twitter")
        {
-            for (const json_view s : r["statuses"])
+            for (const V s : r["statuses"])
            {
                one(s);
            }
@@ -325,20 +344,20 @@ static double pick(const std::string& name, json_view r)
    }
    else if (name == "citm_catalog")
    {
-        for (const json_view p : r["performances"])
+        for (const V p : r["performances"])
        {
-            acc += static_cast<double>(p["id"].get<std::uint64_t>() + p["eventId"].get<std::uint64_t>() + p["seatCategories"].size());
+            acc += static_cast<double>(p["id"].template get<std::uint64_t>() + p["eventId"].template get<std::uint64_t>() + p["seatCategories"].size());
        }
        acc += static_cast<double>(r["events"].size());
    }
    else if (name == "canada")
    {
-        const json_view g = r["features"][0]["geometry"];
+        const V g = r["features"][0]["geometry"];
        acc += static_cast<double>(r["type"].get_string().size() + g["type"].get_string().size() + g["coordinates"].size());
    }
    else if (name == "jeopardy")
    {
-        for (const json_view q : r)
+        for (const V q : r)
        {
            acc += q["round"].get_string() == "Final Jeopardy!" ? 1 : 0;
            acc += static_cast<double>(q["category"].get_string().size());
@@ -347,11 +366,21 @@ static double pick(const std::string& name, json_view r)
    else if (name == "rpc")
    {
        acc += static_cast<double>(r["method"].get_string().size());
-        acc += static_cast<double>(r["params"]["minuend"].get<std::int64_t>() + r["id"].get<std::int64_t>());
+        acc += static_cast<double>(r["params"]["minuend"].template get<std::int64_t>() + r["id"].template get<std::int64_t>());
    }
    return acc;
 }

+static double pick(const std::string& name, json_view r)
+{
+    return pick_view<json_view>(name, r);
+}
+
+static double pick(const std::string& name, json_editable_view r)
+{
+    return pick_view<json_editable_view>(name, r);
+}
+
 static double pick(const std::string& name, const json& r)
 {
    double acc = 0;
@@ -634,15 +663,35 @@ int main(int argc, char** argv)
        walk(json::parse(dc.text), a);
        auto d = json_document::parse(dc.text);
        walk(d.root(), b);
+        auto ed = json_editable_document::parse(dc.text);
+        stats e;
+        walk(ed.root(), e);
        yyjson_doc* y = yyjson_read(dc.text.data(), dc.text.size(), 0);
        walk(yyjson_doc_get_root(y), c);
        simdjson::dom::parser p;
        walk(p.parse(dc.text).value(), dd);
-        const bool ok = a.nodes == b.nodes && a.nodes == c.nodes && a.nodes == dd.nodes && a.str == b.str && a.str == c.str && a.str == dd.str
+        const bool ok = a.nodes == b.nodes && a.nodes == e.nodes && a.str == e.str && std::fabs(a.num - e.num) <= 1e-9 * std::fabs(a.num) && a.nodes == c.nodes && a.nodes == dd.nodes && a.str == b.str && a.str == c.str && a.str == dd.str
                        && std::fabs(a.num - b.num) <= 1e-9 * std::fabs(a.num) && std::fabs(a.num - c.num) <= 1e-9 * std::fabs(a.num);
-        const double pa = pick(dc.name, json::parse(dc.text)), pb = pick(dc.name, d.root()), pc = pick(dc.name, yyjson_doc_get_root(y)), pd = pick(dc.name, p.parse(dc.text).value());
-        std::printf("check %-13s traverse %s select %s\n", dc.name.c_str(), ok ? "OK" : "MISMATCH", (pa == pb && pa == pc && pa == pd) ? "OK" : "MISMATCH");
+        const double pa = pick(dc.name, json::parse(dc.text)), pb = pick(dc.name, d.root()), pe = pick(dc.name, ed.root()), pc = pick(dc.name, yyjson_doc_get_root(y)), pd = pick(dc.name, p.parse(dc.text).value());
+        std::printf("check %-13s traverse %s select %s\n", dc.name.c_str(), ok ? "OK" : "MISMATCH", (pa == pb && pa == pe && pa == pc && pa == pd) ? "OK" : "MISMATCH");
        yyjson_doc_free(y);
+
+        // the dumps of the engines may format floats differently, so only: every dump is non-empty, and the
+        // dump of json_view (also editable) and of json::parse parse back to the same number of nodes
+        const std::string dj = json::parse(dc.text).dump();
+        const std::string dv = d.root().dump();
+        const std::string de = ed.root().dump();
+        std::size_t yn = 0;
+        yyjson_doc* y2 = yyjson_read(dc.text.data(), dc.text.size(), 0);
+        char* yo = yyjson_write(y2, 0, &yn);
+        const bool dumps_ok = !dj.empty() && !dv.empty() && !de.empty() && yo != nullptr && yn > 0 && !simdjson::to_string(p.parse(dc.text).value()).empty();
+        std::free(yo);
+        yyjson_doc_free(y2);
+        stats sj_nodes, sv_nodes, se_nodes;
+        walk(json::parse(dj), sj_nodes);
+        walk(json::parse(dv), sv_nodes);
+        walk(json::parse(de), se_nodes);
+        std::printf("check %-13s dump %s\n", dc.name.c_str(), (dumps_ok && sj_nodes.nodes == a.nodes && sv_nodes.nodes == a.nodes && se_nodes.nodes == a.nodes) ? "OK" : "MISMATCH");
    }

    std::FILE* csv = std::fopen("bench_view.csv", "w");
@@ -669,6 +718,7 @@ int main(int argc, char** argv)
        workloads.push_back({"parse", {
                {"json_view", [&] { auto d = json_document::parse(s); g_sink = static_cast<double>(d.node_count()); }},
                {"json_view (reused)", [&] { reused.read(s); g_sink = static_cast<double>(reused.node_count()); }},
+                {"json_view (editable)", [&] { auto d = json_editable_document::parse(s); g_sink = static_cast<double>(d.root().size()); }},
                {"yyjson", [&] { yyjson_doc* d = yyjson_read(s.data(), s.size(), 0); g_sink = static_cast<double>(yyjson_doc_get_val_count(d)); yyjson_doc_free(d); }},
                {"simdjson DOM", [&] { auto e = sj.parse(ps).value_unsafe(); g_sink = e.is_object(); }},
                {"simdjson DOM (fresh)", [&] { simdjson::dom::parser p; auto e = p.parse(ps).value_unsafe(); g_sink = e.is_object(); }},
@@ -680,6 +730,7 @@ int main(int argc, char** argv)
        workloads.push_back({"traverse", {
                {"json_view", [&] { auto d = json_document::parse(s); stats st; walk(d.root(), st); g_sink = st.num; }},
                {"json_view (reused)", [&] { reused.read(s); stats st; walk(reused.root(), st); g_sink = st.num; }},
+                {"json_view (editable)", [&] { auto d = json_editable_document::parse(s); stats st; walk(d.root(), st); g_sink = st.num; }},
                {"yyjson", [&] { yyjson_doc* d = yyjson_read(s.data(), s.size(), 0); stats st; walk(yyjson_doc_get_root(d), st); g_sink = st.num; yyjson_doc_free(d); }},
                {"simdjson DOM", [&] { stats st; walk(sj.parse(ps).value_unsafe(), st); g_sink = st.num; }},
                {"simdjson OD", [&] { auto d = od.iterate(ps).value_unsafe(); stats st; walk_od(d.get_value().value_unsafe(), st); g_sink = st.num; }},
@@ -691,15 +742,31 @@ int main(int argc, char** argv)
        workloads.push_back({"select", {
                {"json_view", [&] { auto d = json_document::parse(s); g_sink = pick(name, d.root()); }},
                {"json_view (reused)", [&] { reused.read(s); g_sink = pick(name, reused.root()); }},
+                {"json_view (editable)", [&] { auto d = json_editable_document::parse(s); g_sink = pick(name, d.root()); }},
                {"yyjson", [&] { yyjson_doc* d = yyjson_read(s.data(), s.size(), 0); g_sink = pick(name, yyjson_doc_get_root(d)); yyjson_doc_free(d); }},
                {"simdjson DOM", [&] { g_sink = pick(name, sj.parse(ps).value_unsafe()); }},
                {"simdjson OD", [&] { auto d = od.iterate(ps).value_unsafe(); g_sink = pick_od(name, d); }},
                {"json::parse", [&] { json j = json::parse(s); g_sink = pick(name, j); }},
            }});
+        // pipeline: a fresh document, then a dump of it, in one timed call
+        // (simdjson DOM reuses its parser, as in the parse row); the traverse
+        // workload above is already parse+traverse
+        workloads.push_back({"parse+dump", {
+                {"json_view", [&] { auto d = json_document::parse(s); std::string o = d.root().dump(); g_sink = static_cast<double>(o.size()); }},
+                {"json_view (editable)", [&] { auto d = json_editable_document::parse(s); std::string o = d.root().dump(); g_sink = static_cast<double>(o.size()); }},
+                {"yyjson", [&] { yyjson_doc* d = yyjson_read(s.data(), s.size(), 0); std::size_t n = 0; char* o = yyjson_write(d, 0, &n); g_sink = static_cast<double>(n); std::free(o); yyjson_doc_free(d); }},
+                {"simdjson DOM", [&] { std::string o = simdjson::to_string(sj.parse(ps).value_unsafe()); g_sink = static_cast<double>(o.size()); }},
+#if JSON_VIEW_BENCH_BOOST
+                {"Boost.JSON", [&] { boost::json::monotonic_resource mr; auto v = boost::json::parse(s, &mr); std::string o = boost::json::serialize(v); g_sink = static_cast<double>(o.size()); }},
+#endif
+                {"json::parse", [&] { json j = json::parse(s); std::string o = j.dump(); g_sink = static_cast<double>(o.size()); }},
+            }});
        {
            // serialization of an already parsed document
            static json_document vd;
            vd.read(s);
+            static json_editable_document ed = json_editable_document::parse(s);
+            ed = json_editable_document::parse(s);
            static yyjson_doc* yd = nullptr;
            if (yd)
            {
@@ -713,6 +780,7 @@ int main(int argc, char** argv)
            jd = json::parse(s);
            workloads.push_back({"dump", {
                    {"json_view", [&] { std::string o = vd.root().dump(); g_sink = static_cast<double>(o.size()); }},
+                    {"json_view (editable)", [&] { std::string o = ed.root().dump(); g_sink = static_cast<double>(o.size()); }},
                    {"yyjson", [&] { std::size_t n = 0; char* o = yyjson_write(yd, 0, &n); g_sink = static_cast<double>(n); std::free(o); }},
                    {"simdjson DOM", [&] { std::string o = simdjson::to_string(se); g_sink = static_cast<double>(o.size()); }},
                    {"json::parse", [&] { std::string o = jd.dump(); g_sink = static_cast<double>(o.size()); }},
@@ -740,7 +808,7 @@ int main(int argc, char** argv)
                }
            }
            const double ref = best[0];
-            std::printf("%-13s %-9s", dc.name.c_str(), wl.first.c_str());
+            std::printf("%-13s %-14s", dc.name.c_str(), wl.first.c_str());
            for (std::size_t k = 0; k < wl.second.size(); ++k)
            {
                const double us = best[k] / 1e3;
@@ -239,6 +239,8 @@ def main():
    ap.add_argument('--download', action='store_true', help='use pinned downloads instead of system libraries')
    ap.add_argument('--no-boost', action='store_true', help='skip Boost.JSON')
    ap.add_argument('--native', action='store_true', help='compile for this CPU (-march=native / -mcpu=native)')
+    ap.add_argument('--aligned', action='store_true',
+                    help='also build and run with all functions (and loops) aligned, to make code layout artifacts visible')
    ap.add_argument('--rounds', type=int, default=30, help='rounds of bench_view (default: 30)')
    ap.add_argument('--corpus', nargs='*', default=[], help='more files for bench_corpus')
    ap.add_argument('--build-dir', default=os.path.join(HERE, 'build'), help='where to build (default: build/ next to this script)')
@@ -282,32 +284,46 @@ def main():
                + ['-I' + d for d in lib.include])
            objects.append(obj)

-    binaries = {}
-    for bench in ['bench_view', 'bench_corpus', 'bench_edit', 'bench_decode']:
-        exe = os.path.join(args.build_dir, bench)
-        run(cxx + flags + include + [os.path.join(HERE, bench + '.cpp')] + objects + link + ['-o', exe])
-        binaries[bench] = exe
+    cxx_version = output(cxx + ['--version'])
+    is_clang = 'clang' in cxx_version.lower()
+    # alignment flags: functions and (gcc) loops on 64-byte boundaries
+    align_flags = ['-mllvm', '-align-all-functions=6'] if is_clang else ['-falign-functions=64', '-falign-loops=64']
+
+    # the builds: the default one and, with --aligned, one with aligned code
+    variants = [('default build', args.build_dir, [])]
+    if args.aligned:
+        variants.append(('aligned build', os.path.join(args.build_dir, 'aligned'), align_flags))

-    # run: bench_view on its documents, bench_corpus on those and the given files
    corpus = [os.path.join(args.data, f) for f in DEFAULT_CORPUS] + args.corpus
-    outputs = {}
-    outputs['bench_view'] = run([binaries['bench_view'], args.data, str(args.rounds)], cwd=args.build_dir,
-                                capture_output=True, text=True).stdout
-    outputs['bench_corpus'] = run([binaries['bench_corpus']] + corpus, cwd=args.build_dir,
-                                  capture_output=True, text=True).stdout
-    outputs['bench_edit'] = run([binaries['bench_edit'], args.data, str(max(1, args.rounds // 2))], cwd=args.build_dir,
-                                capture_output=True, text=True).stdout
-    outputs['bench_decode'] = run([binaries['bench_decode'], args.data, str(max(1, args.rounds // 2))], cwd=args.build_dir,
-                                  capture_output=True, text=True).stdout
-    for name, text in outputs.items():
-        print(text)
+    # label -> {benchmark: output}
+    all_outputs = {}
+    for label, build_dir, extra in variants:
+        os.makedirs(build_dir, exist_ok=True)
+        binaries = {}
+        for bench in ['bench_view', 'bench_corpus', 'bench_edit', 'bench_decode']:
+            exe = os.path.join(build_dir, bench)
+            run(cxx + flags + extra + include + [os.path.join(HERE, bench + '.cpp')] + objects + link + ['-o', exe])
+            binaries[bench] = exe
+
+        # run: bench_view on its documents, bench_corpus on those and the given files
+        outputs = {}
+        outputs['bench_view'] = run([binaries['bench_view'], args.data, str(args.rounds)], cwd=build_dir,
+                                    capture_output=True, text=True).stdout
+        outputs['bench_corpus'] = run([binaries['bench_corpus']] + corpus, cwd=build_dir,
+                                      capture_output=True, text=True).stdout
+        outputs['bench_edit'] = run([binaries['bench_edit'], args.data, str(max(1, args.rounds // 2))], cwd=build_dir,
+                                    capture_output=True, text=True).stdout
+        outputs['bench_decode'] = run([binaries['bench_decode'], args.data, str(max(1, args.rounds // 2))],
+                                      cwd=build_dir, capture_output=True, text=True).stdout
+        for name, text in outputs.items():
+            print(text)
+        all_outputs[label] = outputs

    # results with their metadata
    now = datetime.datetime.now()
    host = re.sub(r'[^A-Za-z0-9-]+', '-', platform.node().split('.')[0]) or 'host'
    stem = os.path.join(HERE, 'results', f'{now:%Y-%m-%d}-{host}')
    os.makedirs(os.path.dirname(stem), exist_ok=True)
-    cxx_version = output(cxx + ['--version'])
    compiler_version = cxx_version.splitlines()[0] if cxx_version else ' '.join(cxx)
    meta = [
        ('date', f'{now:%Y-%m-%d %H:%M}'),
@@ -316,6 +332,7 @@ def main():
        ('OS', f'{platform.system()} {platform.release()} ({platform.machine()})'),
        ('compiler', compiler_version),
        ('flags', ' '.join(flags)),
+        ('aligned results', ('included (flags: ' + ' '.join(align_flags) + ')') if args.aligned else 'not included'),
        ('yyjson', libs['yyjson'].version),
        ('simdjson', libs['simdjson'].version),
        ('Boost.JSON', libs['boost'].version if with_boost else 'skipped (not found)'),
@@ -328,15 +345,20 @@ def main():
        f.write('| | |\n|---|---|\n')
        for key, value in meta:
            f.write(f'| {key} | {value} |\n')
-        for name, text in outputs.items():
-            f.write(f'\n## {name}\n\n```\n{text.rstrip()}\n```\n')
+        for label, outputs in all_outputs.items():
+            # (without --aligned there is only the default build, and no extra heading level)
+            prefix = f'{label}: ' if args.aligned else ''
+            for name, text in outputs.items():
+                f.write(f'\n## {prefix}{name}\n\n```\n{text.rstrip()}\n```\n')
    with open(stem + '.csv', 'w', encoding='utf-8') as out:
        out.write(''.join(f'# {key}: {value}\n' for key, value in meta))
-        for name in ['bench_view', 'bench_corpus', 'bench_edit', 'bench_decode']:
-            path = os.path.join(args.build_dir, name + '.csv')
-            if os.path.isfile(path):
-                with open(path, encoding='utf-8') as f:
-                    out.write(f'# {name}\n' + f.read())
+        for label, build_dir, _ in variants:
+            for name in ['bench_view', 'bench_corpus', 'bench_edit', 'bench_decode']:
+                path = os.path.join(build_dir, name + '.csv')
+                if os.path.isfile(path):
+                    with open(path, encoding='utf-8') as f:
+                        # (the default build keeps its plain section names)
+                        out.write(f'# {name}' + (f' ({label})' if args.aligned else '') + '\n' + f.read())
    print(f'results: {stem}.md, {stem}.csv')


@@ -1311,6 +1311,8 @@ TEST_CASE("BSON declared document size bounds the content")
    // records the events that a SAX parser receives
    struct recorder : nlohmann::json_sax<json>
    {
+        // GCC's -Weffc++ wants the member initialized in the member initialization list
+        // NOLINTNEXTLINE(readability-redundant-member-init)
        std::string events {};

        bool null() override
@@ -3030,3 +3030,144 @@ TEST_CASE("a json_sax_dom_parser keeps the values read before a parse error")
        CHECK(read_before_error<nlohmann::ordered_json>(c.first) == c.second);
    }
 }
+
+TEST_CASE("object keys are delivered decoded and validated")
+{
+    // json_sax::key and the key event of a parser callback see the decoded name, and
+    // only after the whole name was scanned and validated
+    const auto keys_of_format = [](const std::string & text, const json::input_format_t format)
+    {
+        SaxEventLogger l;
+        json::sax_parse(text, &l, format);
+        std::vector<std::string> keys;
+        for (const auto& e : l.events)
+        {
+            if (e.compare(0, 4, "key(") == 0)
+            {
+                keys.push_back(e.substr(4, e.size() - 5));
+            }
+        }
+        return keys;
+    };
+
+    const auto keys_of = [&keys_of_format](const std::string & text)
+    {
+        return keys_of_format(text, json::input_format_t::json);
+    };
+
+    const auto callback_keys_of = [](const std::string & text)
+    {
+        std::vector<std::string> keys;
+        const json::parser_callback_t cb = [&keys](int /*depth*/, json::parse_event_t event, json & parsed)
+        {
+            if (event == json::parse_event_t::key)
+            {
+                keys.push_back(parsed.get<std::string>());
+            }
+            return true;
+        };
+        const json parsed = json::parse(text, cb, false);
+        static_cast<void>(parsed);
+        return keys;
+    };
+
+    SECTION("different spellings of a name yield the same string")
+    {
+        const std::string e_acute = "\xc3\xa9";
+        const std::string text = std::string(R"({"/":1,"\/":2,"\u002f":3,"\u00e9":4,"\u00E9":5,")") + e_acute + R"(":6})";
+        const std::vector<std::string> expected = {"/", "/", "/", e_acute, e_acute, e_acute};
+        CHECK(keys_of(text) == expected);
+        CHECK(callback_keys_of(text) == expected);
+    }
+
+    SECTION("escape sequences are decoded")
+    {
+        const std::string simple = R"({"\"\\\/\b\f\n\r\t":1})";
+        const std::vector<std::string> simple_expected = {std::string("\"\\/\b\f\n\r\t")};
+        CHECK(keys_of(simple) == simple_expected);
+        CHECK(callback_keys_of(simple) == simple_expected);
+
+        const std::string nul = R"({"\u0000":1})";
+        const std::vector<std::string> nul_expected = {std::string(1, '\0')};
+        CHECK(keys_of(nul) == nul_expected);
+        CHECK(callback_keys_of(nul) == nul_expected);
+
+        const std::string pair = R"({"\ud83d\ude00":1})";
+        const std::vector<std::string> pair_expected = {"\xf0\x9f\x98\x80"};
+        CHECK(keys_of(pair) == pair_expected);
+        CHECK(callback_keys_of(pair) == pair_expected);
+    }
+
+    SECTION("no normalization and no case conversion")
+    {
+        const std::string text = std::string("{\"\xc3\xa9\":1,\"e\xcc\x81\":2,\"A\":3,\"a\":4}");
+        const std::vector<std::string> expected = {"\xc3\xa9", "e\xcc\x81", "A", "a"};
+        CHECK(keys_of(text) == expected);
+        CHECK(callback_keys_of(text) == expected);
+    }
+
+    SECTION("a name that is not valid is not delivered")
+    {
+        const std::vector<std::string> texts =
+        {
+            R"({"\u12G4":1})",       // malformed escape
+            R"({"\udc00":1})",       // lone low surrogate
+            R"({"\ud800":1})",       // lone high surrogate
+            R"({"\ud800\u0041":1})", // high surrogate not followed by a low one
+            R"({"\x":1})",           // unknown escape
+            std::string("{\"a\x01\":1}"),   // control character
+            std::string("{\"\xff\":1}")     // ill-formed UTF-8
+        };
+        for (const auto& text : texts)
+        {
+            CAPTURE(text)
+            CHECK(!json::accept(text));
+            CHECK(keys_of(text).empty());
+            CHECK(callback_keys_of(text).empty());
+        }
+    }
+
+    SECTION("a name is delivered before the following colon is read")
+    {
+        const std::string text = R"({"a" 1})";
+        const std::vector<std::string> expected = {"a"};
+        CHECK(!json::accept(text));
+        CHECK(keys_of(text) == expected);
+        CHECK(callback_keys_of(text) == expected);
+    }
+
+    SECTION("a repeated name is delivered once per occurrence")
+    {
+        const std::string text = R"({"a":1,"a":2})";
+        const std::vector<std::string> expected = {"a", "a"};
+        CHECK(keys_of(text) == expected);
+        CHECK(callback_keys_of(text) == expected);
+    }
+
+    SECTION("binary formats pass the stored bytes through")
+    {
+        const std::string stored = "\xff\\";
+        const std::vector<std::string> expected = {stored};
+        const auto keys_of_bytes = [&keys_of_format](const std::vector<std::uint8_t>& v, json::input_format_t format)
+        {
+            std::string text;
+            for (const auto byte : v)
+            {
+                text.push_back(static_cast<char>(byte));
+            }
+            return keys_of_format(text, format);
+        };
+
+        CHECK(keys_of_bytes({0xA1, 0x62, 0xFF, 0x5C, 0x01}, json::input_format_t::cbor) == expected);
+        CHECK(keys_of_bytes({0x81, 0xA2, 0xFF, 0x5C, 0x01}, json::input_format_t::msgpack) == expected);
+        CHECK(keys_of_bytes({'{', 'i', 2, 0xFF, 0x5C, 'i', 1, '}'}, json::input_format_t::ubjson) == expected);
+        CHECK(keys_of_bytes({0x0D, 0, 0, 0, 0x10, 0xFF, 0x5C, 0, 1, 0, 0, 0, 0}, json::input_format_t::bson) == expected);
+    }
+
+    SECTION("BON8 rejects ill-formed UTF-8 in a name")
+    {
+        const std::vector<std::string> valid = {"\\"};
+        CHECK(keys_of_format(std::string("\x87\x5C\x91"), json::input_format_t::bon8) == valid);
+        CHECK(keys_of_format(std::string("\x87\xC3\x28\x91"), json::input_format_t::bon8).empty());
+    }
+}
@@ -826,6 +826,129 @@ TEST_CASE("JSON patch")
            CHECK(doc.at("foo") == "bar");
        }
 #endif // !defined(JSON_NOEXCEPTION)
+
+        SECTION("applying a value as patch to itself")
+        {
+            // a JSON patch is an array, so an array of operations can be
+            // applied to itself; the operations are read from the patch as
+            // it was before the first operation, as patch() does it
+            const json copy_op = {{"op", "copy"}, {"from", "/0"}, {"path", "/-"}};
+            json copy_ops = json::array();
+            for (int i = 0; i < 5; ++i)
+            {
+                copy_ops.push_back(copy_op);
+            }
+
+            json expected_copies = copy_ops;
+            for (int i = 0; i < 5; ++i)
+            {
+                expected_copies.push_back(copy_op);
+            }
+
+            SECTION("copy operations without spare capacity")
+            {
+                // a copy has exactly as much capacity as elements
+                json doc = copy_ops;
+                CHECK(doc.patch(doc) == expected_copies);
+
+                doc.patch_inplace(doc);
+                CHECK(doc == expected_copies);
+            }
+
+#if JSON_DIAGNOSTICS
+            SECTION("patch stored inside the patched value")
+            {
+                // the parent pointers of JSON_DIAGNOSTICS make the aliasing detectable
+                const json op = {{"op", "replace"}, {"path", "/patch"}, {"value", 1}};
+                json doc = {{"a", 1}, {"patch", json::array({op})}};
+                const json expected = doc.patch(doc["patch"]);
+
+                doc.patch_inplace(doc["patch"]);
+                CHECK(doc == expected);
+            }
+#endif
+
+            SECTION("copy operations with spare capacity")
+            {
+                // reserve while the array is empty: reallocating non-empty
+                // elements behind the library's back leaves stale parent
+                // pointers with JSON_DIAGNOSTICS
+                json doc = json::array();
+                doc.get_ref<json::array_t&>().reserve(100);
+                for (int i = 0; i < 5; ++i)
+                {
+                    doc.push_back(copy_op);
+                }
+                CHECK(doc.patch(doc) == expected_copies);
+
+                doc.patch_inplace(doc);
+                CHECK(doc == expected_copies);
+            }
+
+            SECTION("remove operations")
+            {
+                json doc = R"([
+                        {"op": "remove", "path": "/0"},
+                        {"op": "remove", "path": "/0"},
+                        {"op": "remove", "path": "/0"}
+                    ])"_json;
+                CHECK(doc.patch(doc) == json::array());
+
+                doc.patch_inplace(doc);
+                CHECK(doc == json::array());
+            }
+
+            SECTION("operations that read a changed element")
+            {
+                // the second operation is still a "test" operation, although
+                // the first one replaced it in the document
+                json doc = R"([
+                        {"op": "replace", "path": "/1", "value": 1},
+                        {"op": "test", "path": "/1", "value": 1},
+                        {"op": "add", "path": "/-", "value": 2}
+                    ])"_json;
+                const json expected = R"([
+                        {"op": "replace", "path": "/1", "value": 1},
+                        1,
+                        {"op": "add", "path": "/-", "value": 2},
+                        2
+                    ])"_json;
+                CHECK(doc.patch(doc) == expected);
+
+                doc.patch_inplace(doc);
+                CHECK(doc == expected);
+            }
+
+            SECTION("replacing the root")
+            {
+                json doc = R"([
+                        {"op": "add", "path": "", "value": [1, 2]},
+                        {"op": "add", "path": "/-", "value": 3},
+                        {"op": "replace", "path": "", "value": {"a": 4}}
+                    ])"_json;
+                const json expected = {{"a", 4}};
+                CHECK(doc.patch(doc) == expected);
+
+                doc.patch_inplace(doc);
+                CHECK(doc == expected);
+            }
+
+#if !defined(JSON_NOEXCEPTION)
+            SECTION("failing operation")
+            {
+                // the operations before the failing one remain applied
+                json doc = R"([
+                        {"op": "add", "path": "/-", "value": 1},
+                        {"op": "test", "path": "/0/op", "value": "remove"}
+                    ])"_json;
+                CHECK_THROWS_AS(doc.patch(doc), json::other_error&);
+
+                CHECK_THROWS_AS(doc.patch_inplace(doc), json::other_error&);
+                CHECK(doc.size() == 3);
+                CHECK(doc.back() == 1);
+            }
+#endif // !defined(JSON_NOEXCEPTION)
+        }
    }

    SECTION("errors")
@@ -917,6 +917,46 @@ TEST_CASE("JSON pointers")
        CHECK(ptr.to_string() == "/object/~1");
    }

+    SECTION("appending a pointer to itself")
+    {
+        // operator/= must not pass iterators into its own token vector to
+        // insert(); each pointer is appended to itself and must yield the
+        // pointer whose string representation is the original one twice
+        const std::vector<std::string> pointers =
+        {
+            "",
+            "/",
+            "/a",
+            "/a/b",
+            "/foo/0/-",
+            "/a~1b/~0c/~01",
+            "/1/2/3/4/5/6/7/8/9/10/11/12/13/14/15/16/17"
+        };
+
+        for (const auto& s : pointers)
+        {
+            CAPTURE(s)
+            json::json_pointer ptr(s);
+            const json::json_pointer expected(s + s);
+
+            const json::json_pointer& ret = (ptr /= ptr);
+            CHECK(&ret == &ptr);
+            CHECK(ptr == expected);
+            CHECK(ptr.to_string() == s + s);
+
+            // appending to itself again doubles the pointer once more
+            ptr /= ptr;
+            std::string quadruple = s + s;
+            quadruple += quadruple;
+            CHECK(ptr.to_string() == quadruple);
+
+            // operator/ appends to a copy and leaves the operand unchanged
+            const json::json_pointer original(s);
+            CHECK((original / original) == expected);
+            CHECK(original.to_string() == s);
+        }
+    }
+
    SECTION("equality comparison")
    {
        std::string ptr_string{"/foo/bar"};
@@ -749,6 +749,20 @@ std::string exception_of(F f)
    }
    return "";
 }
+
+// the exception a call on a basic_json value throws, without the byte range of
+// the value (JSON_DIAGNOSTIC_POSITIONS), which the exceptions of views lack
+template<typename F>
+std::string json_exception_of(F f)
+{
+    std::string what = exception_of(f);
+    const std::size_t at = what.find("] (bytes ");
+    if (at != std::string::npos)
+    {
+        what.erase(at + 2, what.find(") ", at) - at);
+    }
+    return what;
+}
 #endif

 // compares a view with the ordered_json value materialize() gives for it:
@@ -957,24 +971,24 @@ TEST_CASE("json_view element access and iteration")
 #if !defined(JSON_NOEXCEPTION)
            if (!j.is_object())
            {
-                CHECK(exception_of([&] { static_cast<void>(v["a"]); }) == exception_of([&] { static_cast<void>(j["a"]); }));
+                CHECK(exception_of([&] { static_cast<void>(v["a"]); }) == json_exception_of([&] { static_cast<void>(j["a"]); }));
            }
            if (!j.is_array())
            {
-                CHECK(exception_of([&] { static_cast<void>(v[0]); }) == exception_of([&] { static_cast<void>(j[0]); }));
+                CHECK(exception_of([&] { static_cast<void>(v[0]); }) == json_exception_of([&] { static_cast<void>(j[0]); }));
            }
-            CHECK(exception_of([&] { static_cast<void>(v.at("a")); }) == exception_of([&] { static_cast<void>(j.at("a")); }));
-            CHECK(exception_of([&] { static_cast<void>(v.at("missing")); }) == exception_of([&] { static_cast<void>(j.at("missing")); }));
-            CHECK(exception_of([&] { static_cast<void>(v.at(0)); }) == exception_of([&] { static_cast<void>(j.at(0)); }));
-            CHECK(exception_of([&] { static_cast<void>(v.at(5)); }) == exception_of([&] { static_cast<void>(j.at(5)); }));
+            CHECK(exception_of([&] { static_cast<void>(v.at("a")); }) == json_exception_of([&] { static_cast<void>(j.at("a")); }));
+            CHECK(exception_of([&] { static_cast<void>(v.at("missing")); }) == json_exception_of([&] { static_cast<void>(j.at("missing")); }));
+            CHECK(exception_of([&] { static_cast<void>(v.at(0)); }) == json_exception_of([&] { static_cast<void>(j.at(0)); }));
+            CHECK(exception_of([&] { static_cast<void>(v.at(5)); }) == json_exception_of([&] { static_cast<void>(j.at(5)); }));
            if (!(j.is_object() && j.empty())) // (key() of an end iterator)
            {
-                CHECK(exception_of([&] { static_cast<void>(v.begin().key()); }) == exception_of([&] { static_cast<void>(j.begin().key()); }));
+                CHECK(exception_of([&] { static_cast<void>(v.begin().key()); }) == json_exception_of([&] { static_cast<void>(j.begin().key()); }));
            }
            if (!j.empty() || j.is_null())
            {
-                CHECK(exception_of([&] { static_cast<void>(v.front()); }) == exception_of([&] { static_cast<void>(j.front()); }));
-                CHECK(exception_of([&] { static_cast<void>(v.back()); }) == exception_of([&] { static_cast<void>(j.back()); }));
+                CHECK(exception_of([&] { static_cast<void>(v.front()); }) == json_exception_of([&] { static_cast<void>(j.front()); }));
+                CHECK(exception_of([&] { static_cast<void>(v.back()); }) == json_exception_of([&] { static_cast<void>(j.back()); }));
            }
 #endif
            CHECK(v.contains("a") == j.contains("a"));
@@ -0,0 +1,364 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  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
+
+#include "doctest_compatibility.h"
+
+#include <nlohmann/json_view.hpp>
+using nlohmann::json;
+using nlohmann::ordered_json;
+using nlohmann::json_document;
+using nlohmann::ordered_json_editable_document;
+using nlohmann::json_view;
+using nlohmann::ordered_json_document;
+
+#include "json_view_test_helpers.hpp"
+using json_view_test::generator;
+
+#include <array>
+#include <cstddef>
+#include <string>
+#include <vector>
+
+// These tests were split off unit-json_view_dump.cpp, whose object file got too
+// large for the MinGW assembler ("file too big"). Like that file, this one is
+// also built with C++17, as it mentions JSON_HAS_CPP_17.
+
+TEST_CASE("json_view comparison")
+{
+    SECTION("equality of the values parse() produces")
+    {
+        generator g;
+        std::vector<std::string> texts;
+        for (int i = 0; i < 600; ++i)
+        {
+            std::string text;
+            g.value(text, 0);
+            texts.push_back(text);
+            // the same value written differently: sorted keys, canonical numbers
+            texts.push_back(json::parse(text).dump(1));
+        }
+        for (std::size_t i = 0; i + 2 < texts.size(); ++i)
+        {
+            for (std::size_t k = i; k < i + 3; ++k)
+            {
+                CAPTURE(texts[i])
+                CAPTURE(texts[k])
+                const json_document a = json_document::parse(texts[i]);
+                const json_document b = json_document::parse(texts[k]);
+                const json ja = json::parse(texts[i]);
+                const json jb = json::parse(texts[k]);
+                CHECK((a.root() == b.root()) == (ja == jb));
+                CHECK((a.root() != b.root()) == (ja != jb));
+                CHECK((a.root() == jb) == (ja == jb));
+                CHECK((jb == a.root()) == (ja == jb));
+                CHECK((a.root() != jb) == (ja != jb));
+                CHECK((jb != a.root()) == (ja != jb));
+
+                // ordered_json compares members in order
+                const ordered_json_document oa = ordered_json_document::parse(texts[i]);
+                const ordered_json_document ob = ordered_json_document::parse(texts[k]);
+                const ordered_json oja = ordered_json::parse(texts[i]);
+                const ordered_json ojb = ordered_json::parse(texts[k]);
+                CHECK((oa.root() == ob.root()) == (oja == ojb));
+                CHECK((oa.root() == ojb) == (oja == ojb));
+            }
+        }
+    }
+
+    SECTION("objects whose first keys differ or repeat")
+    {
+        const std::array<const char*, 17> texts =
+        {
+            {
+                R"({"a":1,"b":2})", R"({"a":1,"c":2})", R"({"b":1,"a":2})", R"({"a":1,"a":2,"b":3})", R"({"a":2,"b":3})",
+                R"({"a":1,"b":1,"a":2})", R"({"a":2,"b":1})", R"({"a":1,"a":2})", R"({"b":1})", R"({"a":1,"b":2,"c":3,"d":4,"e":5})",
+                R"({"a":1,"b":2,"c":3,"d":4,"f":5})", R"({"a":1,"b":2,"c":3,"a":4,"e":5})", R"({"a":4,"b":2,"c":3,"e":5})",
+                R"({"\u0061":1,"b":2})", R"({})", R"([{"a":1,"b":2}])", R"([{"a":1,"c":2}])"
+            }
+        };
+        for (const char* const x : texts)
+        {
+            for (const char* const y : texts)
+            {
+                CAPTURE(x)
+                CAPTURE(y)
+                const ordered_json_document dx = ordered_json_document::parse(x);
+                const ordered_json_document dy = ordered_json_document::parse(y);
+                const ordered_json_editable_document ex = ordered_json_editable_document::parse(x);
+                const ordered_json jx = ordered_json::parse(x);
+                const ordered_json jy = ordered_json::parse(y);
+                CHECK((dx.root() == dy.root()) == (jx == jy));
+                CHECK((dx.root() == jy) == (jx == jy));
+                CHECK((ex.root() == dy.root()) == (jx == jy));
+            }
+        }
+    }
+
+    SECTION("objects with duplicate keys, small and large")
+    {
+        // n members with keys in descending order; with duplicates, some keys
+        // repeat later (the first after unique ones in key order); in reverse,
+        // the members are in ascending key order
+        const auto object = [](int n, bool duplicates, bool reverse, int value)
+        {
+            std::string s = "{";
+            for (int i = 0; i < n; ++i)
+            {
+                const int k = reverse ? i : n - 1 - i;
+                s += (i != 0 ? ",\"k" : "\"k") + std::to_string(100 + k) + "\":" + std::to_string(value + k);
+            }
+            if (duplicates)
+            {
+                for (int k = n / 2; k < n; k += 3)
+                {
+                    s += ",\"k" + std::to_string(100 + k) + "\":" + std::to_string(value + k);
+                }
+            }
+            return s + "}";
+        };
+        std::vector<std::string> texts;
+        for (const int n :
+                {
+                    3, 16, 17, 40
+                })
+        {
+            for (const int flags :
+                    {
+                        0, 1, 2, 3
+                    })
+            {
+                texts.push_back(object(n, (flags & 1) != 0, (flags & 2) != 0, 0));
+            }
+            texts.push_back(object(n, true, false, 1)); // other values
+        }
+        // many objects in one comparison (working memory reused across objects)
+        std::string array = "[";
+        std::string array_other = "[";
+        for (std::size_t i = 0; i < texts.size(); ++i)
+        {
+            array += (i != 0 ? "," : "") + texts[i];
+            array_other += (i != 0 ? "," : "") + texts[texts.size() - 1 - i];
+        }
+        texts.push_back(array + "]");
+        texts.push_back(array_other + "]");
+        for (const std::string& x : texts)
+        {
+            for (const std::string& y : texts)
+            {
+                CAPTURE(x)
+                CAPTURE(y)
+                const ordered_json_document dx = ordered_json_document::parse(x);
+                const ordered_json_document dy = ordered_json_document::parse(y);
+                const ordered_json jx = ordered_json::parse(x);
+                const ordered_json jy = ordered_json::parse(y);
+                CHECK((dx.root() == dy.root()) == (jx == jy));
+                CHECK((dx.root() == jy) == (jx == jy));
+                const json_document ux = json_document::parse(x);
+                const json uy = json::parse(y);
+                CHECK((ux.root() == uy) == (json::parse(x) == uy));
+            }
+        }
+    }
+
+    SECTION("numbers, duplicate keys, member order")
+    {
+        const auto same = [](const char* x, const char* y)
+        {
+            const json_document dx = json_document::parse(x);
+            const json_document dy = json_document::parse(y);
+            return dx.root() == dy.root();
+        };
+        CHECK(same("1", "1.0"));
+        CHECK(same("[1, -1, 2.5]", "[1.0, -1.0, 25e-1]"));
+        CHECK(!same("1", "1.5"));
+        CHECK(same("18446744073709551615", "18446744073709551615"));
+        CHECK(same(R"({"a": 1, "a": 2})", R"({"a": 2})"));
+        CHECK(!same(R"({"a": 1, "a": 2})", R"({"a": 1})"));
+        CHECK(same(R"({"a": 1, "b": 2})", R"({"b": 2, "a": 1})"));
+        CHECK(!same(R"({"a": 1})", R"({"a": 1, "b": 2})"));
+        CHECK(!same("[1, 2]", "[2, 1]"));
+        CHECK(!same("\"a\"", "\"b\""));
+        CHECK(same("\"\\u00e9\"", "\"\xc3\xa9\""));
+        CHECK(!same("null", "false"));
+        CHECK(!same("[]", "{}"));
+        const ordered_json_document dup = ordered_json_document::parse(R"({"a": 1, "b": 2, "a": 3})");
+        const ordered_json_document last = ordered_json_document::parse(R"({"a": 3, "b": 2})");
+        CHECK(dup.root() == last.root());
+        // (== compares as parse() resolves duplicates, a lookup finds the first)
+        CHECK(dup.root()["a"].materialize() == 1);
+        CHECK(dup.root()["a"] != last.root()["a"]);
+        const ordered_json_document ab = ordered_json_document::parse(R"({"a": 1, "b": 2})");
+        const ordered_json_document ba = ordered_json_document::parse(R"({"b": 2, "a": 1})");
+        CHECK(ab.root() != ba.root());
+
+        // discarded values compare as basic_json's do
+        const json discarded(json::value_t::discarded);
+        CHECK((json_view() == json_view()) == (discarded == discarded)); // NOLINT(readability-container-size-empty): operator== is tested
+        CHECK((json_view() == discarded) == (discarded == discarded)); // NOLINT(readability-container-size-empty)
+        const json_document null_document = json_document::parse("null");
+        CHECK(!(json_view() == null_document.root())); // NOLINT(readability-container-size-empty)
+        CHECK(!(null_document.root() == discarded));
+    }
+
+    SECTION("values that are the same text, or the same value written differently, at any depth")
+    {
+        // nested arrays and objects around depths where the walk over equal text gives up
+        for (const int depth :
+                {
+                    1, 5, 47, 48, 49, 50, 60, 300
+                })
+        {
+            CAPTURE(depth)
+            std::string head;
+            std::string tail;
+            for (int i = 0; i < depth; ++i)
+            {
+                head += i % 2 == 0 ? R"({"k":[1,"s",{"x":true},)" : R"([null,2.5,{"y":)";
+                tail.insert(0, i % 2 == 0 ? "]}" : "}]");
+            }
+            // the same text, one number changed, and one number written differently
+            const auto with_number = [&](const char* number)
+            {
+                std::string result = head;
+                result += number;
+                result += tail;
+                return result;
+            };
+            const std::string text = with_number("7");
+            const std::string changed = with_number("8");
+            const std::string spelled = with_number("7.0");
+            const json_document a = json_document::parse(text);
+            const json_document b = json_document::parse(text);
+            const json_document c = json_document::parse(changed);
+            const json_document d = json_document::parse(spelled);
+            CHECK(a.root() == b.root());
+            CHECK(a.root() != c.root());
+            CHECK(c.root() != a.root());
+            CHECK(a.root() == d.root());
+            CHECK(d.root() == a.root());
+            CHECK(a.root() == json::parse(text));
+            CHECK(a.root() != json::parse(changed));
+            CHECK(json::parse(spelled) == a.root());
+            const nlohmann::json_editable_document e = nlohmann::json_editable_document::parse(text);
+            CHECK(a.root() == e.root());
+            CHECK(e.root() == a.root());
+            CHECK(c.root() != e.root());
+            CHECK(e.root() == e.root());
+            const ordered_json_document oa = ordered_json_document::parse(text);
+            const ordered_json_document oc = ordered_json_document::parse(changed);
+            CHECK(oa.root() != oc.root());
+            CHECK(oa.root() == ordered_json::parse(text));
+            CHECK(oc.root() != ordered_json::parse(text));
+        }
+
+        // not the same text, but the same value
+        const auto same = [](const char* x, const char* y)
+        {
+            const json_document dx = json_document::parse(x);
+            const json_document dy = json_document::parse(y);
+            const bool equal = dx.root() == dy.root();
+            CHECK(equal == (json::parse(x) == json::parse(y)));
+            CHECK(equal == (dx.root() == json::parse(y)));
+            return equal;
+        };
+        CHECK(same(R"({"a":1,"a":2})", R"({"a":3,"a":2})"));
+        CHECK(same(R"({"a":1,"b":[1,{"c":2,"c":3}]})", R"({"b":[1,{"c":9,"c":3}],"a":1})"));
+        CHECK(!same(R"({"a":1,"a":2})", R"({"a":2,"a":3})"));
+        CHECK(same("[1.0,-0,0,1e2]", "[1.00,0,-0,100.0]"));
+        CHECK(same(R"(["\u00e9","\n"])", "[\"\xc3\xa9\",\"\\n\"]"));
+        CHECK(!same(R"({"a":[1,2,{"b":null}]})", R"({"a":[1,2,{"b":false}]})"));
+        CHECK(!same(R"({"a":[1,2,{"b":null}]})", R"({"a":[1,2,{"c":null}]})"));
+        CHECK(!same(R"({"a":[1,2,{"b":null}]})", R"({"a":[1,2,{"b":null,"c":1}]})"));
+
+        // edited documents: moved sequences, links, and values of new nodes
+        nlohmann::json_editable_document edited = nlohmann::json_editable_document::parse(R"({"a":[1,2,3],"b":{"c":"d"},"e":0.5})");
+        const json_document plain = json_document::parse(R"({"a":[1,2,3,4],"b":{"c":"x","y":null},"e":0.5,"z":[]})");
+        edited.push_back(edited.root()["a"], 4);
+        edited.set(edited.root()["b"], "c", "x");
+        edited.set(edited.root()["b"], "y", nullptr);
+        edited.set(edited.root(), "z", json::array());
+        CHECK(edited.root() == plain.root());
+        CHECK(plain.root() == edited.root());
+        edited.erase(edited.root()["a"], 0);
+        CHECK(edited.root() != plain.root());
+        CHECK(edited.root()["a"] == json::parse("[2,3,4]"));
+        const json_document tail = json_document::parse("[2,3,4]");
+        CHECK(edited.root()["a"] == tail.root());
+    }
+
+    SECTION("large documents, with a difference at any place")
+    {
+        const auto make = [](std::size_t count, std::size_t changed, bool swap_members)
+        {
+            std::string text = R"({"b":1,"list":[)";
+            for (std::size_t i = 0; i < count; ++i)
+            {
+                text += (i != 0 ? "," : "");
+                const std::string id = std::to_string(i == changed ? i + 1 : i);
+                if (swap_members && i % 3 == 0)
+                {
+                    text += R"({"v":[1.5,"s",{"k":)";
+                    text += id;
+                    text += R"(}],"id":)";
+                    text += id;
+                    text += "}";
+                }
+                else
+                {
+                    text += R"({"id":)";
+                    text += id;
+                    text += R"(,"v":[1.5,"s",{"k":)";
+                    text += id;
+                    text += "}]}";
+                }
+            }
+            return text + R"(],"a":{"y":2,"x":3}})";
+        };
+        const std::size_t count = 3000;
+        for (const std::size_t changed :
+                {
+                    count, std::size_t{0}, std::size_t{1}, count / 2, count - 1
+                })
+        {
+            for (const bool swap :
+                    {
+                        false, true
+                    })
+            {
+                CAPTURE(changed)
+                CAPTURE(swap)
+                const std::string text_a = make(count, count, false);
+                const std::string text_b = make(count, changed, swap);
+                const json_document a = json_document::parse(text_a);
+                const json_document b = json_document::parse(text_b);
+                const bool equal = changed == count;
+                CHECK((a.root() == b.root()) == equal);
+                CHECK((b.root() == a.root()) == equal);
+                CHECK((a.root() == json::parse(text_b)) == equal);
+                CHECK((json::parse(text_b) == a.root()) == equal);
+                CHECK((a.root()["list"] == b.root()["list"]) == equal);
+                const ordered_json_document oa = ordered_json_document::parse(text_a);
+                const ordered_json_document ob = ordered_json_document::parse(text_b);
+                CHECK((oa.root() == ob.root()) == (equal && !swap));
+                CHECK((oa.root() == ordered_json::parse(text_b)) == (equal && !swap));
+            }
+        }
+    }
+
+    SECTION("deep nesting")
+    {
+        const std::string deep = std::string(100000, '[') + std::string(100000, ']');
+        const json_document a = json_document::parse(deep);
+        const json_document b = json_document::parse(deep);
+        CHECK(a.root() == b.root());
+        CHECK(a.root() == json::parse(deep));
+        const std::string other = std::string(100000, '[') + "1" + std::string(100000, ']');
+        const json_document c = json_document::parse(other);
+        CHECK(a.root() != c.root());
+    }
+}
@@ -35,9 +35,9 @@ using json_view_test::has_duplicate_keys;
 #include <string>
 #include <vector>

-// These tests were split off unit-json_view.cpp, whose object file got too large for the MinGW
-// linker (see json_view_test_helpers.hpp). Like that file, this one is also built
-// with C++17, as it mentions JSON_HAS_CPP_17.
+// These tests were split off unit-json_view.cpp, whose object file got too large
+// for the MinGW linker (see json_view_test_helpers.hpp). Like that file, this one
+// is also built with C++17, as it mentions JSON_HAS_CPP_17.

 TEST_CASE("json_view dump")
 {
@@ -150,88 +150,6 @@ TEST_CASE("json_view dump")
            CHECK(many_doc.root().dump() == json::parse(many_tokens).dump());
        }

-        // tokens of 16 and 17 digits without an exponent (like GeoJSON
-        // coordinates), which dump() converts in batches: doubles exactly
-        // halfway between two candidates for the shortest digits, random
-        // digits, and digits near a shorter decimal (...99999997,
-        // ...00000003), whose rounding carries; in pairs and among other
-        // values, so that the batches are interrupted; the last token near the
-        // end of the text
-        {
-            std::mt19937_64 tokens(5627); // NOLINT(cert-msc32-c,cert-msc51-cpp,bugprone-random-generator-seed)
-            const auto draw = [&tokens](std::size_t n)
-            {
-                const std::uint64_t r = tokens() % n;
-                return static_cast<std::size_t>(r);
-            };
-            std::string coordinates = "[754570942.33984373,257769445.56835938,858106901.94921875,97944964.876953125,"
-                                      "[0.5,1e-7],[1.5,-0.0,2.5],[1E2,12.5,0.1,3.25,4.5,5.75,6.125,7.0,8.5],[],[1.5],[1,2.5],[2.5,\"x\"],[[1.5],2.5],";
-            for (int i = 0; i < 20000; ++i)
-            {
-                const std::size_t length = 16 + draw(2);
-                std::string digits(1, static_cast<char>('1' + draw(9)));
-                const std::size_t kept = draw(3) == 0 ? length : 2 + draw(length - 3);
-                for (std::size_t k = 1; k < kept; ++k)
-                {
-                    digits += static_cast<char>('0' + draw(10));
-                }
-                digits += std::string(length - kept, draw(2) == 0 ? '9' : '0');
-                digits.back() = static_cast<char>('0' + draw(10));
-                const std::size_t point = 1 + draw(9);
-                const std::string token = (draw(2) == 0 ? "-" : "") + digits.substr(0, point) + "." + digits.substr(point);
-                if (i != 0)
-                {
-                    coordinates += ',';
-                }
-                if (draw(8) == 0)
-                {
-                    coordinates += R"({"x":)";
-                    coordinates += token;
-                    coordinates += R"(,"s":"a"})";
-                }
-                else
-                {
-                    coordinates += '[';
-                    coordinates += token;
-                    coordinates += ',';
-                    coordinates += token;
-                    coordinates += ']';
-                }
-            }
-            coordinates += ",-65.613616999999977]";
-            const json_document parsed = json_document::parse(coordinates);
-            const ordered_json j = ordered_json::parse(coordinates);
-            CHECK(parsed.root().dump() == j.dump());
-            CHECK(parsed.root().dump(1) == j.dump(1));
-            CHECK(parsed.root().dump(-1, ' ', true) == j.dump(-1, ' ', true));
-            CHECK(parsed.root().back().get<double>() == j.back().get<double>());
-            CHECK(parsed.root().back().dump() == "-65.61361699999998");
-            std::size_t i = 0;
-            for (const json_view v : parsed.root())
-            {
-                const ordered_json& e = j[i++];
-                CHECK(v.dump() == e.dump());
-                if (v.is_array() && !v.empty() && v[0].is_number())
-                {
-                    CHECK(v[0].get<double>() == e[0].get<double>());
-                }
-            }
-
-            // an editable document: edits move some arrays, so that the walk
-            // leaves the order of the parsed nodes
-            ordered_json_editable_document editable = ordered_json_editable_document::parse(coordinates);
-            ordered_json expected = j;
-            for (std::size_t k = 0; k < 20000; k += 97)
-            {
-                if (expected[k].is_array())
-                {
-                    editable.push_back(editable.root()[k], ordered_json(1.5));
-                    expected[k].push_back(1.5);
-                }
-            }
-            CHECK(editable.root().dump() == expected.dump());
-        }
-
        // random doubles, written as parse() and dump() would
        std::mt19937_64 rng(1170); // NOLINT(cert-msc32-c,cert-msc51-cpp,bugprone-random-generator-seed)
        std::string many = "[";
@@ -253,4 +171,673 @@ TEST_CASE("json_view dump")
        const nlohmann::basic_json_document<json_float> float_document = nlohmann::basic_json_document<json_float>::parse("[0.1, 1.5e10, 3.4028235e38]");
        CHECK(float_document.root().dump() == json_float::parse("[0.1, 1.5e10, 3.4028235e38]").dump());
    }
+
+    SECTION("members in document order, all of them")
+    {
+        const json_document d = json_document::parse(R"({"b": 1, "a": 2, "b": 3})");
+        CHECK(d.root().dump() == R"({"b":1,"a":2,"b":3})");
+        CHECK(d.root().dump(1) == "{\n \"b\": 1,\n \"a\": 2,\n \"b\": 3\n}");
+        // dump() writes all members, though the lookup finds the first
+        CHECK(d.root()["b"].dump() == "1");
+    }
+
+    SECTION("deep nesting")
+    {
+        const std::string deep = std::string(100000, '[') + std::string(100000, ']');
+        const json_document deep_document = json_document::parse(deep);
+        CHECK(deep_document.root().dump() == deep);
+    }
+
+    SECTION("ensure_ascii: a character that needs an escape at each position of a string")
+    {
+        // string lengths around the width of the vector steps, in a string value, a key, and a value near the end of the text
+        for (const char* const special :
+                {
+                    "\xC3\xA9", "\xE4\xB8\xAD", "\xF0\x9F\x98\x80", "\x7F", "\\n", "\\u0001", "\\\"", "\\\\"
+                })
+        {
+            for (std::size_t length = 0; length <= 40; ++length)
+            {
+                for (std::size_t position = 0; position <= length; ++position)
+                {
+                    std::string content(length, 'a');
+                    content.insert(position, special);
+                    const std::array<std::string, 3> texts =
+                    {
+                        {
+                            "\"" + content + "\"",
+                            "[\"" + content + "\"]",
+                            "{\"" + content + "\":1}",
+                        }
+                    };
+                    for (const std::string& text : texts)
+                    {
+                        CAPTURE(text)
+                        const ordered_json_document d = ordered_json_document::parse(text);
+                        const ordered_json j = ordered_json::parse(text);
+                        CHECK(d.root().dump(-1, ' ', true) == j.dump(-1, ' ', true));
+                        CHECK(d.root().dump(2, ' ', true) == j.dump(2, ' ', true));
+                        CHECK(d.root().dump() == j.dump());
+                    }
+                }
+            }
+        }
+    }
+
+    SECTION("ensure_ascii: every character of the Basic Multilingual Plane and some beyond")
+    {
+        // (the two- and three-byte sequences, including the ranges that need a check: E0, ED, EF BF BF)
+        std::string text = "[";
+        std::size_t in_chunk = 0;
+        const auto append = [&](std::uint32_t cp)
+        {
+            if (cp < 0x80)
+            {
+                if (cp < 0x20 || cp == '"' || cp == '\\')
+                {
+                    return;
+                }
+                text += static_cast<char>(cp);
+            }
+            else if (cp < 0x800)
+            {
+                text += static_cast<char>(0xC0 | (cp >> 6));
+                text += static_cast<char>(0x80 | (cp & 0x3F));
+            }
+            else if (cp < 0x10000)
+            {
+                text += static_cast<char>(0xE0 | (cp >> 12));
+                text += static_cast<char>(0x80 | ((cp >> 6) & 0x3F));
+                text += static_cast<char>(0x80 | (cp & 0x3F));
+            }
+            else
+            {
+                text += static_cast<char>(0xF0 | (cp >> 18));
+                text += static_cast<char>(0x80 | ((cp >> 12) & 0x3F));
+                text += static_cast<char>(0x80 | ((cp >> 6) & 0x3F));
+                text += static_cast<char>(0x80 | (cp & 0x3F));
+            }
+        };
+        for (std::uint32_t cp = 0x20; cp < 0x10400; ++cp)
+        {
+            if (cp >= 0xD800 && cp < 0xE000)
+            {
+                continue;
+            }
+            if (in_chunk == 0)
+            {
+                text += text.size() > 1 ? ",\"" : "\"";
+            }
+            append(cp);
+            if (++in_chunk == 37)
+            {
+                text += "\"";
+                in_chunk = 0;
+            }
+        }
+        text += in_chunk != 0 ? "\"]" : "]";
+        const ordered_json_document d = ordered_json_document::parse(text);
+        const ordered_json j = ordered_json::parse(text);
+        CHECK(d.root().dump(-1, ' ', true) == j.dump(-1, ' ', true));
+        CHECK(d.root().dump(2, ' ', true) == j.dump(2, ' ', true));
+        CHECK(d.root().dump() == j.dump());
+        CHECK(d.root().dump(2) == j.dump(2));
+    }
+
+    SECTION("deep nesting, indented")
+    {
+        // indentations of up to and beyond the width of the writer's fixed-size copy
+        for (const int depth :
+                {
+                    1, 5, 20, 70, 300
+                })
+        {
+            std::string text;
+            for (int i = 0; i < depth; ++i)
+            {
+                text += i % 2 == 0 ? "[1," : R"({"k":2,"\u00e9":)";
+            }
+            text += "[]";
+            for (int i = depth - 1; i >= 0; --i)
+            {
+                text += i % 2 == 0 ? "]" : "}";
+            }
+            const ordered_json_document d = ordered_json_document::parse(text);
+            const ordered_json j = ordered_json::parse(text);
+            for (const int indent :
+                    {
+                        0, 1, 2, 3, 8
+                    })
+            {
+                CHECK(d.root().dump(indent) == j.dump(indent));
+                CHECK(d.root().dump(indent, '\t') == j.dump(indent, '\t'));
+            }
+        }
+    }
+
+    SECTION("the output buffer of a small value is small")
+    {
+        // an escaped key after the value: its node lies in the arena, so the
+        // source extent of the value cannot be read from the next node
+        const std::string big(100000, 'a');
+        const std::string text = R"({"small":1,"list":[1,2,3],"k\n":")" + big + R"("})";
+        const json_document d = json_document::parse(text);
+        const auto small = d.root()["small"].dump();
+        CHECK(small == "1");
+        CHECK(small.capacity() < 4096);
+        const auto list = d.root()["list"].dump();
+        CHECK(list == "[1,2,3]");
+        CHECK(list.capacity() < 4096);
+        CHECK(d.root()["list"].dump(2).capacity() < 4096);
+
+        // the whole document and the large value are unaffected
+        CHECK(d.root().dump() == ordered_json::parse(text).dump());
+        CHECK(d.root()["k\n"].dump() == "\"" + big + "\"");
+    }
+
+    SECTION("output that outgrows the estimate")
+    {
+        // ensure_ascii writes six bytes for each two-byte character
+        std::string chars;
+        for (int i = 0; i < 5000; ++i)
+        {
+            chars += "\xC3\xA9";
+        }
+        const json_document d = json_document::parse(R"({"a":")" + chars + R"(","k\n":1})");
+        const json expected = json::parse("\"" + chars + "\"");
+        CHECK(d.root()["a"].dump(-1, ' ', true) == expected.dump(-1, ' ', true));
+        CHECK(d.root()["a"].dump(-1, ' ', true).size() == 2 + (5000 * 6));
+    }
+
+    SECTION("ensure_ascii with strings of the source, decoded strings, and edited strings")
+    {
+        // plain ASCII, non-ASCII, escaped (decoded), and mixed strings, as values and as keys;
+        // the second text has a DEL, which ensure_ascii writes as an escape
+        for (const char* const del :
+                {"", "\x7F"
+                })
+        {
+            const std::string text = std::string("{\"plain\":\"abc\",\"caf\xC3\xA9\":\"\xC3\xA9\xE2\x82\xAC\xF0\x9F\x98\x80\",")
+                                     + "\"esc\\n\\\"\":\"a\\tb\\u00e4\\ud83d\\ude00\",\"del\":\"a" + del + "b\",\"\":\"\"," // NOLINT(modernize-raw-string-literal)
+                                     + "\"list\":[\"x\",\"\xC3\xBC\",\"\\\\\",\"long ASCII string with more than thirty-two bytes in it\","
+                                     + "\"long string with more than thirty-two bytes and one non-ASCII byte \xC3\xB6\"],"
+                                     + "\"n\":[1,2.5,-0,true,null]}";
+            const ordered_json j = ordered_json::parse(text);
+            const ordered_json_document d = ordered_json_document::parse(text);
+            CHECK(d.root().dump(-1, ' ', true) == j.dump(-1, ' ', true));
+            CHECK(d.root().dump(4, ' ', true) == j.dump(4, ' ', true));
+            CHECK(d.root().dump() == j.dump());
+            CHECK(d.root()["list"].dump(-1, ' ', true) == j["list"].dump(-1, ' ', true));
+            CHECK(d.root()["del"].dump(-1, ' ', true) == j["del"].dump(-1, ' ', true));
+
+            // strings that an edit wrote (the source strings that they replace were plain)
+            ordered_json_editable_document e = ordered_json_editable_document::parse(text);
+            ordered_json k = j;
+            e.set(e.root()["plain"], std::string("\xC3\xA4gypten"));
+            k["plain"] = "\xC3\xA4gypten";
+            e.set(e.root()["list"][0], std::string("ascii after edit"));
+            k["list"][0] = "ascii after edit";
+            e.set(e.root()["list"][1], std::string("\xC3\xA4"));
+            k["list"][1] = "\xC3\xA4";
+            e.set(e.root()["del"], std::string("tab\there"));
+            k["del"] = "tab\there";
+            CHECK(e.root().dump(-1, ' ', true) == k.dump(-1, ' ', true));
+            CHECK(e.root().dump(2, ' ', true) == k.dump(2, ' ', true));
+            CHECK(e.root().dump() == k.dump());
+
+            // strings that were edited from or to ASCII text
+            e.set(e.root()["list"][2], std::string("\xC3\xA4"));
+            k["list"][2] = "\xC3\xA4";
+            e.set(e.root()["list"][4], std::string("plain again"));
+            k["list"][4] = "plain again";
+            CHECK(e.root().dump(-1, ' ', true) == k.dump(-1, ' ', true));
+        }
+    }
+
+    SECTION("ensure_ascii with DEL or a non-ASCII character at every position")
+    {
+        // the check whether a string of the source has no byte >= 0x7F reads
+        // eight bytes at a time and then the rest one by one
+        for (std::size_t length = 1; length <= 20; ++length)
+        {
+            for (std::size_t pos = 0; pos < length; ++pos)
+            {
+                for (const char* const c :
+                        {
+                            "\x7F", "\x7E", "\xC3\xA4", "\xC3\xBF" // NOLINT(modernize-raw-string-literal)
+                        })
+                {
+                    const std::string s = std::string(pos, 'a') + c + std::string(length - pos - 1, 'b');
+                    std::string text = "[\"";
+                    text.append(s).append("\",{\"").append(s).append("\":1}]");
+                    const json_document d = json_document::parse(text);
+                    const json j = json::parse(text);
+                    CHECK(d.root().dump(-1, ' ', true) == j.dump(-1, ' ', true));
+                    CHECK(d.root().dump(1, ' ', true) == j.dump(1, ' ', true));
+                }
+            }
+        }
+    }
+
+    SECTION("streams and discarded views")
+    {
+        const json_document d = json_document::parse(R"({"a": [1, 2]})");
+        std::ostringstream compact;
+        compact << d.root();
+        CHECK(compact.str() == R"({"a":[1,2]})");
+        std::ostringstream pretty;
+        pretty << std::setw(2) << std::setfill('.') << d.root() << d.root()["a"];
+        CHECK(pretty.str() == "{\n..\"a\": [\n....1,\n....2\n..]\n}[1,2]");
+        CHECK(json_view().dump() == json(json::value_t::discarded).dump());
+    }
+}
+
+TEST_CASE("json_view large objects")
+{
+    // objects with 128 members or more are looked up with a hash index
+    for (const std::size_t members :
+            {
+                127u, 128u, 129u, 10000u
+            })
+    {
+        CAPTURE(members)
+        std::string text = "{";
+        for (std::size_t i = 0; i < members; ++i)
+        {
+            text += (i != 0 ? ",\"" : "\"") + std::string(i % 23, 'k') + std::to_string(i) + (i % 7 == 0 ? "\\n" : "") + "\":" + std::to_string(i);
+        }
+        text += R"(,"":"empty key","k1":"a duplicate of an earlier key"})";
+        const json_document d = json_document::parse(text);
+        const json_view v = d.root();
+        const json j = json::parse(text);
+        for (std::size_t i = 0; i < members; ++i)
+        {
+            const std::string key = std::string(i % 23, 'k') + std::to_string(i) + (i % 7 == 0 ? "\n" : "");
+            CHECK(v[key].get<std::size_t>() == i);
+            CHECK(v.contains(key));
+            CHECK(v.find(key).key() == key);
+            CHECK(v.at(key).get<std::size_t>() == i);
+            CHECK(!v.contains(key + "x"));
+        }
+        CHECK(v[""].get_string() == "empty key");
+        CHECK(v["k1"].get<int>() == 1); // the first of duplicate keys, as for small objects
+        CHECK(!v.contains("missing"));
+        CHECK_THROWS_WITH_AS(v.at("missing"), "[json.exception.out_of_range.403] key 'missing' not found", json::out_of_range&);
+        CHECK(v == j);
+        CHECK(v.materialize() == j);
+    }
+
+    SECTION("duplicate keys: the first member wins, with and without a table")
+    {
+        // an object of `total` members: the keys "k0".."k<n-1>" in order, then
+        // three keys repeated twice more (one copy in the middle, one at the
+        // end), and two keys repeated once; the value of a member is its
+        // position, so that the first member of a key can be told apart
+        struct member
+        {
+            std::string key;
+            std::size_t position;
+        };
+        const auto make_members = [](std::size_t total)
+        {
+            std::vector<std::string> keys;
+            for (std::size_t i = 0; i + 8 < total; ++i)
+            {
+                keys.push_back("k" + std::to_string(i));
+            }
+            const std::size_t n = keys.size();
+            const std::array<std::size_t, 3> triple = {{3, 17, n - 1}};
+            const std::array<std::size_t, 2> twice = {{5, n / 2}};
+            std::vector<std::string> ordered = keys;
+            for (const std::size_t i : triple)
+            {
+                ordered.insert(ordered.begin() + static_cast<std::ptrdiff_t>(ordered.size() / 2), keys[i]);
+            }
+            for (const std::size_t i : twice)
+            {
+                ordered.insert(ordered.begin() + static_cast<std::ptrdiff_t>(ordered.size() / 3), keys[i]);
+            }
+            for (const std::size_t i : triple)
+            {
+                ordered.push_back(keys[i]);
+            }
+            std::vector<member> result;
+            result.reserve(ordered.size());
+            for (std::size_t i = 0; i < ordered.size(); ++i)
+            {
+                result.push_back({ordered[i], i});
+            }
+            return result;
+        };
+
+        // 100 and 127 members: no table; 128 members and more: a table
+        for (const std::size_t total :
+                {
+                    100u, 127u, 128u, 200u, 5000u
+                })
+        {
+            CAPTURE(total)
+            const std::vector<member> members = make_members(total);
+            REQUIRE(members.size() >= total);
+            REQUIRE(members.size() >= 100);
+            std::string text = "{";
+            std::map<std::string, std::size_t> first;
+            std::map<std::string, std::size_t> last;
+            std::map<std::string, std::size_t> occurrences;
+            for (const member& m : members)
+            {
+                text += (text.size() > 1 ? ",\"" : "\"") + m.key + "\":" + std::to_string(m.position);
+                first.insert({m.key, m.position});
+                last[m.key] = m.position;
+                ++occurrences[m.key];
+            }
+            text += '}';
+            REQUIRE(first.size() < members.size());
+
+            const json_document d = json_document::parse(text);
+            const json_view v = d.root();
+            const json j = json::parse(text);
+            CHECK(v.size() == members.size()); // every occurrence is visited
+            const json m = v.materialize();
+            for (const auto& entry : first)
+            {
+                CAPTURE(entry.first)
+                const std::size_t expected = entry.second;
+                CHECK(v[entry.first].get<std::size_t>() == expected);
+                CHECK(v.at(entry.first).get<std::size_t>() == expected);
+                CHECK(v.find(entry.first).value().get<std::size_t>() == expected);
+                CHECK(v.value(entry.first, std::size_t{0}) == expected);
+                CHECK(v.contains(entry.first));
+                CHECK(v.count(entry.first) == occurrences[entry.first]);
+                const std::string pointer = "/" + entry.first;
+                CHECK(v[json::json_pointer(pointer)].get<std::size_t>() == expected);
+                CHECK(v.at(json::json_pointer(pointer)).get<std::size_t>() == expected);
+                CHECK(v.value(json::json_pointer(pointer), std::size_t{0}) == expected);
+                CHECK(v.contains(json::json_pointer(pointer)));
+                // materialize() and parse() keep the last value instead
+                CHECK(j[entry.first].get<std::size_t>() == last.at(entry.first));
+                CHECK(m[entry.first].get<std::size_t>() == last.at(entry.first));
+            }
+            CHECK(!v.contains("k"));
+            CHECK(v["missing"].is_discarded());
+            CHECK(v.materialize() == j);
+            CHECK(v == j);
+        }
+    }
+
+    SECTION("colliding keys")
+    {
+        // the hash is not seeded, so keys that all land in one place must not
+        // make the table build quadratic: such an object gets no table and is
+        // searched linearly
+        constexpr std::size_t members = 300;
+        constexpr std::size_t table_size = 1024; // the table size for 300 members: the next power of two >= 600
+        std::vector<std::string> colliding;
+        std::vector<std::string> spread;
+        for (std::uint64_t counter = 0; colliding.size() < members || spread.size() < members; ++counter)
+        {
+            std::string key(8, 'a');
+            std::uint64_t x = counter;
+            for (std::size_t i = 0; i < 8; ++i, x /= 26)
+            {
+                key[i] = static_cast<char>('a' + (x % 26));
+            }
+            const bool lands_in_slot_zero = (nlohmann::detail::view::key_hash(key.data(), key.size()) & (table_size - 1)) == 0;
+            if (lands_in_slot_zero && colliding.size() < members)
+            {
+                colliding.push_back(key);
+            }
+            else if (!lands_in_slot_zero && spread.size() < members)
+            {
+                spread.push_back(key);
+            }
+        }
+
+        const auto make_text = [](const std::vector<std::string>& keys)
+        {
+            std::string text = "{";
+            for (std::size_t i = 0; i < keys.size(); ++i)
+            {
+                text += (i != 0 ? ",\"" : "\"") + keys[i] + "\":" + std::to_string(i % 10);
+            }
+            return text + "}";
+        };
+        const std::string colliding_text = make_text(colliding);
+        const std::string spread_text = make_text(spread);
+
+        json_document with_collisions = json_document::parse(colliding_text);
+        json_document without_collisions = json_document::parse(spread_text);
+        for (const auto* pair :
+                {
+                    &colliding, &spread
+                })
+        {
+            const json_view v = (pair == &colliding ? with_collisions : without_collisions).root();
+            for (std::size_t i = 0; i < members; ++i)
+            {
+                CAPTURE(i)
+                CHECK(v[(*pair)[i]].get<std::size_t>() == i % 10);
+                CHECK(v.at((*pair)[i]).get<std::size_t>() == i % 10);
+                CHECK(v.find((*pair)[i]).key() == (*pair)[i]);
+                CHECK(!v.contains((*pair)[i] + "x"));
+            }
+            CHECK(!v.contains("missing"));
+        }
+        CHECK(with_collisions.root() == json::parse(colliding_text));
+
+        // only the object with the spread keys got a table (both texts have the
+        // same length, so the tables are the only difference)
+        with_collisions.shrink_to_fit();
+        without_collisions.shrink_to_fit();
+        CHECK(without_collisions.memory_usage() >= with_collisions.memory_usage() + (table_size * sizeof(std::uint32_t)));
+    }
+
+    SECTION("keys that differ in their last bytes are spread over the table")
+    {
+        // The hash must spread the usual families of keys (numbered names, hex
+        // strings, dates, short names): a key farther than index_max_displacement
+        // from its home slot would leave the object without a table. The keys
+        // are placed with linear probing, as the table does.
+        const auto max_displacement = [](const std::vector<std::string>& keys)
+        {
+            std::size_t slots = 16;
+            while (slots < 2 * keys.size())
+            {
+                slots *= 2;
+            }
+            std::vector<bool> used(slots, false);
+            std::size_t farthest = 0;
+            for (const std::string& key : keys)
+            {
+                std::size_t i = nlohmann::detail::conditional_static_cast<std::size_t>(nlohmann::detail::view::key_hash(key.data(), key.size())) & (slots - 1);
+                std::size_t distance = 0;
+                while (used[i])
+                {
+                    i = (i + 1) & (slots - 1);
+                    ++distance;
+                }
+                used[i] = true;
+                farthest = (std::max)(farthest, distance);
+            }
+            return farthest;
+        };
+        // the keys of a printf-like pattern with one %d, %0Nd or %0Nx, formatted with a stream
+        // (a format string that is not a literal is a Flawfinder error)
+        const auto numbered = [](const char* format, int count, int step)
+        {
+            const std::string pattern(format);
+            const std::size_t percent = pattern.find('%');
+            std::size_t conversion = percent + 1;
+            std::size_t width = 0;
+            while (pattern[conversion] >= '0' && pattern[conversion] <= '9')
+            {
+                width = (width * 10) + static_cast<std::size_t>(pattern[conversion] - '0');
+                ++conversion;
+            }
+            const bool hex = pattern[conversion] == 'x';
+            std::vector<std::string> keys;
+            for (int i = 0; i < count; ++i)
+            {
+                std::ostringstream key;
+                key << pattern.substr(0, percent) << std::setfill('0') << std::setw(static_cast<int>(width))
+                    << (hex ? std::hex : std::dec) << (i * step) << pattern.substr(conversion + 1);
+                keys.push_back(key.str());
+            }
+            return keys;
+        };
+        for (const char* format :
+                {"key%d", "%d", "item_%04d", "a%05d", "%03dxyz", "id%d", "user_%d", "%d_suffix", "0x%04x", "A%07d", "12345678%d", "1234567%d", "123456789%d",
+                 "configuration_parameter_value_%04d_extra", "2026-01-%02dT00:00:00Z"
+                })
+        {
+            CAPTURE(format)
+            CHECK(max_displacement(numbered(format, std::string(format).find("%02d") != std::string::npos ? 60 : 1000, 1)) < nlohmann::detail::view::index_max_displacement); // NOLINT(abseil-string-find-str-contains)
+            CHECK(max_displacement(numbered(format, 600, 7)) < nlohmann::detail::view::index_max_displacement);
+        }
+        std::mt19937_64 rng(7); // NOLINT(cert-msc32-c,cert-msc51-cpp,bugprone-random-generator-seed)
+        for (const std::size_t length :
+                {
+                    std::size_t{1}, std::size_t{2}, std::size_t{3}, std::size_t{5}, std::size_t{7}, std::size_t{8}, std::size_t{9}, std::size_t{12}, std::size_t{16}, std::size_t{17}, std::size_t{33}
+                })
+        {
+            CAPTURE(length)
+            std::set<std::string> distinct;
+            // (there are 26 and 676 keys of one and two letters)
+            std::size_t wanted = 700;
+            if (length == 1)
+            {
+                wanted = 26;
+            }
+            else if (length == 2)
+            {
+                wanted = 500;
+            }
+            while (distinct.size() < wanted)
+            {
+                std::string key(length, 'a');
+                for (char& c : key)
+                {
+                    c = static_cast<char>('a' + (rng() % 26));
+                }
+                distinct.insert(key);
+            }
+            CHECK(max_displacement(std::vector<std::string>(distinct.begin(), distinct.end())) < nlohmann::detail::view::index_max_displacement);
+        }
+    }
+
+    SECTION("keys of every length that differ in one byte")
+    {
+        // In a large object, a key is found by comparing its bytes with those of the member the
+        // table points to: up to 16 bytes as two overlapping words, longer ones with memcmp.
+        // Keys of every length from 0 to 40, and keys that differ from them in one byte.
+        std::mt19937_64 rng(2026); // NOLINT(cert-msc32-c,cert-msc51-cpp,bugprone-random-generator-seed)
+        std::vector<std::string> keys;
+        std::set<std::string> distinct;
+        for (std::size_t length = 0; length <= 40; ++length)
+        {
+            for (int copy = 0; copy < 5; ++copy)
+            {
+                std::string key(length, 'a');
+                for (char& c : key)
+                {
+                    c = static_cast<char>('a' + (rng() % 26));
+                }
+                if (distinct.insert(key).second)
+                {
+                    keys.push_back(key);
+                }
+            }
+        }
+        std::string text = "{";
+        for (std::size_t i = 0; i < keys.size(); ++i)
+        {
+            text += (i != 0 ? ",\"" : "\"") + keys[i] + "\":" + std::to_string(i);
+        }
+        text += "}";
+        REQUIRE(keys.size() >= 128); // (a table is built for 128 members)
+        const json_document d = json_document::parse(text);
+        const json_view v = d.root();
+        for (std::size_t i = 0; i < keys.size(); ++i)
+        {
+            CAPTURE(keys[i])
+            CHECK(v[keys[i]].get<std::size_t>() == i);
+            CHECK(v.at(keys[i]).get<std::size_t>() == i);
+            CHECK(v.contains(keys[i]));
+            for (std::size_t at = 0; at < keys[i].size(); ++at)
+            {
+                std::string other = keys[i];
+                other[at] = other[at] == 'z' ? 'y' : 'z';
+                CAPTURE(other)
+                CHECK(v.contains(other) == (distinct.count(other) != 0));
+            }
+            CHECK(v.contains(keys[i] + "a") == (distinct.count(keys[i] + "a") != 0));
+            if (!keys[i].empty())
+            {
+                CHECK(v.contains(keys[i].substr(1)) == (distinct.count(keys[i].substr(1)) != 0));
+            }
+        }
+    }
+
+    SECTION("shrink_to_fit releases the tables' spare capacity")
+    {
+        const auto make_text = [](int objects, int members)
+        {
+            std::string text = "[";
+            for (int object = 0; object < objects; ++object)
+            {
+                text += object != 0 ? ",{" : "{";
+                for (int i = 0, n = members + object; i < n; ++i)
+                {
+                    text += (i != 0 ? ",\"" : "\"") + std::to_string(i) + "\":" + std::to_string(i);
+                }
+                text += '}';
+            }
+            return text + "]";
+        };
+        const std::string small_text = make_text(5, 150);
+        const std::string big_text = make_text(40, 400);
+
+        // reading a big text, and then a small one, leaves the spare capacity
+        // of the big one: shrink_to_fit() brings the document to the size of
+        // one parsed from the small text alone
+        json_document d = json_document::parse(big_text);
+        const std::size_t big = d.memory_usage();
+        d.read(small_text);
+        CHECK(d.memory_usage() >= big);
+        d.shrink_to_fit();
+        json_document fresh = json_document::parse(small_text);
+        fresh.shrink_to_fit();
+        CHECK(d.memory_usage() == fresh.memory_usage());
+        CHECK(d.memory_usage() < big / 2);
+        CHECK(d.root() == json::parse(small_text));
+        for (int object = 0; object < 5; ++object)
+        {
+            const json_view v = d.root()[static_cast<std::size_t>(object)];
+            for (int i = 0, n = 150 + object; i < n; ++i)
+            {
+                CHECK(v[std::to_string(i)].get<int>() == i);
+            }
+        }
+    }
+
+    SECTION("nested, reused, and in arrays")
+    {
+        std::string inner = "{";
+        for (int i = 0; i < 300; ++i)
+        {
+            inner += (i != 0 ? ",\"m" : "\"m") + std::to_string(i) + "\":" + std::to_string(i);
+        }
+        inner += '}';
+        const std::string text = "[" + inner + ",{\"x\":" + inner + "}," + inner + "]";
+        json_document d = json_document::parse(text);
+        CHECK(d.root()[0]["m299"].get<int>() == 299);
+        CHECK(d.root()[1]["x"]["m150"].get<int>() == 150);
+        CHECK(d.root()[2]["m0"].get<int>() == 0);
+        const std::size_t with_index = d.memory_usage();
+        d.read(std::string("{\"small\": 1}"));
+        CHECK(d.root()["small"].get<int>() == 1);
+        d.read(text);
+        CHECK(d.root()[2]["m7"].get<int>() == 7);
+        CHECK(d.memory_usage() >= with_index / 2);
+    }
 }
@@ -1,298 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++ (supporting code)
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-License-Identifier: MIT
-
-#include "doctest_compatibility.h"
-
-#include <nlohmann/json_view.hpp>
-using nlohmann::json;
-using nlohmann::ordered_json;
-using nlohmann::json_document;
-using nlohmann::ordered_json_editable_document;
-using nlohmann::json_view;
-using nlohmann::ordered_json_document;
-using nlohmann::ordered_json_view;
-
-#include <algorithm>
-#include <array>
-#include <cmath>
-#include <cstddef>
-#include <cstdint>
-#include <cstring>
-#include <iomanip>
-#include <map>
-#include <random>
-#include <set>
-#include <sstream>
-#include <string>
-#include <vector>
-
-// These tests were split off unit-json_view_dump.cpp, whose object file got too large for the MinGW
-// linker (see json_view_test_helpers.hpp). Like that file, this one is also built
-// with C++17, as it mentions JSON_HAS_CPP_17.
-
-TEST_CASE("json_view dump: escaping, nesting, and output buffers")
-{
-    SECTION("members in document order, all of them")
-    {
-        const json_document d = json_document::parse(R"({"b": 1, "a": 2, "b": 3})");
-        CHECK(d.root().dump() == R"({"b":1,"a":2,"b":3})");
-        CHECK(d.root().dump(1) == "{\n \"b\": 1,\n \"a\": 2,\n \"b\": 3\n}");
-        // dump() writes all members, though the lookup finds the first
-        CHECK(d.root()["b"].dump() == "1");
-    }
-
-    SECTION("deep nesting")
-    {
-        const std::string deep = std::string(100000, '[') + std::string(100000, ']');
-        const json_document deep_document = json_document::parse(deep);
-        CHECK(deep_document.root().dump() == deep);
-    }
-
-    SECTION("ensure_ascii: a character that needs an escape at each position of a string")
-    {
-        // string lengths around the width of the vector steps, in a string value, a key, and a value near the end of the text
-        for (const char* const special :
-                {
-                    "\xC3\xA9", "\xE4\xB8\xAD", "\xF0\x9F\x98\x80", "\x7F", "\\n", "\\u0001", "\\\"", "\\\\"
-                })
-        {
-            for (std::size_t length = 0; length <= 40; ++length)
-            {
-                for (std::size_t position = 0; position <= length; ++position)
-                {
-                    std::string content(length, 'a');
-                    content.insert(position, special);
-                    const std::array<std::string, 3> texts =
-                    {
-                        {
-                            "\"" + content + "\"",
-                            "[\"" + content + "\"]",
-                            "{\"" + content + "\":1}",
-                        }
-                    };
-                    for (const std::string& text : texts)
-                    {
-                        CAPTURE(text)
-                        const ordered_json_document d = ordered_json_document::parse(text);
-                        const ordered_json j = ordered_json::parse(text);
-                        CHECK(d.root().dump(-1, ' ', true) == j.dump(-1, ' ', true));
-                        CHECK(d.root().dump(2, ' ', true) == j.dump(2, ' ', true));
-                        CHECK(d.root().dump() == j.dump());
-                    }
-                }
-            }
-        }
-    }
-
-    SECTION("ensure_ascii: every character of the Basic Multilingual Plane and some beyond")
-    {
-        // (the two- and three-byte sequences, including the ranges that need a check: E0, ED, EF BF BF)
-        std::string text = "[";
-        std::size_t in_chunk = 0;
-        const auto append = [&](std::uint32_t cp)
-        {
-            if (cp < 0x80)
-            {
-                if (cp < 0x20 || cp == '"' || cp == '\\')
-                {
-                    return;
-                }
-                text += static_cast<char>(cp);
-            }
-            else if (cp < 0x800)
-            {
-                text += static_cast<char>(0xC0 | (cp >> 6));
-                text += static_cast<char>(0x80 | (cp & 0x3F));
-            }
-            else if (cp < 0x10000)
-            {
-                text += static_cast<char>(0xE0 | (cp >> 12));
-                text += static_cast<char>(0x80 | ((cp >> 6) & 0x3F));
-                text += static_cast<char>(0x80 | (cp & 0x3F));
-            }
-            else
-            {
-                text += static_cast<char>(0xF0 | (cp >> 18));
-                text += static_cast<char>(0x80 | ((cp >> 12) & 0x3F));
-                text += static_cast<char>(0x80 | ((cp >> 6) & 0x3F));
-                text += static_cast<char>(0x80 | (cp & 0x3F));
-            }
-        };
-        for (std::uint32_t cp = 0x20; cp < 0x10400; ++cp)
-        {
-            if (cp >= 0xD800 && cp < 0xE000)
-            {
-                continue;
-            }
-            if (in_chunk == 0)
-            {
-                text += text.size() > 1 ? ",\"" : "\"";
-            }
-            append(cp);
-            if (++in_chunk == 37)
-            {
-                text += "\"";
-                in_chunk = 0;
-            }
-        }
-        text += in_chunk != 0 ? "\"]" : "]";
-        const ordered_json_document d = ordered_json_document::parse(text);
-        const ordered_json j = ordered_json::parse(text);
-        CHECK(d.root().dump(-1, ' ', true) == j.dump(-1, ' ', true));
-        CHECK(d.root().dump(2, ' ', true) == j.dump(2, ' ', true));
-        CHECK(d.root().dump() == j.dump());
-        CHECK(d.root().dump(2) == j.dump(2));
-    }
-
-    SECTION("deep nesting, indented")
-    {
-        // indentations of up to and beyond the width of the writer's fixed-size copy
-        for (const int depth :
-                {
-                    1, 5, 20, 70, 300
-                })
-        {
-            std::string text;
-            for (int i = 0; i < depth; ++i)
-            {
-                text += i % 2 == 0 ? "[1," : R"({"k":2,"\u00e9":)";
-            }
-            text += "[]";
-            for (int i = depth - 1; i >= 0; --i)
-            {
-                text += i % 2 == 0 ? "]" : "}";
-            }
-            const ordered_json_document d = ordered_json_document::parse(text);
-            const ordered_json j = ordered_json::parse(text);
-            for (const int indent :
-                    {
-                        0, 1, 2, 3, 8
-                    })
-            {
-                CHECK(d.root().dump(indent) == j.dump(indent));
-                CHECK(d.root().dump(indent, '\t') == j.dump(indent, '\t'));
-            }
-        }
-    }
-
-    SECTION("the output buffer of a small value is small")
-    {
-        // an escaped key after the value: its node lies in the arena, so the
-        // source extent of the value cannot be read from the next node
-        const std::string big(100000, 'a');
-        const std::string text = R"({"small":1,"list":[1,2,3],"k\n":")" + big + R"("})";
-        const json_document d = json_document::parse(text);
-        const auto small = d.root()["small"].dump();
-        CHECK(small == "1");
-        CHECK(small.capacity() < 4096);
-        const auto list = d.root()["list"].dump();
-        CHECK(list == "[1,2,3]");
-        CHECK(list.capacity() < 4096);
-        CHECK(d.root()["list"].dump(2).capacity() < 4096);
-
-        // the whole document and the large value are unaffected
-        CHECK(d.root().dump() == ordered_json::parse(text).dump());
-        CHECK(d.root()["k\n"].dump() == "\"" + big + "\"");
-    }
-
-    SECTION("output that outgrows the estimate")
-    {
-        // ensure_ascii writes six bytes for each two-byte character
-        std::string chars;
-        for (int i = 0; i < 5000; ++i)
-        {
-            chars += "\xC3\xA9";
-        }
-        const json_document d = json_document::parse(R"({"a":")" + chars + R"(","k\n":1})");
-        const json expected = json::parse("\"" + chars + "\"");
-        CHECK(d.root()["a"].dump(-1, ' ', true) == expected.dump(-1, ' ', true));
-        CHECK(d.root()["a"].dump(-1, ' ', true).size() == 2 + (5000 * 6));
-    }
-
-    SECTION("ensure_ascii with strings of the source, decoded strings, and edited strings")
-    {
-        // plain ASCII, non-ASCII, escaped (decoded), and mixed strings, as values and as keys;
-        // the second text has a DEL, which ensure_ascii writes as an escape
-        for (const char* const del :
-                {"", "\x7F"
-                })
-        {
-            const std::string text = std::string("{\"plain\":\"abc\",\"caf\xC3\xA9\":\"\xC3\xA9\xE2\x82\xAC\xF0\x9F\x98\x80\",")
-                                     + "\"esc\\n\\\"\":\"a\\tb\\u00e4\\ud83d\\ude00\",\"del\":\"a" + del + "b\",\"\":\"\"," // NOLINT(modernize-raw-string-literal)
-                                     + "\"list\":[\"x\",\"\xC3\xBC\",\"\\\\\",\"long ASCII string with more than thirty-two bytes in it\","
-                                     + "\"long string with more than thirty-two bytes and one non-ASCII byte \xC3\xB6\"],"
-                                     + "\"n\":[1,2.5,-0,true,null]}";
-            const ordered_json j = ordered_json::parse(text);
-            const ordered_json_document d = ordered_json_document::parse(text);
-            CHECK(d.root().dump(-1, ' ', true) == j.dump(-1, ' ', true));
-            CHECK(d.root().dump(4, ' ', true) == j.dump(4, ' ', true));
-            CHECK(d.root().dump() == j.dump());
-            CHECK(d.root()["list"].dump(-1, ' ', true) == j["list"].dump(-1, ' ', true));
-            CHECK(d.root()["del"].dump(-1, ' ', true) == j["del"].dump(-1, ' ', true));
-
-            // strings that an edit wrote (the source strings that they replace were plain)
-            ordered_json_editable_document e = ordered_json_editable_document::parse(text);
-            ordered_json k = j;
-            e.set(e.root()["plain"], std::string("\xC3\xA4gypten"));
-            k["plain"] = "\xC3\xA4gypten";
-            e.set(e.root()["list"][0], std::string("ascii after edit"));
-            k["list"][0] = "ascii after edit";
-            e.set(e.root()["list"][1], std::string("\xC3\xA4"));
-            k["list"][1] = "\xC3\xA4";
-            e.set(e.root()["del"], std::string("tab\there"));
-            k["del"] = "tab\there";
-            CHECK(e.root().dump(-1, ' ', true) == k.dump(-1, ' ', true));
-            CHECK(e.root().dump(2, ' ', true) == k.dump(2, ' ', true));
-            CHECK(e.root().dump() == k.dump());
-
-            // strings that were edited from or to ASCII text
-            e.set(e.root()["list"][2], std::string("\xC3\xA4"));
-            k["list"][2] = "\xC3\xA4";
-            e.set(e.root()["list"][4], std::string("plain again"));
-            k["list"][4] = "plain again";
-            CHECK(e.root().dump(-1, ' ', true) == k.dump(-1, ' ', true));
-        }
-    }
-
-    SECTION("ensure_ascii with DEL or a non-ASCII character at every position")
-    {
-        // the check whether a string of the source has no byte >= 0x7F reads
-        // eight bytes at a time and then the rest one by one
-        for (std::size_t length = 1; length <= 20; ++length)
-        {
-            for (std::size_t pos = 0; pos < length; ++pos)
-            {
-                for (const char* const c :
-                        {
-                            "\x7F", "\x7E", "\xC3\xA4", "\xC3\xBF" // NOLINT(modernize-raw-string-literal)
-                        })
-                {
-                    const std::string s = std::string(pos, 'a') + c + std::string(length - pos - 1, 'b');
-                    std::string text = "[\"";
-                    text.append(s).append("\",{\"").append(s).append("\":1}]");
-                    const json_document d = json_document::parse(text);
-                    const json j = json::parse(text);
-                    CHECK(d.root().dump(-1, ' ', true) == j.dump(-1, ' ', true));
-                    CHECK(d.root().dump(1, ' ', true) == j.dump(1, ' ', true));
-                }
-            }
-        }
-    }
-
-    SECTION("streams and discarded views")
-    {
-        const json_document d = json_document::parse(R"({"a": [1, 2]})");
-        std::ostringstream compact;
-        compact << d.root();
-        CHECK(compact.str() == R"({"a":[1,2]})");
-        std::ostringstream pretty;
-        pretty << std::setw(2) << std::setfill('.') << d.root() << d.root()["a"];
-        CHECK(pretty.str() == "{\n..\"a\": [\n....1,\n....2\n..]\n}[1,2]");
-        CHECK(json_view().dump() == json(json::value_t::discarded).dump());
-    }
-}
@@ -941,3 +941,123 @@ TEST_CASE("json_view edits: duplicate keys")
        CHECK(d.root()["o"]["d"].get<int>() == 0);
    }
 }
+
+#if !defined(JSON_NOEXCEPTION)
+TEST_CASE("json_view edits: check_utf8 agrees with the byte-wise check")
+{
+    namespace dv = nlohmann::detail::view;
+
+    // "ok" or the exception message
+    const auto run = [](bool fast, const std::string & s) -> std::string
+    {
+        try
+        {
+            if (fast)
+            {
+                dv::check_utf8(s.data(), s.size());
+            }
+            else
+            {
+                dv::check_utf8_bytewise(reinterpret_cast<const unsigned char*>(s.data()), s.size(), 0);
+            }
+        }
+        catch (const json::type_error& e)
+        {
+            return {e.what()};
+        }
+        return {"ok"};
+    };
+    std::size_t errors = 0;
+    const auto same = [&](const std::string & s)
+    {
+        const std::string a = run(true, s);
+        const std::string b = run(false, s);
+        if (a != b)
+        {
+            INFO("fast: " << a << ", byte-wise: " << b << ", length " << s.size());
+            CHECK(a == b);
+        }
+        errors += b != "ok" ? 1u : 0u;
+    };
+
+    const std::vector<std::string> pieces =
+    {
+        "a", "Z", " ", "\"", "\\", "\n", "\x01", "\x7f", "\xc3\xa4", "\xe4\xb8\xad", "\xf0\x9f\x98\x80",
+        "\x80", "\xbf", "\xc0\x80", "\xc1\xbf", "\xc2", "\xe0\x80\x80", "\xe0\x9f\xbf", "\xed\xa0\x80", "\xed\xbf\xbf",
+        "\xf0\x80\x80\x80", "\xf0\x8f\xbf\xbf", "\xf4\x90\x80\x80", "\xf4\x8f\xbf\xbf", "\xf5", "\xf8", "\xff", "\xfe",
+        "\xe4\xb8", "\xf0\x9f\x98", "\xf0\x9f", "\xf0"
+    };
+
+    // every piece behind prefixes of every length, and followed by more bytes
+    for (std::size_t prefix = 0; prefix <= 64; ++prefix)
+    {
+        for (const auto& piece : pieces)
+        {
+            same(std::string(prefix, 'x') + piece);
+            same(std::string(prefix, 'x') + piece + "yz");
+            same(std::string(prefix, '"') + piece);
+            same(std::string(prefix, '\xc3') + piece);
+            same(std::string(prefix / 2, '\xc3').append(prefix / 2, '\xa4') + piece);
+            same(std::string(prefix, 'x') + "\xe4\xb8\xad" + piece);
+        }
+    }
+    // an invalid byte at every position of valid strings of every length
+    for (std::size_t len = 0; len <= 64; ++len)
+    {
+        const std::string ascii(len, 'a');
+        std::string mixed;
+        while (mixed.size() < len)
+        {
+            if (mixed.size() % 7 == 0)
+            {
+                mixed += "\xc3\xa4";
+            }
+            else if (mixed.size() % 11 == 0)
+            {
+                mixed += "\xf0\x9f\x98\x80";
+            }
+            else
+            {
+                mixed += "a";
+            }
+        }
+        same(ascii);
+        same(mixed);
+        for (std::size_t pos = 0; pos < len; ++pos)
+        {
+            for (const char bad :
+                    {'\x80', '\xc0', '\xc2', '\xe0', '\xf4', '\xff', '"', '\\', '\x1f'
+                    })
+            {
+                std::string s = ascii;
+                s[pos] = bad;
+                same(s);
+                s = mixed;
+                s[pos] = bad;
+                same(s);
+            }
+        }
+    }
+    // random bytes, biased to the interesting ones
+    std::mt19937 gen(5869); // NOLINT(cert-msc32-c,cert-msc51-cpp,bugprone-random-generator-seed): reproducible
+    static const std::array<unsigned char, 23> interesting = {{0x00, 0x1f, 0x22, 0x5c, 0x7f, 0x80, 0x8f, 0x90, 0x9f, 0xa0, 0xbf, 0xc0, 0xc2, 0xdf, 0xe0, 0xe1, 0xed, 0xef, 0xf0, 0xf1, 0xf4, 0xf5, 0xff}};
+    for (int i = 0; i < 100000; ++i)
+    {
+        std::string s(gen() % 80, 'a');
+        for (auto& c : s)
+        {
+            const unsigned r = gen() % 8;
+            if (r == 0)
+            {
+                c = static_cast<char>(gen() & 0xff);
+            }
+            else if (r == 1)
+            {
+                c = static_cast<char>(interesting[gen() % interesting.size()]);
+            }
+        }
+        same(s);
+    }
+    CHECK(errors > 1000);
+}
+#endif
@@ -54,14 +54,18 @@ int accepts_any(nlohmann::basic_json_view<BasicJsonType, Mode> /*unused*/)
    return Mode == nlohmann::view_mode::editable ? 3 : 4;
 }

-template<typename View>
-auto overload(View v) -> decltype(accepts_editable(v))
+// overloads that differ only in the mode; deduction ignores the conversion from
+// read-only to editable views, so each view picks the overload of its own mode
+// (two templates that differ only in a decltype return type are a redefinition
+// for MSVC 2015)
+template<typename BasicJsonType>
+int overload(nlohmann::basic_json_view<BasicJsonType, nlohmann::view_mode::editable> v)
 {
    return accepts_editable(v);
 }

-template<typename View>
-auto overload(View v) -> decltype(accepts_read_only(v))
+template<typename BasicJsonType>
+int overload(nlohmann::basic_json_view<BasicJsonType, nlohmann::view_mode::read_only> v)
 {
    return accepts_read_only(v);
 }
@@ -69,9 +69,12 @@ struct point
 struct shape
 {
    // initialized for GCC -Weffc++
+    // NOLINTNEXTLINE(readability-redundant-member-init)
    std::string name{};
+    // NOLINTNEXTLINE(readability-redundant-member-init)
    std::vector<point> points{};
    point center{};
+    // NOLINTNEXTLINE(readability-redundant-member-init)
    std::map<std::string, point> named{};
    NLOHMANN_DEFINE_TYPE_INTRUSIVE(shape, name, points, center, named)
 };
@@ -82,13 +85,17 @@ struct with_defaults
    std::string b = "default";
    std::vector<int> c = {1, 2};
 };
+// NOLINTNEXTLINE(misc-use-internal-linkage): found by ADL, like the from_json() functions of users
 NLOHMANN_DEFINE_TYPE_NON_INTRUSIVE_WITH_DEFAULT(with_defaults, a, b, c)

 struct with_names
 {
    int value = 0;
-    std::string text{};  // initialized for GCC -Weffc++
+    // initialized for GCC -Weffc++
+    // NOLINTNEXTLINE(readability-redundant-member-init)
+    std::string text{};
 };
+// NOLINTNEXTLINE(misc-use-internal-linkage): found by ADL, like the from_json() functions of users
 NLOHMANN_DEFINE_TYPE_NON_INTRUSIVE_WITH_NAMES(with_names, "Value", value, "Text", text)

 struct empty
@@ -102,6 +109,7 @@ enum class color
    green,
    blue
 };
+// NOLINTNEXTLINE(misc-use-internal-linkage): found by ADL, like the from_json() functions of users
 NLOHMANN_JSON_SERIALIZE_ENUM(color,
 {
    {color::red, "red"},
@@ -114,6 +122,7 @@ enum class strict_color
    red,
    green
 };
+// NOLINTNEXTLINE(misc-use-internal-linkage): found by ADL, like the from_json() functions of users
 NLOHMANN_JSON_SERIALIZE_ENUM_STRICT(strict_color,
 {
    {strict_color::red, "red"},
@@ -154,6 +163,7 @@ struct derived_from_legacy : legacy_base
 {
    int extra = 0;
 };
+// NOLINTNEXTLINE(misc-use-internal-linkage): found by ADL, like the from_json() functions of users
 NLOHMANN_DEFINE_DERIVED_TYPE_NON_INTRUSIVE(derived_from_legacy, legacy_base, extra)

 // from_json() for json only: converted through materialize()
@@ -301,18 +311,19 @@ TEST_CASE("json_view from_json")
        CHECK(same<std::string>(v, j, "text"));
        CHECK(same<std::nullptr_t>(v, j, "nothing"));
        CHECK(same<json>(v, j, "object"));
-        const std::valarray<int> va = v["ints"].get<std::valarray<int>>();
+        const auto va = v["ints"].get<std::valarray<int>>();
        CHECK(va.size() == 4);
        CHECK(va[0] == 3);
        int c_array[2][2] = {{0, 0}, {0, 0}}; // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays): the conversion to C arrays
        v["nested"][0].get_to(c_array[0]);
        CHECK(c_array[0][1] == 2);
 #ifdef JSON_HAS_CPP_17
-        CHECK(v["points"][0].get<std::optional<point>>()->y == 2);
+        const auto first = v["points"][0].get<std::optional<point>>();
+        CHECK((first.has_value() && first->y == 2));
        CHECK(!v["nothing"].get<std::optional<point>>().has_value());
 #endif
        // containers of views keep views of the elements
-        const std::vector<json_view> views = v["points"].get<std::vector<json_view>>();
+        const auto views = v["points"].get<std::vector<json_view>>();
        CHECK(views.size() == 2);
        CHECK(views[1]["x"].get<int>() == 3);
        CHECK(v["object"].get<std::map<std::string, json_view>>().at("a").get<int>() == 2);
@@ -326,7 +337,8 @@ TEST_CASE("json_view from_json")
        CHECK(d.root().get<std::unordered_map<std::string, int>>().at("a") == 3);
    }

-#if !defined(JSON_NOEXCEPTION) && !JSON_DIAGNOSTICS
+    // (the exceptions of views have neither the path nor the byte range of the value)
+#if !defined(JSON_NOEXCEPTION) && !JSON_DIAGNOSTICS && !JSON_DIAGNOSTIC_POSITIONS
    SECTION("std types: the same errors as from the materialized value")
    {
        const json_document d = json_document::parse(R"([[1, "x"], {"a": 1}, "text", [1], 5, null])");
@@ -352,7 +364,7 @@ TEST_CASE("json_view from_json")
    {
        const json_document d = json_document::parse(R"({"name": "s", "points": [{"x": 1, "y": 2}, {"x": 3, "y": 4}],
            "center": {"x": 5, "y": 6}, "named": {"a": {"x": 7, "y": 8}}})");
-        const shape s = d.root().get<shape>();
+        const auto s = d.root().get<shape>();
        CHECK(s.name == "s");
        CHECK(s.points.size() == 2);
        CHECK(s.points[1].y == 4);
@@ -370,13 +382,13 @@ TEST_CASE("json_view from_json")
    SECTION("defaults and names")
    {
        const json_document d = json_document::parse(R"({"a": 5, "Value": 3, "Text": "t"})");
-        const with_defaults w = d.root().get<with_defaults>();
+        const auto w = d.root().get<with_defaults>();
        CHECK(w.a == 5);
        CHECK(w.b == "default");
        CHECK(w.c == std::vector<int> {1, 2});
        const json_document null_document = json_document::parse("null");
        CHECK(null_document.root().get<with_defaults>().a == 1);
-        const with_names n = d.root().get<with_names>();
+        const auto n = d.root().get<with_names>();
        CHECK(n.value == 3);
        CHECK(n.text == "t");
    }
@@ -392,7 +404,7 @@ TEST_CASE("json_view from_json")
 #if !defined(JSON_NOEXCEPTION)
        const json j = d.root().materialize();
        CHECK(exception_of_call([&] { static_cast<void>(d.root()[2].get<strict_color>()); }) == "[json.exception.out_of_range.410] enum value out of range for strict_color: \"purple\"");
-#if !JSON_DIAGNOSTICS
+#if !JSON_DIAGNOSTICS && !JSON_DIAGNOSTIC_POSITIONS
        CHECK(exception_of_call([&] { static_cast<void>(d.root()[2].get<strict_color>()); }) == exception_of_call([&] { static_cast<void>(j[2].get<strict_color>()); }));
 #endif
 #endif
@@ -401,13 +413,13 @@ TEST_CASE("json_view from_json")
    SECTION("derived types")
    {
        const json_document d = json_document::parse(R"({"id": 7, "c": "green", "extra": 3})");
-        const derived x = d.root().get<derived>();
+        const auto x = d.root().get<derived>();
        CHECK(x.id == 7);
        CHECK(x.c == color::green);
-        const derived_with_defaults y = d.root().get<derived_with_defaults>();
+        const auto y = d.root().get<derived_with_defaults>();
        CHECK(y.id == 7);
        CHECK(y.label == "none");
-        const derived_from_legacy z = d.root().get<derived_from_legacy>();
+        const auto z = d.root().get<derived_from_legacy>();
        CHECK(z.id == 7);
        CHECK(z.extra == 3);
    }
@@ -440,10 +452,11 @@ TEST_CASE("json_view from_json")
        CHECK(o.root().get<shape>().center.y == 2);
    }

-#if !defined(JSON_NOEXCEPTION) && !JSON_DIAGNOSTICS
+#if !defined(JSON_NOEXCEPTION) && !JSON_DIAGNOSTICS && !JSON_DIAGNOSTIC_POSITIONS
    SECTION("errors are those of the same conversion of a json value")
    {
-        // (with JSON_DIAGNOSTICS, those of json name the path of the value)
+        // (with JSON_DIAGNOSTICS, those of json name the path of the value,
+        // and with JSON_DIAGNOSTIC_POSITIONS its bytes)
        const json_document d = json_document::parse(R"([{"x": 1}, {"x": "1", "y": 2}, [1, 2], {"id": "7", "c": "red"}])");
        const json j = d.root().materialize();
        for (std::size_t i = 0; i < 3; ++i)
@@ -185,8 +185,10 @@ std::uint32_t rng()

 TEST_CASE("json_view images: round trips")
 {
-    static_assert(json_view_image_test::has_save<json_document>::value && json_view_image_test::has_load<json_document>::value, "save() and load() on a little-endian target");
-    static_assert(json_view_image_test::has_save<ordered_json_editable_document>::value && json_view_image_test::has_load<ordered_json_editable_document>::value, "save() and load() on a little-endian target");
+    static_assert(json_view_image_test::has_save<json_document>::value, "save() on a little-endian target");
+    static_assert(json_view_image_test::has_load<json_document>::value, "load() on a little-endian target");
+    static_assert(json_view_image_test::has_save<ordered_json_editable_document>::value, "save() on a little-endian target");
+    static_assert(json_view_image_test::has_load<ordered_json_editable_document>::value, "load() on a little-endian target");

    SECTION("small documents")
    {
@@ -699,6 +701,64 @@ TEST_CASE("json_view images: ownership")
 #if !defined(JSON_NOEXCEPTION)
 TEST_CASE("json_view images: errors")
 {
+    SECTION("float tokens: a changed byte is accepted if the text is still a number with the digits the node records")
+    {
+        for (const char* const token :
+                {
+                    "-12.375", "0.5", "123456.0", "-0.0", "9999999999999999999.5", "0.000000000000000000000001", "1.25e10", "5E-3"
+                })
+        {
+            CAPTURE(token)
+            const std::string text = std::string("[") + token + "]";
+            const json_document d = json_document::parse(text);
+            const std::vector<std::uint8_t> image = d.save();
+            const std::size_t at = text_at(image) + 1; // the first byte of the token
+            const std::uint16_t recorded = node_at(image, 1).extra;
+            CHECK(loaded_dump(image) == json::parse(text).dump());
+            for (std::size_t pos = 0; token[pos] != '\0'; ++pos)
+            {
+                for (unsigned int byte = 0; byte < 256; ++byte)
+                {
+                    std::vector<std::uint8_t> changed = image;
+                    changed[at + pos] = static_cast<std::uint8_t>(byte);
+                    std::string t = token;
+                    t[pos] = static_cast<char>(byte);
+                    // the digits of the integer part and of the fraction of the changed token
+                    std::size_t integer = 0;
+                    std::size_t fraction = 0;
+                    std::size_t k = (t[0] == '-') ? 1 : 0;
+                    for (; k < t.size() && t[k] >= '0' && t[k] <= '9'; ++k)
+                    {
+                        ++integer;
+                    }
+                    if (k < t.size() && t[k] == '.')
+                    {
+                        for (++k; k < t.size() && t[k] >= '0' && t[k] <= '9'; ++k)
+                        {
+                            ++fraction;
+                        }
+                    }
+                    // (as a JSON text, the token may have white space around it)
+                    const bool float_token = json::accept(t) && t.find_first_of(std::string(" \t\r\n\0", 5)) == std::string::npos && (t.find('.') != std::string::npos || t.find_first_of("eE") != std::string::npos) // NOLINT(abseil-string-find-str-contains)
+                                             && ((integer | (fraction << 8U)) == recorded);
+                    CAPTURE(pos)
+                    CAPTURE(byte)
+                    std::string result;
+                    try
+                    {
+                        result = loaded_dump(changed);
+                    }
+                    catch (const json::parse_error& e)
+                    {
+                        CHECK(std::string(e.what()) == check_failed);
+                        result = "rejected";
+                    }
+                    CHECK((result != "rejected") == float_token);
+                }
+            }
+        }
+    }
+
    SECTION("invalid UTF-8 of a decoded string: the compact dump writes it, the others throw")
    {
        const json_document d = json_document::parse(R"({"k\n":"\u00e9x"})");
@@ -1,544 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++ (supporting code)
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-License-Identifier: MIT
-
-#include "doctest_compatibility.h"
-
-#include <nlohmann/json_view.hpp>
-using nlohmann::json;
-using nlohmann::ordered_json;
-using nlohmann::json_document;
-using nlohmann::ordered_json_editable_document;
-using nlohmann::json_view;
-using nlohmann::ordered_json_document;
-using nlohmann::ordered_json_view;
-
-#include "json_view_test_helpers.hpp"
-using json_view_test::generator;
-
-#include <algorithm>
-#include <array>
-#include <cmath>
-#include <cstddef>
-#include <cstdint>
-#include <cstring>
-#include <iomanip>
-#include <map>
-#include <random>
-#include <set>
-#include <sstream>
-#include <string>
-#include <vector>
-
-// These tests were split off unit-json_view_dump.cpp, whose object file got too large for the MinGW
-// linker (see json_view_test_helpers.hpp). Like that file, this one is also built
-// with C++17, as it mentions JSON_HAS_CPP_17.
-
-TEST_CASE("json_view comparison")
-{
-    SECTION("equality of the values parse() produces")
-    {
-        generator g;
-        std::vector<std::string> texts;
-        for (int i = 0; i < 600; ++i)
-        {
-            std::string text;
-            g.value(text, 0);
-            texts.push_back(text);
-            // the same value written differently: sorted keys, canonical numbers
-            texts.push_back(json::parse(text).dump(1));
-        }
-        for (std::size_t i = 0; i + 2 < texts.size(); ++i)
-        {
-            for (std::size_t k = i; k < i + 3; ++k)
-            {
-                CAPTURE(texts[i])
-                CAPTURE(texts[k])
-                const json_document a = json_document::parse(texts[i]);
-                const json_document b = json_document::parse(texts[k]);
-                const json ja = json::parse(texts[i]);
-                const json jb = json::parse(texts[k]);
-                CHECK((a.root() == b.root()) == (ja == jb));
-                CHECK((a.root() != b.root()) == (ja != jb));
-                CHECK((a.root() == jb) == (ja == jb));
-                CHECK((jb == a.root()) == (ja == jb));
-                CHECK((a.root() != jb) == (ja != jb));
-                CHECK((jb != a.root()) == (ja != jb));
-
-                // ordered_json compares members in order
-                const ordered_json_document oa = ordered_json_document::parse(texts[i]);
-                const ordered_json_document ob = ordered_json_document::parse(texts[k]);
-                const ordered_json oja = ordered_json::parse(texts[i]);
-                const ordered_json ojb = ordered_json::parse(texts[k]);
-                CHECK((oa.root() == ob.root()) == (oja == ojb));
-                CHECK((oa.root() == ojb) == (oja == ojb));
-            }
-        }
-    }
-
-    SECTION("numbers, duplicate keys, member order")
-    {
-        const auto same = [](const char* x, const char* y)
-        {
-            const json_document dx = json_document::parse(x);
-            const json_document dy = json_document::parse(y);
-            return dx.root() == dy.root();
-        };
-        CHECK(same("1", "1.0"));
-        CHECK(same("[1, -1, 2.5]", "[1.0, -1.0, 25e-1]"));
-        CHECK(!same("1", "1.5"));
-        CHECK(same("18446744073709551615", "18446744073709551615"));
-        CHECK(same(R"({"a": 1, "a": 2})", R"({"a": 2})"));
-        CHECK(!same(R"({"a": 1, "a": 2})", R"({"a": 1})"));
-        CHECK(same(R"({"a": 1, "b": 2})", R"({"b": 2, "a": 1})"));
-        CHECK(!same(R"({"a": 1})", R"({"a": 1, "b": 2})"));
-        CHECK(!same("[1, 2]", "[2, 1]"));
-        CHECK(!same("\"a\"", "\"b\""));
-        CHECK(same("\"\\u00e9\"", "\"\xc3\xa9\""));
-        CHECK(!same("null", "false"));
-        CHECK(!same("[]", "{}"));
-        const ordered_json_document dup = ordered_json_document::parse(R"({"a": 1, "b": 2, "a": 3})");
-        const ordered_json_document last = ordered_json_document::parse(R"({"a": 3, "b": 2})");
-        CHECK(dup.root() == last.root());
-        // (== compares as parse() resolves duplicates, a lookup finds the first)
-        CHECK(dup.root()["a"].materialize() == 1);
-        CHECK(dup.root()["a"] != last.root()["a"]);
-        const ordered_json_document ab = ordered_json_document::parse(R"({"a": 1, "b": 2})");
-        const ordered_json_document ba = ordered_json_document::parse(R"({"b": 2, "a": 1})");
-        CHECK(ab.root() != ba.root());
-
-        // discarded values compare as basic_json's do
-        const json discarded(json::value_t::discarded);
-        CHECK((json_view() == json_view()) == (discarded == discarded)); // NOLINT(readability-container-size-empty): operator== is tested
-        CHECK((json_view() == discarded) == (discarded == discarded)); // NOLINT(readability-container-size-empty)
-        const json_document null_document = json_document::parse("null");
-        CHECK(!(json_view() == null_document.root())); // NOLINT(readability-container-size-empty)
-        CHECK(!(null_document.root() == discarded));
-    }
-
-    SECTION("deep nesting")
-    {
-        const std::string deep = std::string(100000, '[') + std::string(100000, ']');
-        const json_document a = json_document::parse(deep);
-        const json_document b = json_document::parse(deep);
-        CHECK(a.root() == b.root());
-        CHECK(a.root() == json::parse(deep));
-        const std::string other = std::string(100000, '[') + "1" + std::string(100000, ']');
-        const json_document c = json_document::parse(other);
-        CHECK(a.root() != c.root());
-    }
-}
-
-TEST_CASE("json_view large objects")
-{
-    // objects with 128 members or more are looked up with a hash index
-    for (const std::size_t members :
-            {
-                127u, 128u, 129u, 10000u
-            })
-    {
-        CAPTURE(members)
-        std::string text = "{";
-        for (std::size_t i = 0; i < members; ++i)
-        {
-            text += (i != 0 ? ",\"" : "\"") + std::string(i % 23, 'k') + std::to_string(i) + (i % 7 == 0 ? "\\n" : "") + "\":" + std::to_string(i);
-        }
-        text += R"(,"":"empty key","k1":"a duplicate of an earlier key"})";
-        const json_document d = json_document::parse(text);
-        const json_view v = d.root();
-        const json j = json::parse(text);
-        for (std::size_t i = 0; i < members; ++i)
-        {
-            const std::string key = std::string(i % 23, 'k') + std::to_string(i) + (i % 7 == 0 ? "\n" : "");
-            CHECK(v[key].get<std::size_t>() == i);
-            CHECK(v.contains(key));
-            CHECK(v.find(key).key() == key);
-            CHECK(v.at(key).get<std::size_t>() == i);
-            CHECK(!v.contains(key + "x"));
-        }
-        CHECK(v[""].get_string() == "empty key");
-        CHECK(v["k1"].get<int>() == 1); // the first of duplicate keys, as for small objects
-        CHECK(!v.contains("missing"));
-        CHECK_THROWS_WITH_AS(v.at("missing"), "[json.exception.out_of_range.403] key 'missing' not found", json::out_of_range&);
-        CHECK(v == j);
-        CHECK(v.materialize() == j);
-    }
-
-    SECTION("duplicate keys: the first member wins, with and without a table")
-    {
-        // an object of `total` members: the keys "k0".."k<n-1>" in order, then
-        // three keys repeated twice more (one copy in the middle, one at the
-        // end), and two keys repeated once; the value of a member is its
-        // position, so that the first member of a key can be told apart
-        struct member
-        {
-            std::string key;
-            std::size_t position;
-        };
-        const auto make_members = [](std::size_t total)
-        {
-            std::vector<std::string> keys;
-            for (std::size_t i = 0; i + 8 < total; ++i)
-            {
-                keys.push_back("k" + std::to_string(i));
-            }
-            const std::size_t n = keys.size();
-            const std::array<std::size_t, 3> triple = {{3, 17, n - 1}};
-            const std::array<std::size_t, 2> twice = {{5, n / 2}};
-            std::vector<std::string> ordered = keys;
-            for (const std::size_t i : triple)
-            {
-                ordered.insert(ordered.begin() + static_cast<std::ptrdiff_t>(ordered.size() / 2), keys[i]);
-            }
-            for (const std::size_t i : twice)
-            {
-                ordered.insert(ordered.begin() + static_cast<std::ptrdiff_t>(ordered.size() / 3), keys[i]);
-            }
-            for (const std::size_t i : triple)
-            {
-                ordered.push_back(keys[i]);
-            }
-            std::vector<member> result;
-            result.reserve(ordered.size());
-            for (std::size_t i = 0; i < ordered.size(); ++i)
-            {
-                result.push_back({ordered[i], i});
-            }
-            return result;
-        };
-
-        // 100 and 127 members: no table; 128 members and more: a table
-        for (const std::size_t total :
-                {
-                    100u, 127u, 128u, 200u, 5000u
-                })
-        {
-            CAPTURE(total)
-            const std::vector<member> members = make_members(total);
-            REQUIRE(members.size() >= total);
-            REQUIRE(members.size() >= 100);
-            std::string text = "{";
-            std::map<std::string, std::size_t> first;
-            std::map<std::string, std::size_t> last;
-            std::map<std::string, std::size_t> occurrences;
-            for (const member& m : members)
-            {
-                text += (text.size() > 1 ? ",\"" : "\"") + m.key + "\":" + std::to_string(m.position);
-                first.insert({m.key, m.position});
-                last[m.key] = m.position;
-                ++occurrences[m.key];
-            }
-            text += '}';
-            REQUIRE(first.size() < members.size());
-
-            const json_document d = json_document::parse(text);
-            const json_view v = d.root();
-            const json j = json::parse(text);
-            CHECK(v.size() == members.size()); // every occurrence is visited
-            const json m = v.materialize();
-            for (const auto& entry : first)
-            {
-                CAPTURE(entry.first)
-                const std::size_t expected = entry.second;
-                CHECK(v[entry.first].get<std::size_t>() == expected);
-                CHECK(v.at(entry.first).get<std::size_t>() == expected);
-                CHECK(v.find(entry.first).value().get<std::size_t>() == expected);
-                CHECK(v.value(entry.first, std::size_t{0}) == expected);
-                CHECK(v.contains(entry.first));
-                CHECK(v.count(entry.first) == occurrences[entry.first]);
-                const std::string pointer = "/" + entry.first;
-                CHECK(v[json::json_pointer(pointer)].get<std::size_t>() == expected);
-                CHECK(v.at(json::json_pointer(pointer)).get<std::size_t>() == expected);
-                CHECK(v.value(json::json_pointer(pointer), std::size_t{0}) == expected);
-                CHECK(v.contains(json::json_pointer(pointer)));
-                // materialize() and parse() keep the last value instead
-                CHECK(j[entry.first].get<std::size_t>() == last.at(entry.first));
-                CHECK(m[entry.first].get<std::size_t>() == last.at(entry.first));
-            }
-            CHECK(!v.contains("k"));
-            CHECK(v["missing"].is_discarded());
-            CHECK(v.materialize() == j);
-            CHECK(v == j);
-        }
-    }
-
-    SECTION("colliding keys")
-    {
-        // the hash is not seeded, so keys that all land in one place must not
-        // make the table build quadratic: such an object gets no table and is
-        // searched linearly
-        constexpr std::size_t members = 300;
-        constexpr std::size_t table_size = 1024; // the table size for 300 members: the next power of two >= 600
-        std::vector<std::string> colliding;
-        std::vector<std::string> spread;
-        for (std::uint64_t counter = 0; colliding.size() < members || spread.size() < members; ++counter)
-        {
-            std::string key(8, 'a');
-            std::uint64_t x = counter;
-            for (std::size_t i = 0; i < 8; ++i, x /= 26)
-            {
-                key[i] = static_cast<char>('a' + (x % 26));
-            }
-            const bool lands_in_slot_zero = (nlohmann::detail::view::key_hash(key.data(), key.size()) & (table_size - 1)) == 0;
-            if (lands_in_slot_zero && colliding.size() < members)
-            {
-                colliding.push_back(key);
-            }
-            else if (!lands_in_slot_zero && spread.size() < members)
-            {
-                spread.push_back(key);
-            }
-        }
-
-        const auto make_text = [](const std::vector<std::string>& keys)
-        {
-            std::string text = "{";
-            for (std::size_t i = 0; i < keys.size(); ++i)
-            {
-                text += (i != 0 ? ",\"" : "\"") + keys[i] + "\":" + std::to_string(i % 10);
-            }
-            return text + "}";
-        };
-        const std::string colliding_text = make_text(colliding);
-        const std::string spread_text = make_text(spread);
-
-        json_document with_collisions = json_document::parse(colliding_text);
-        json_document without_collisions = json_document::parse(spread_text);
-        for (const auto* pair :
-                {
-                    &colliding, &spread
-                })
-        {
-            const json_view v = (pair == &colliding ? with_collisions : without_collisions).root();
-            for (std::size_t i = 0; i < members; ++i)
-            {
-                CAPTURE(i)
-                CHECK(v[(*pair)[i]].get<std::size_t>() == i % 10);
-                CHECK(v.at((*pair)[i]).get<std::size_t>() == i % 10);
-                CHECK(v.find((*pair)[i]).key() == (*pair)[i]);
-                CHECK(!v.contains((*pair)[i] + "x"));
-            }
-            CHECK(!v.contains("missing"));
-        }
-        CHECK(with_collisions.root() == json::parse(colliding_text));
-
-        // only the object with the spread keys got a table (both texts have the
-        // same length, so the tables are the only difference)
-        with_collisions.shrink_to_fit();
-        without_collisions.shrink_to_fit();
-        CHECK(without_collisions.memory_usage() >= with_collisions.memory_usage() + (table_size * sizeof(std::uint32_t)));
-    }
-
-    SECTION("keys that differ in their last bytes are spread over the table")
-    {
-        // The hash must spread the usual families of keys (numbered names, hex
-        // strings, dates, short names): a key farther than index_max_displacement
-        // from its home slot would leave the object without a table. The keys
-        // are placed with linear probing, as the table does.
-        const auto max_displacement = [](const std::vector<std::string>& keys)
-        {
-            std::size_t slots = 16;
-            while (slots < 2 * keys.size())
-            {
-                slots *= 2;
-            }
-            std::vector<bool> used(slots, false);
-            std::size_t farthest = 0;
-            for (const std::string& key : keys)
-            {
-                std::size_t i = nlohmann::detail::conditional_static_cast<std::size_t>(nlohmann::detail::view::key_hash(key.data(), key.size())) & (slots - 1);
-                std::size_t distance = 0;
-                while (used[i])
-                {
-                    i = (i + 1) & (slots - 1);
-                    ++distance;
-                }
-                used[i] = true;
-                farthest = (std::max)(farthest, distance);
-            }
-            return farthest;
-        };
-        // the keys of a printf-like pattern with one %d, %0Nd or %0Nx, formatted with a stream
-        // (a format string that is not a literal is a Flawfinder error)
-        const auto numbered = [](const char* format, int count, int step)
-        {
-            const std::string pattern(format);
-            const std::size_t percent = pattern.find('%');
-            std::size_t conversion = percent + 1;
-            std::size_t width = 0;
-            while (pattern[conversion] >= '0' && pattern[conversion] <= '9')
-            {
-                width = (width * 10) + static_cast<std::size_t>(pattern[conversion] - '0');
-                ++conversion;
-            }
-            const bool hex = pattern[conversion] == 'x';
-            std::vector<std::string> keys;
-            for (int i = 0; i < count; ++i)
-            {
-                std::ostringstream key;
-                key << pattern.substr(0, percent) << std::setfill('0') << std::setw(static_cast<int>(width))
-                    << (hex ? std::hex : std::dec) << (i * step) << pattern.substr(conversion + 1);
-                keys.push_back(key.str());
-            }
-            return keys;
-        };
-        for (const char* format :
-                {"key%d", "%d", "item_%04d", "a%05d", "%03dxyz", "id%d", "user_%d", "%d_suffix", "0x%04x", "A%07d", "12345678%d", "1234567%d", "123456789%d",
-                 "configuration_parameter_value_%04d_extra", "2026-01-%02dT00:00:00Z"
-                })
-        {
-            CAPTURE(format)
-            CHECK(max_displacement(numbered(format, std::string(format).find("%02d") != std::string::npos ? 60 : 1000, 1)) < nlohmann::detail::view::index_max_displacement); // NOLINT(abseil-string-find-str-contains)
-            CHECK(max_displacement(numbered(format, 600, 7)) < nlohmann::detail::view::index_max_displacement);
-        }
-        std::mt19937_64 rng(7); // NOLINT(cert-msc32-c,cert-msc51-cpp,bugprone-random-generator-seed)
-        for (const std::size_t length :
-                {
-                    std::size_t{1}, std::size_t{2}, std::size_t{3}, std::size_t{5}, std::size_t{7}, std::size_t{8}, std::size_t{9}, std::size_t{12}, std::size_t{16}, std::size_t{17}, std::size_t{33}
-                })
-        {
-            CAPTURE(length)
-            std::set<std::string> distinct;
-            // (there are 26 and 676 keys of one and two letters)
-            std::size_t wanted = 700;
-            if (length == 1)
-            {
-                wanted = 26;
-            }
-            else if (length == 2)
-            {
-                wanted = 500;
-            }
-            while (distinct.size() < wanted)
-            {
-                std::string key(length, 'a');
-                for (char& c : key)
-                {
-                    c = static_cast<char>('a' + (rng() % 26));
-                }
-                distinct.insert(key);
-            }
-            CHECK(max_displacement(std::vector<std::string>(distinct.begin(), distinct.end())) < nlohmann::detail::view::index_max_displacement);
-        }
-    }
-
-    SECTION("keys of every length that differ in one byte")
-    {
-        // In a large object, a key is found by comparing its bytes with those of the member the
-        // table points to: up to 16 bytes as two overlapping words, longer ones with memcmp.
-        // Keys of every length from 0 to 40, and keys that differ from them in one byte.
-        std::mt19937_64 rng(2026); // NOLINT(cert-msc32-c,cert-msc51-cpp,bugprone-random-generator-seed)
-        std::vector<std::string> keys;
-        std::set<std::string> distinct;
-        for (std::size_t length = 0; length <= 40; ++length)
-        {
-            for (int copy = 0; copy < 5; ++copy)
-            {
-                std::string key(length, 'a');
-                for (char& c : key)
-                {
-                    c = static_cast<char>('a' + (rng() % 26));
-                }
-                if (distinct.insert(key).second)
-                {
-                    keys.push_back(key);
-                }
-            }
-        }
-        std::string text = "{";
-        for (std::size_t i = 0; i < keys.size(); ++i)
-        {
-            text += (i != 0 ? ",\"" : "\"") + keys[i] + "\":" + std::to_string(i);
-        }
-        text += "}";
-        REQUIRE(keys.size() >= 128); // (a table is built for 128 members)
-        const json_document d = json_document::parse(text);
-        const json_view v = d.root();
-        for (std::size_t i = 0; i < keys.size(); ++i)
-        {
-            CAPTURE(keys[i])
-            CHECK(v[keys[i]].get<std::size_t>() == i);
-            CHECK(v.at(keys[i]).get<std::size_t>() == i);
-            CHECK(v.contains(keys[i]));
-            for (std::size_t at = 0; at < keys[i].size(); ++at)
-            {
-                std::string other = keys[i];
-                other[at] = other[at] == 'z' ? 'y' : 'z';
-                CAPTURE(other)
-                CHECK(v.contains(other) == (distinct.count(other) != 0));
-            }
-            CHECK(v.contains(keys[i] + "a") == (distinct.count(keys[i] + "a") != 0));
-            if (!keys[i].empty())
-            {
-                CHECK(v.contains(keys[i].substr(1)) == (distinct.count(keys[i].substr(1)) != 0));
-            }
-        }
-    }
-
-    SECTION("shrink_to_fit releases the tables' spare capacity")
-    {
-        const auto make_text = [](int objects, int members)
-        {
-            std::string text = "[";
-            for (int object = 0; object < objects; ++object)
-            {
-                text += object != 0 ? ",{" : "{";
-                for (int i = 0, n = members + object; i < n; ++i)
-                {
-                    text += (i != 0 ? ",\"" : "\"") + std::to_string(i) + "\":" + std::to_string(i);
-                }
-                text += '}';
-            }
-            return text + "]";
-        };
-        const std::string small_text = make_text(5, 150);
-        const std::string big_text = make_text(40, 400);
-
-        // reading a big text, and then a small one, leaves the spare capacity
-        // of the big one: shrink_to_fit() brings the document to the size of
-        // one parsed from the small text alone
-        json_document d = json_document::parse(big_text);
-        const std::size_t big = d.memory_usage();
-        d.read(small_text);
-        CHECK(d.memory_usage() >= big);
-        d.shrink_to_fit();
-        json_document fresh = json_document::parse(small_text);
-        fresh.shrink_to_fit();
-        CHECK(d.memory_usage() == fresh.memory_usage());
-        CHECK(d.memory_usage() < big / 2);
-        CHECK(d.root() == json::parse(small_text));
-        for (int object = 0; object < 5; ++object)
-        {
-            const json_view v = d.root()[static_cast<std::size_t>(object)];
-            for (int i = 0, n = 150 + object; i < n; ++i)
-            {
-                CHECK(v[std::to_string(i)].get<int>() == i);
-            }
-        }
-    }
-
-    SECTION("nested, reused, and in arrays")
-    {
-        std::string inner = "{";
-        for (int i = 0; i < 300; ++i)
-        {
-            inner += (i != 0 ? ",\"m" : "\"m") + std::to_string(i) + "\":" + std::to_string(i);
-        }
-        inner += '}';
-        const std::string text = "[" + inner + ",{\"x\":" + inner + "}," + inner + "]";
-        json_document d = json_document::parse(text);
-        CHECK(d.root()[0]["m299"].get<int>() == 299);
-        CHECK(d.root()[1]["x"]["m150"].get<int>() == 150);
-        CHECK(d.root()[2]["m0"].get<int>() == 0);
-        const std::size_t with_index = d.memory_usage();
-        d.read(std::string("{\"small\": 1}"));
-        CHECK(d.root()["small"].get<int>() == 1);
-        d.read(text);
-        CHECK(d.root()[2]["m7"].get<int>() == 7);
-        CHECK(d.memory_usage() >= with_index / 2);
-    }
-}
@@ -0,0 +1,347 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  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
+
+// source positions of materialize() (JSON_DIAGNOSTIC_POSITIONS, #5864)
+
+#include "doctest_compatibility.h"
+
+#ifndef JSON_DIAGNOSTICS
+    #define JSON_DIAGNOSTICS 1
+#endif
+#define JSON_DIAGNOSTIC_POSITIONS 1
+#include <nlohmann/json_view.hpp>
+using nlohmann::json;
+using nlohmann::ordered_json;
+using nlohmann::json_document;
+using nlohmann::json_editable_document;
+
+#include <cstdint>
+#include <cstring>
+#include <fstream>
+#include <sstream>
+#include <string>
+#include <vector>
+
+#include "json_view_test_helpers.hpp"
+#include <test_data.hpp>
+
+namespace
+{
+// not constexpr: VS 2015 does not accept std::string::npos in a constant expression (C2131)
+const std::size_t npos = std::string::npos;
+
+// whether every value of a has the source positions of the value of b at the
+// same place (a and b are equal; shallow test documents only)
+template<typename BasicJsonType>
+bool same_positions(const BasicJsonType& a, const BasicJsonType& b)
+{
+    if (a.start_pos() != b.start_pos() || a.end_pos() != b.end_pos() || a.type() != b.type() || a.size() != b.size())
+    {
+        return false;
+    }
+    if (a.is_object())
+    {
+        for (auto it = a.begin(); it != a.end(); ++it)
+        {
+            if (!same_positions(it.value(), b.at(it.key())))
+            {
+                return false;
+            }
+        }
+    }
+    else if (a.is_array())
+    {
+        for (std::size_t i = 0; i < a.size(); ++i)
+        {
+            if (!same_positions(a[i], b[i]))
+            {
+                return false;
+            }
+        }
+    }
+    return true;
+}
+
+// the materialized root of text has the positions of parse()
+template<typename BasicJsonType>
+bool positions_as_parse(const std::string& text, bool comments = false, bool trailing_commas = false)
+{
+    const auto j = BasicJsonType::parse(text, nullptr, true, comments, trailing_commas);
+    const auto d = nlohmann::basic_json_document<BasicJsonType>::parse(text, true, comments, trailing_commas);
+    const auto e = nlohmann::basic_json_document<BasicJsonType, nlohmann::view_mode::editable>::parse(text, true, comments, trailing_commas);
+    return same_positions(d.root().materialize(), j) && same_positions(e.root().materialize(), j);
+}
+
+std::string range(const json& j)
+{
+    return j.start_pos() == npos && j.end_pos() == npos ? "none" : std::to_string(j.start_pos()) + "-" + std::to_string(j.end_pos());
+}
+} // namespace
+
+TEST_CASE("json_view materialize() source positions")
+{
+    SECTION("as parse()")
+    {
+        const std::vector<std::string> texts =
+        {
+            "null", "true", "false", "0", "-12", "3.25e-2", "18446744073709551615", "-9223372036854775809", R"("a")",
+            R"("\n")", R"("\u00e9")", R"("\ud83d\ude00")", "\"\xf0\x9f\x98\x80\"", R"("a\"b\\")", R"("x\\")",
+            "  [ ]  ", "{}", "[[[]]]", R"({"a":{"b":[1,{"c":[]}]}})",
+            R"({"\u0041": "v\n", "k": "\"", "\t":[ "\/" ]})",
+            R"([1, 2.5, true, false, null, "s", "\u0000", -0])",
+            "\n\t[\r\n  1 ,\n  {\n    \"a\" : [ ]\n  }\n]\n",
+            "\xef\xbb\xbf[1, {\"a\": \"b\"}]", "\xef\xbb\xbf\"\\n\"",
+        };
+        for (const auto& text : texts)
+        {
+            CAPTURE(text)
+            CHECK(positions_as_parse<json>(text));
+            CHECK(positions_as_parse<ordered_json>(text));
+        }
+    }
+
+    SECTION("comments and trailing commas")
+    {
+        const std::vector<std::string> texts =
+        {
+            "[1 /* ] */]", "[1 // ]\n]", "{\"a\": 1 /* } */ , }", "[1, 2, ]", "[[1,],[2 , /**/ ] , ]",
+            "{\"a\": [] // }\n, \"b\": {} /* } ] */ }", "[ /* empty */ ]", "{ // }\n}", "/* a */ [1] // b",
+            R"(["\n" /* " */ , ])",
+        };
+        for (const auto& text : texts)
+        {
+            CAPTURE(text)
+            CHECK(positions_as_parse<json>(text, true, true));
+        }
+    }
+
+    SECTION("generated documents")
+    {
+        json_view_test::generator gen;
+        for (int i = 0; i < 300; ++i)
+        {
+            std::string text;
+            gen.value(text, 0);
+            CAPTURE(text)
+            CHECK(positions_as_parse<json>(text));
+            CHECK(positions_as_parse<ordered_json>(text));
+        }
+    }
+
+    SECTION("test data")
+    {
+        for (const char* name :
+                {
+                    "/json_testsuite/sample.json", "/nativejson-benchmark/canada.json", "/nativejson-benchmark/citm_catalog.json",
+                    "/nativejson-benchmark/twitter.json", "/json_tests/pass1.json"
+                })
+        {
+            CAPTURE(name)
+            const std::ifstream f(std::string(TEST_DATA_DIRECTORY) + name, std::ios::binary);
+            std::stringstream ss;
+            ss << f.rdbuf();
+            CHECK(positions_as_parse<json>(ss.str()));
+        }
+    }
+
+    SECTION("subtrees")
+    {
+        const std::string text = R"({"a": [1, "\n", {"b": null}], "s": "x\ty", "n": -1.5})";
+        const json j = json::parse(text);
+        const json_document d = json_document::parse(text);
+        CHECK(same_positions(d.root()["a"].materialize(), j["a"]));
+        CHECK(same_positions(d.root()["a"][2].materialize(), j["a"][2]));
+        CHECK(same_positions(d.root()["a"][1].materialize(), j["a"][1]));
+        CHECK(same_positions(d.root()["s"].materialize(), j["s"]));
+        CHECK(same_positions(d.root()["n"].materialize(), j["n"]));
+        CHECK(range(d.root()["a"][1].materialize()) == "10-14");
+        CHECK(range(d.root()["s"].materialize()) == "35-41");
+    }
+
+#if !defined(JSON_NOEXCEPTION)
+    SECTION("exception messages")
+    {
+        const std::string text = "{\n  \"address\": {\"street\": \"Fake\\tStreet\", \"housenumber\": \"1\"},\n  \"list\": [1, [true]]\n}";
+        const json j = json::parse(text);
+        const json_document d = json_document::parse(text);
+        const json m = d.root().materialize();
+        const std::string expected = json_view_test::exception_of_call([&]
+        {
+            static_cast<void>(j.at("address").at("housenumber").get<int>());
+        });
+        CHECK(expected.find("(bytes ") != std::string::npos);
+        CHECK(json_view_test::exception_of_call([&]
+        {
+            static_cast<void>(m.at("address").at("housenumber").get<int>());
+        }) == expected);
+        CHECK(json_view_test::exception_of_call([&]
+        {
+            static_cast<void>(m.at("address").at("street").get<int>());
+        }) == json_view_test::exception_of_call([&]
+        {
+            static_cast<void>(j.at("address").at("street").get<int>());
+        }));
+        CHECK(json_view_test::exception_of_call([&]
+        {
+            static_cast<void>(m.at("list").at(1).get<int>());
+        }) == json_view_test::exception_of_call([&]
+        {
+            static_cast<void>(j.at("list").at(1).get<int>());
+        }));
+    }
+#endif
+
+    SECTION("edited documents")
+    {
+        const std::string text = R"({"a": [1, 2], "b": {"c": "\n", "d": true}, "e": [3, [4]], "f": "x"})";
+        const json j = json::parse(text);
+
+        SECTION("new scalars have none")
+        {
+            json_editable_document d = json_editable_document::parse(text);
+            d.set(d.root()["f"], 5);
+            d.set(d.root()["b"]["d"], "s");
+            const json m = d.root().materialize();
+            CHECK(range(m["f"]) == "none");
+            CHECK(range(m["b"]["d"]) == "none");
+            // the object whose last member is new has none; the others keep theirs
+            CHECK(range(m) == "none");
+            CHECK(range(m["b"]) == "none");
+            CHECK(same_positions(m["a"], j["a"]));
+            CHECK(same_positions(m["e"], j["e"]));
+            CHECK(same_positions(m["b"]["c"], j["b"]["c"]));
+        }
+
+        SECTION("containers whose elements change have none")
+        {
+            json_editable_document d = json_editable_document::parse(text);
+            d.push_back(d.root()["a"], 7);
+            d.erase(d.root()["e"], 0);
+            const json m = d.root().materialize();
+            CHECK(range(m["a"]) == "none");
+            CHECK(range(m["a"][2]) == "none");
+            CHECK(range(m["e"]) == "none");
+            // the elements kept keep theirs
+            CHECK(range(m["a"][0]) == range(j["a"][0]));
+            CHECK(range(m["a"][1]) == range(j["a"][1]));
+            CHECK(same_positions(m["e"][0], j["e"][1]));
+            CHECK(same_positions(m["b"], j["b"]));
+            // the root's elements did not change
+            CHECK(range(m) == range(j));
+        }
+
+        SECTION("new containers have none")
+        {
+            json_editable_document d = json_editable_document::parse(text);
+            d.set(d.root()["b"], json::parse(R"({"x": [1]})"));
+            const json m = d.root().materialize();
+            CHECK(range(m["b"]) == "none");
+            CHECK(range(m["b"]["x"]) == "none");
+            CHECK(range(m["b"]["x"][0]) == "none");
+            CHECK(range(m) == range(j));
+        }
+
+        SECTION("copies of scalars of the document keep theirs")
+        {
+            // (a copy of an array or object is a new one; its scalars are the
+            // parsed ones)
+            json_editable_document d = json_editable_document::parse(text);
+            d.set(d.root()["f"], d.root()["e"]);
+            d.set(d.root()["a"], d.root()["b"]["c"]);
+            const json m = d.root().materialize();
+            CHECK(range(m["a"]) == range(j["b"]["c"]));
+            CHECK(range(m["f"]) == "none");
+            CHECK(range(m["f"][1]) == "none");
+            CHECK(range(m["f"][0]) == range(j["e"][0]));
+            CHECK(range(m["f"][1][0]) == range(j["e"][1][0]));
+        }
+    }
+
+#if !(defined(__BYTE_ORDER__) && defined(__ORDER_BIG_ENDIAN__) && __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__)
+    SECTION("images")
+    {
+        const std::string text = R"({"a\n": ["\u00e9", 1.5, {"b": [true, null]}], "c": "d"})";
+        const json j = json::parse(text);
+
+        SECTION("round trip")
+        {
+            const json_document d = json_document::load(json_document::parse(text).save());
+            CHECK(same_positions(d.root().materialize(), j));
+        }
+
+        SECTION("edited")
+        {
+            json_editable_document e = json_editable_document::parse(text);
+            e.set(e.root()["c"], 1);
+            e.push_back(e.root()[std::string("a") + '\n'], false);
+            e.set(e.root()[std::string("a") + '\n'][2]["b"][0], "\"");
+            const json_document d = json_document::load(e.save());
+            const json m = d.root().materialize();
+            CHECK(range(m["c"]) == "none");
+            CHECK(range(m) == "none");
+            const json& a = m[std::string("a") + '\n'];
+            const json& ja = j[std::string("a") + '\n'];
+            CHECK(range(a) == "none");
+            CHECK(range(a[3]) == "none");
+            CHECK(range(a[0]) == range(ja[0]));
+            CHECK(range(a[1]) == range(ja[1]));
+            CHECK(range(a[2]["b"][0]) == "none");
+            CHECK(range(a[2]["b"][1]) == range(ja[2]["b"][1]));
+            // the last element of b is still the parsed one
+            CHECK(range(a[2]["b"]) == range(ja[2]["b"]));
+            CHECK(range(a[2]) == range(ja[2]));
+        }
+
+        SECTION("without positions")
+        {
+            // an image saved without JSON_DIAGNOSTIC_POSITIONS: next is 0 for
+            // the strings with escapes
+            std::vector<std::uint8_t> image = json_document::parse(text).save();
+            std::uint64_t count = 0;
+            std::memcpy(&count, image.data() + 8, sizeof(count));
+            for (std::size_t i = 0; i < count; ++i)
+            {
+                nlohmann::detail::view::node n{};
+                std::memcpy(&n, image.data() + 64 + (i * sizeof(n)), sizeof(n));
+                if (n.kind == nlohmann::detail::view::node_kind::string)
+                {
+                    n.next = 0;
+                }
+                std::memcpy(image.data() + 64 + (i * sizeof(n)), &n, sizeof(n));
+            }
+            const json_document d = json_document::load(image);
+            const json m = d.root().materialize();
+            CHECK(range(m[std::string("a") + '\n'][0]) == "none");
+            CHECK(range(m["c"]) == range(j["c"]));
+            CHECK(same_positions(m[std::string("a") + '\n'][2], j[std::string("a") + '\n'][2]));
+        }
+
+#if !defined(JSON_NOEXCEPTION)
+        SECTION("a decoded string's position must be within the text")
+        {
+            std::vector<std::uint8_t> image = json_document::parse(R"(["\n"])").save();
+            nlohmann::detail::view::node n{};
+            std::memcpy(&n, image.data() + 64 + sizeof(n), sizeof(n));
+            REQUIRE(n.next == 2);
+            n.next = 7;
+            std::memcpy(image.data() + 64 + sizeof(n), &n, sizeof(n));
+            const auto load_image = [&image]
+            {
+                // GCC ignores a cast to void for [[nodiscard]]-like results, so keep the document
+                const json_document d = json_document::load(image);
+                static_cast<void>(d);
+            };
+            CHECK_THROWS_AS(load_image(), json::parse_error&);
+            // without the check, the position is out of bounds and ignored
+            const json_document d = json_document::load(image, json_document::image_check::none);
+            CHECK(range(d.root()[0].materialize()) == "none");
+        }
+#endif
+    }
+#endif
+}
@@ -0,0 +1,34 @@
+# check_path_filters
+
+The compiler workflows [`ubuntu.yml`](../../.github/workflows/ubuntu.yml),
+[`macos.yml`](../../.github/workflows/macos.yml), and [`windows.yml`](../../.github/workflows/windows.yml) skip pull
+requests that change only files no compiler job reads: the documentation, Markdown files, GitHub metadata, other
+workflows, and the license files. Pushes to `develop`, `master`, and `release/*` always run them. The documentation,
+license, and path-filter checks run in [`repository_checks.yml`](../../.github/workflows/repository_checks.yml), which
+has no path filter.
+
+The filter starts with `'**'` and excludes these files explicitly, so a new file runs the compiler workflows unless it
+is excluded on purpose. [`check_path_filters.py`](check_path_filters.py) holds the filter (`PATHS`) and checks that
+
+- each of the three workflows has exactly this filter, with its own workflow file included,
+- the CI targets that read excluded files (`UNFILTERED_TARGETS`) do not run in these workflows, and
+- no file the filter keeps (sources, tests, build files, tools, workflows) mentions an excluded file or directory
+  outside a comment line, unless the mention is listed in `KNOWN_REFERENCES` with a reason.
+
+When the check reports a mention, decide whether a compiler job reads that file:
+
+- If it does, include the file in `PATHS` after the exclusions (as `package_managers.md` and the Swift example are) and
+  copy the new filter into the three workflows.
+- If it does not, add the mention to `KNOWN_REFERENCES` with the reason.
+
+Run the check with
+
+```shell
+python3 tools/check_path_filters/check_path_filters.py
+```
+
+To see which workflows a pull request would run, pass the changed files:
+
+```shell
+python3 tools/check_path_filters/check_path_filters.py --changed $(git diff --name-only origin/develop)
+```
@@ -0,0 +1,269 @@
+#!/usr/bin/env python3
+"""Check the path filters of the compiler workflows.
+
+ubuntu.yml, macos.yml and windows.yml skip pull requests that change only files
+no compiler job reads (documentation, Markdown files, GitHub metadata, license
+files). The filter starts with '**' and excludes these files explicitly, so a
+new file runs the workflows unless it is excluded on purpose.
+
+The script checks that
+
+- each of the three workflows has exactly the filter defined in PATHS below,
+  with its own workflow file included, and
+- no tracked file that the filter keeps (sources, tests, build files, tools,
+  workflows) mentions a file the filter excludes, unless the mention is listed
+  in KNOWN_REFERENCES with the reason why it does not matter.
+
+A mention found this way must either be added to PATHS as an included path
+(the file is read by a compiler job) or to KNOWN_REFERENCES (it is not).
+
+With --changed FILE..., the script prints instead which workflows a pull
+request changing these files would run.
+"""
+
+import argparse
+import os
+import re
+import subprocess  # nosec B404
+import sys
+
+REPO_ROOT = os.path.normpath(os.path.join(sys.path[0], '..', '..'))
+SELF = 'tools/check_path_filters/check_path_filters.py'
+
+WORKFLOWS = ['.github/workflows/ubuntu.yml', '.github/workflows/macos.yml', '.github/workflows/windows.yml']
+
+# The pull_request paths filter of the workflows above; '{workflow}' is replaced
+# with the workflow's own file. GitHub applies the patterns in order: a file
+# matching a later pattern is included ('pattern') or excluded ('!pattern').
+PATHS = [
+    '**',
+    '!docs/**',
+    '!**.md',
+    '!.github/*',
+    '!.github/ISSUE_TEMPLATE/**',
+    '!.github/external_ci/**',
+    '!.github/workflows/**',
+    '!.reuse/**',
+    '!LICENSES/**',
+    '!CITATION.cff',
+    '!REUSE.toml',
+    # read by tools/check_build_options in the ci_meson_install job (ubuntu.yml)
+    'docs/mkdocs/docs/integration/package_managers.md',
+    # built by the swiftpm job (macos.yml)
+    'docs/mkdocs/docs/integration/swift/**',
+    '{workflow}',
+]
+
+# Mentions of excluded files that no job of the three workflows depends on:
+# (file that mentions it, the mention, reason)
+KNOWN_REFERENCES = [
+    ('cmake/ci.cmake', 'docs/', 'ci_test_examples; runs in repository_checks.yml, which has no path filter'),
+    ('cmake/ci.cmake', 'docs/mkdocs/', 'ci_test_build_documentation and ci_test_documentation_mermaid; they run in '
+                                       'repository_checks.yml, which has no path filter'),
+    ('cmake/ci.cmake', 'docs/mkdocs/docs/examples/', 'indentation check of ci_test_amalgamation; the same check runs in '
+                                                     'check_amalgamation.yml, which has no path filter'),
+    ('Makefile', 'docs/mkdocs/docs/examples/', 'make pretty; runs in check_amalgamation.yml, which has no path filter'),
+    ('Makefile', 'ChangeLog.md', 'make ChangeLog.md writes the file; no CI job runs it'),
+    ('Makefile', 'tests/fuzzing.md', 'help text'),
+    ('Makefile', 'tools/generate_natvis/README.md', 'help text'),
+    ('tests/src/make_test_data_available.hpp', 'README.md', 'a file of the external test data repository'),
+    ('tools/check_build_options/check_build_options.py', 'docs/', 'builds the path of package_managers.md, which '
+                                                                  'PATHS includes'),
+]
+
+
+# CI targets that read excluded files; they must run in a workflow without a path filter
+UNFILTERED_TARGETS = ['ci_test_examples', 'ci_test_build_documentation', 'ci_test_documentation_mermaid',
+                      'ci_test_amalgamation', 'ci_reuse_compliance']
+
+
+def git_files(root):
+    # fixed command, no user input; includes new files not yet added, so a local run
+    # sees what CI sees after the commit
+    out = subprocess.check_output(['git', 'ls-files', '-z', '--cached', '--others', '--exclude-standard'], cwd=root)  # nosec B603, B607
+    return [f for f in out.decode('utf-8').split('\0') if f]
+
+
+def glob_to_regex(pattern):
+    """Translate a GitHub Actions path pattern to a regular expression."""
+    regex = ''
+    i = 0
+    while i < len(pattern):
+        if pattern.startswith('**', i):
+            regex += '.*'
+            i += 2
+        elif pattern[i] == '*':
+            regex += '[^/]*'
+            i += 1
+        elif pattern[i] == '?':
+            regex += '[^/]'
+            i += 1
+        else:
+            regex += re.escape(pattern[i])
+            i += 1
+    return re.compile(regex + r'\Z')
+
+
+def compile_filter(paths, workflow):
+    return [(p.startswith('!'), glob_to_regex(p.lstrip('!').replace('{workflow}', workflow))) for p in paths]
+
+
+def included(compiled, path):
+    result = False
+    for negated, regex in compiled:
+        if regex.match(path):
+            result = not negated
+    return result
+
+
+def read_filter(root, workflow):
+    """Return the pull_request paths list of a workflow file."""
+    with open(os.path.join(root, workflow), encoding='utf-8') as f:
+        lines = f.read().splitlines()
+    paths = None
+    in_pull_request = False
+    for line in lines:
+        if re.match(r'^  pull_request:', line):
+            in_pull_request = True
+            continue
+        if in_pull_request:
+            if re.match(r'^  \S', line) or re.match(r'^\S', line):
+                break
+            if re.match(r'^    paths:\s*$', line):
+                paths = []
+                continue
+            m = re.match(r"^      - '(.*)'\s*(#.*)?$", line)
+            if paths is not None and m:
+                paths.append(m.group(1))
+            elif paths is not None and line.strip() and not line.strip().startswith('#'):
+                break
+    return paths
+
+
+TOKEN = re.compile(r'(["\'/]?)([\w.-]+(?:/[\w.-]+)*)')
+
+
+COMMENT_LINE = re.compile(r'^[ \t]*(//|#|/?\*|--).*$', re.MULTILINE)
+
+
+class Mentions:
+    """Finds the words and paths in a text that name an excluded file or directory."""
+
+    def __init__(self, files, excluded, is_excluded):
+        self.files = set(files)
+        self.excluded = excluded
+        self.dirs = {'/'.join(f.split('/')[:n]) for f in files for n in range(1, f.count('/') + 1)}
+        # an excluded directory: a new file in it would be excluded
+        self.excluded_dirs = {d for d in self.dirs if is_excluded(d + '/new_file')}
+        # base names that only excluded files have, e.g. 'ChangeLog.md' but not 'CMakeLists.txt'
+        self.names = {os.path.basename(f) for f in excluded} - {os.path.basename(f) for f in files if f not in excluded}
+
+    def find(self, text):
+        """Yield (offset, mention) for every word or path in text that names an excluded file or directory."""
+        for m in TOKEN.finditer(text):
+            parts = m.group(2).rstrip('/').split('/')
+            # a single word names a directory only in a path context, e.g. 'docs' in os.path.join('docs', ...)
+            path_context = len(parts) > 1 or m.group(1)
+            for i in range(len(parts)):
+                path = '/'.join(parts[i:])
+                if path in self.files:
+                    if path in self.excluded:
+                        yield m.start(2), path
+                    break
+                if path in self.dirs and path_context:
+                    if path in self.excluded_dirs:
+                        yield m.start(2), path + '/'
+                    break
+            else:
+                if parts[-1] in self.names and '.' in parts[-1]:
+                    yield m.start(2), parts[-1]
+
+
+def known(path, mention):
+    return any(path == file and mention == known_mention for file, known_mention, _ in KNOWN_REFERENCES)
+
+
+def check_workflows(root):
+    """Return the errors in the filters of the workflows and in the targets they run."""
+    errors = []
+    for workflow in WORKFLOWS:
+        expected = [p.replace('{workflow}', workflow) for p in PATHS]
+        actual = read_filter(root, workflow)
+        if actual != expected:
+            errors.append('{}: the pull_request paths filter differs from tools/check_path_filters/check_path_filters.py\n'
+                          '  expected: {}\n  actual:   {}'.format(workflow, expected, actual))
+        with open(os.path.join(root, workflow), encoding='utf-8') as f:
+            text = f.read()
+        errors += ['{}: runs {}, which reads excluded files; run it in repository_checks.yml'.format(workflow, target)
+                   for target in UNFILTERED_TARGETS if re.search(r'\b' + target + r'\b', text)]
+    return errors
+
+
+def scanned_text(root, path):
+    """Return the text of a kept file without comment lines and without the filter itself, or None to skip it."""
+    # third-party code and Markdown files read nothing; this script lists the excluded files
+    if path.startswith('tests/thirdparty/') or path.endswith('.md') or path == SELF:
+        return None
+    try:
+        with open(os.path.join(root, path), encoding='utf-8') as f:
+            # a mention in a comment line reads nothing; keep the line numbers
+            text = COMMENT_LINE.sub('', f.read())
+    except (UnicodeDecodeError, OSError):
+        return None
+    if path in WORKFLOWS:
+        # the filter itself lists the excluded files
+        for p in PATHS:
+            text = text.replace("      - '{}'".format(p.replace('{workflow}', path)), '')
+    return text
+
+
+def check_mentions(root, files, excluded, finder):
+    """Return an error for every mention of an excluded file in a kept file that KNOWN_REFERENCES does not list."""
+    errors = []
+    for path in sorted(set(files) - excluded):
+        text = scanned_text(root, path)
+        reported = set()
+        for offset, mention in finder.find(text or ''):
+            if mention not in reported and not known(path, mention):
+                reported.add(mention)
+                line = text.count('\n', 0, offset) + 1
+                errors.append('{}:{}: mentions excluded {}; include it in PATHS if a compiler job reads it, '
+                              'or add it to KNOWN_REFERENCES'.format(path, line, mention))
+    return errors
+
+
+def check(root):
+    files = git_files(root)
+    union = [compile_filter(PATHS, w) for w in WORKFLOWS]
+
+    def is_excluded(path):
+        return not any(included(c, path) for c in union)
+
+    excluded = {f for f in files if is_excluded(f)}
+    errors = check_workflows(root) + check_mentions(root, files, excluded, Mentions(files, excluded, is_excluded))
+    for e in errors:
+        print(e)
+    if not errors:
+        print('path filters OK: {} of {} tracked files skip the compiler workflows'.format(len(excluded), len(files)))
+    return 1 if errors else 0
+
+
+def explain(changed):
+    for workflow in WORKFLOWS:
+        compiled = compile_filter(PATHS, workflow)
+        hits = [f for f in changed if included(compiled, f)]
+        print('{}: {}'.format(workflow, 'runs ({})'.format(', '.join(hits[:3]) + (' ...' if len(hits) > 3 else ''))
+                                       if hits else 'skipped'))
+    return 0
+
+
+def main():
+    parser = argparse.ArgumentParser(description=__doc__.splitlines()[0])
+    parser.add_argument('--root', default=REPO_ROOT, help='repository root')
+    parser.add_argument('--changed', nargs='+', metavar='FILE', help='show which workflows these changed files run')
+    args = parser.parse_args()
+    return explain(args.changed) if args.changed else check(args.root)
+
+
+if __name__ == '__main__':
+    sys.exit(main())