Call alloc_nodes() before reading chunks.back() in the json_view chunk test

The operands of == are unsequenced, and MSVC evaluated
d->edits->chunks.back() before alloc_nodes() added the new chunk, so the
check compared the result with the previous chunk and failed on
msvc-arm64 (Debug and Release).

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

.github/dependabot.yml

@@ -29,13 +29,6 @@ updates:
       - dependency-name: mermaid
         update-types: ["version-update:semver-major"]
 
-  - package-ecosystem: pip
-    directory: /.github/requirements
-    schedule:
-      interval: daily
-    cooldown:
-      default-days: 7
-
   - package-ecosystem: pip
     directory: /tools/astyle
     schedule:
@@ -43,7 +36,7 @@ updates:
     cooldown:
       default-days: 7
     ignore:
-      # astyle is deliberately pinned (see tools/astyle/requirements.in): newer versions
+      # astyle is deliberately pinned (see tools/astyle/requirements.txt): newer versions
       # reformat the code, and the pinned version defines the formatting CI enforces
       - dependency-name: astyle
 

.github/external_ci/appveyor.yml

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

.github/labeler.yml

@@ -63,8 +63,7 @@ labels:
     - "single_include/nlohmann/json_view\\.hpp"
     - "tests/src/unit-json_view.*"
     - "tests/src/json_view_test_helpers\\.hpp"
-    - "tests/src/fuzzer-(parse_json_view|json_view_image)\\.cpp"
-    - "tests/benchmarks/json_view/.*"
+    - "tests/src/fuzzer-parse_json_view\\.cpp"
     - "tools/amalgamate/config_json_view\\.json"
     - "docs/mkdocs/docs/features/json_view\\.md"
     - "docs/mkdocs/docs/api/basic_json_(document|view)/.*"

.github/requirements/meson.in

@@ -1 +0,0 @@
-meson==1.12.1

.github/requirements/meson.txt

@@ -1,10 +0,0 @@
-#
-# This file is autogenerated by pip-compile with Python 3.14
-# by the following command:
-#
-#    pip-compile --generate-hashes --no-emit-index-url --output-file=.github/requirements/meson.txt --strip-extras .github/requirements/meson.in
-#
-meson==1.12.1 \
-    --hash=sha256:930bc7542cbd9f57009e182fd014eba48cf1a0180a7b9006d2d32d8f168d8b02 \
-    --hash=sha256:ab0a6ca09f8ef70c564c8241fb5a23957886a0b53fb58412b5e07eaf07dba743
-    # via -r .github/requirements/meson.in

.github/requirements/semgrep.in

@@ -1 +0,0 @@
-semgrep==1.182.1

.github/workflows/check_amalgamation.yml

@@ -67,22 +67,23 @@ jobs:
       - name: Install astyle
         run: |
           python3 -mvenv venv
-          venv/bin/pip3 install --require-hashes -r $MAIN_DIR/tools/astyle/requirements.txt
+          venv/bin/pip3 install -r $MAIN_DIR/tools/astyle/requirements.txt
 
       - name: Install generate_natvis dependencies
-        run: pip3 install --require-hashes -r $MAIN_DIR/tools/generate_natvis/requirements.txt
+        run: pip3 install -r $NATVIS_TOOL_DIR/requirements.txt
 
       - name: Regenerate the tools/macro_builder tables in macro_scope.hpp
         run: |
           cd $MAIN_DIR
 
           # Built from this PR's own tools/macro_builder/main.cpp, not a
-          # develop checkout: unlike amalgamate.py, this tool has no other
-          # source of truth to check against (its own README documents that
-          # it must reproduce macro_scope.hpp byte for byte), so there is
-          # nothing to gain from checking out a separate copy, and doing so
-          # would make this step fail on a PR that adds support for a new
-          # dispatch table until that PR itself merges to develop.
+          # develop checkout: unlike amalgamate.py and generate_natvis.py,
+          # this tool has no other source of truth to check against (its
+          # own README documents that it must reproduce macro_scope.hpp
+          # byte for byte), so there is nothing to gain from checking out a
+          # separate copy, and doing so would make this step fail on a PR
+          # that adds support for a new dispatch table until that PR itself
+          # merges to develop.
           TMPDIR=$(mktemp -d ./macro_builder_check.XXXXXX)
           c++ -std=c++11 tools/macro_builder/main.cpp -o "$TMPDIR/macro_builder"
           "$TMPDIR/macro_builder" > "$TMPDIR/paste.hpp"
@@ -145,36 +146,14 @@ jobs:
       - name: Regenerate nlohmann_json.natvis
         run: |
           cd $MAIN_DIR
-          # The generator and its template are what this check verifies the
-          # committed natvis file against (which namespaces it lists, and
-          # what each entry looks like), so run this PR's copy rather than
-          # the develop checkout's: with develop's, a PR that changes either
-          # could never pass. generate_natvis.py loads the template from its
-          # own directory. Like the macro_builder step above, this only runs
-          # PR content in a job without credentials.
-          python3 tools/generate_natvis/generate_natvis.py $MAIN_DIR
-
-      - name: Check the nlohmann_json.natvis generator options
-        run: |
-          cd $MAIN_DIR
-          # The options for configurations outside the checked-in file write
-          # to a temporary file, so they do not affect the diff below.
-          GENERATOR=tools/generate_natvis/generate_natvis.py
-          python3 $GENERATOR --list-tags
-          TAG_COUNT=$(python3 $GENERATOR --list-tags | wc -l)
-
-          python3 $GENERATOR --abi-tags diag,_dp,_vns --abi-tags _diag --output $RUNNER_TEMP/abi_tags.natvis
-          grep -q '<!-- Namespace nlohmann::json_abi_diag_dp_vns -->' $RUNNER_TEMP/abi_tags.natvis
-          grep -q '<!-- Namespace nlohmann::json_abi_diag_dp_vns_v[0-9_]* -->' $RUNNER_TEMP/abi_tags.natvis
-          test $(grep -c '<!-- Namespace ' $RUNNER_TEMP/abi_tags.natvis) -eq $(( $(grep -c '<!-- Namespace ' nlohmann_json.natvis) + 2 ))
-
-          python3 $GENERATOR --all --output $RUNNER_TEMP/all.natvis
-          test $(grep -c '<!-- Namespace ' $RUNNER_TEMP/all.natvis) -eq $(( (1 << TAG_COUNT) * 2 + 1 ))
-
-          if python3 $GENERATOR --abi-tags _unknown --output $RUNNER_TEMP/unknown.natvis; then
-            echo "generate_natvis.py accepted an unknown ABI tag"
-            exit 1
-          fi
+          # The template is what this check verifies the committed natvis
+          # file against, so take it from this PR rather than from the
+          # develop checkout: generate_natvis.py loads the template from its
+          # own directory, and with develop's copy a PR that changes the
+          # template could never pass. Like the macro_builder step above,
+          # this only renders PR content in a job without credentials.
+          cp tools/generate_natvis/nlohmann_json.natvis.j2 $NATVIS_TOOL_DIR/
+          python3 $NATVIS_TOOL_DIR/generate_natvis.py $MAIN_DIR
 
       - name: Build patch and check for differences
         id: diff

.github/workflows/codeql-analysis.yml

@@ -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@24c54180a607b1449ed407dd24f251e4e9147c8d # v4.38.3
       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@24c54180a607b1449ed407dd24f251e4e9147c8d # v4.38.3
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@6f2ac81f5cd81fe351a197ba0b00d91d03cd2aee # v4.39.0
+      uses: github/codeql-action/analyze@24c54180a607b1449ed407dd24f251e4e9147c8d # v4.38.3

.github/workflows/comment_check_amalgamation.yml

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

.github/workflows/dependency-review.yml

@@ -31,12 +31,3 @@ jobs:
           persist-credentials: false
       - name: 'Dependency Review'
         uses: actions/dependency-review-action@a1d282b36b6f3519aa1f3fc636f609c47dddb294 # v5.0.0
-        with:
-          # Semgrep pins mcp==1.29.0 and opentelemetry-api~=1.37.0 exactly
-          # (.github/requirements/semgrep.txt), so these cannot be upgraded
-          # until Semgrep lifts its pins. They do not apply to our use: CI
-          # only runs `semgrep scan` on the checkout and never starts the MCP
-          # server (GHSA-84m7-p3x7-pcfv, StreamableHTTP sessions) or parses
-          # incoming trace context (GHSA-xcq7-p3pf-p88h, tracestate parsing).
-          # Remove the entries once a Semgrep release allows the fixed versions.
-          allow-ghsas: GHSA-84m7-p3x7-pcfv, GHSA-xcq7-p3pf-p88h

.github/workflows/flawfinder.yml

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

.github/workflows/json_view_benchmarks.yml

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

.github/workflows/scorecards.yml

@@ -50,7 +50,7 @@ jobs:
           persist-credentials: false
 
       - name: "Run analysis"
-        uses: ossf/scorecard-action@fa7117db83c52d787ae5a89f350999701505d78e # v2.5.0
+        uses: ossf/scorecard-action@2d1146689b8cda280b9bc96326124645441f03bc # v2.4.4
         with:
           results_file: results.sarif
           results_format: sarif
@@ -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@24c54180a607b1449ed407dd24f251e4e9147c8d # v4.38.3
         with:
           sarif_file: results.sarif

.github/workflows/semgrep.yml

@@ -53,7 +53,7 @@ jobs:
       # SEMGREP_APP_TOKEN is still passed through so registry auth works if a
       # token is ever added.
       - name: Install Semgrep
-        run: python3 -m pip install --user --require-hashes -r .github/requirements/semgrep.txt
+        run: python3 -m pip install --user semgrep==1.168.0
 
       # `semgrep scan --sarif` always exits 0 even with findings; continue-on-error
       # is a safety net so the SARIF upload still runs if the scan itself errors.
@@ -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@24c54180a607b1449ed407dd24f251e4e9147c8d # v4.38.3
         with:
           sarif_file: semgrep.sarif
         if: always()

.github/workflows/ubuntu.yml

@@ -42,7 +42,7 @@ jobs:
       - name: Check that Meson and pkg-config offer the CMake options
         run: make check_build_options
       - name: Install Meson
-        run: pip install --require-hashes -r .github/requirements/meson.txt
+        run: pip install meson
       - name: Install with Meson
         run: |
           meson setup build-meson --prefix=${{ github.workspace }}/install

BUILD.bazel

@@ -37,7 +37,6 @@ cc_library(
         "include/nlohmann/detail/input/parser.hpp",
         "include/nlohmann/detail/input/position_t.hpp",
         "include/nlohmann/detail/input/pow5_table.hpp",
-        "include/nlohmann/detail/input/simd_scan.hpp",
         "include/nlohmann/detail/input/string_scan.hpp",
         "include/nlohmann/detail/iterators/internal_iterator.hpp",
         "include/nlohmann/detail/iterators/iter_impl.hpp",
@@ -74,7 +73,6 @@ cc_library(
         "include/nlohmann/detail/view/edit.hpp",
         "include/nlohmann/detail/view/edit_storage.hpp",
         "include/nlohmann/detail/view/errors.hpp",
-        "include/nlohmann/detail/view/image.hpp",
         "include/nlohmann/detail/view/input.hpp",
         "include/nlohmann/detail/view/iterator.hpp",
         "include/nlohmann/detail/view/lookup.hpp",

FILES.md

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

Makefile

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

cmake/requirements/requirements-cppcheck.txt

@@ -1 +1 @@
-cppcheck==1.5.3
+cppcheck==1.5.2

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

@@ -123,6 +123,4 @@ Linear in the size of the JSON value `j`.
   that is not valid UTF-8 unchanged, as before; `strict` (the default if
   [`JSON_STRICT_BINARY_UTF8`](../macros/json_strict_binary_utf8.md) is enabled) throws `type_error.316`.
 - Throws `type_error.321` for a discarded value since version 3.13.0; previously, a discarded value nested in an
-  array or object was silently skipped, producing invalid BJData.
-- Writes unsigned integers wider than 64 bits as high-precision numbers since version 3.13.0; previously, they were
-  silently truncated to 64 bits.
+  array or object was silently skipped, producing invalid BJData.

docs/mkdocs/docs/api/basic_json/to_bon8.md

@@ -37,9 +37,8 @@ With (2), the bytes written before the exception remain in the output adapter.
 
 ## Exceptions
 
-- Throws [out_of_range.407](../../home/exceptions.md#jsonexceptionout_of_range407) if `j` contains an integer outside
-  the range of int64 (an unsigned integer above 9223372036854775807, or, with a number type wider than 64 bits, any
-  integer beyond int64), which BON8 cannot represent
+- Throws [out_of_range.407](../../home/exceptions.md#jsonexceptionout_of_range407) if `j` contains an unsigned integer
+  above 9223372036854775807, which BON8 cannot represent
 - Throws [type_error.316](../../home/exceptions.md#jsonexceptiontype_error316) if `j` contains a string that is not
   valid UTF-8
 - Throws [type_error.321](../../home/exceptions.md#jsonexceptiontype_error321) if `j` or a value nested in it is

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

@@ -47,10 +47,6 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
 
 - Throws [`type_error.317`](../../home/exceptions.md#jsonexceptiontype_error317) if the top-level type of the JSON value
   is not an object; example: `"to serialize to BSON, top-level type must be object, but is string"`
-- Throws [`out_of_range.407`](../../home/exceptions.md#jsonexceptionout_of_range407) if `j` contains a signed integer
-  outside the range of int64 or an unsigned integer outside the range of uint64, which is only possible with a number
-  type wider than 64 bits; example:
-  `"integer number 9223372036854775808 cannot be represented by BSON as it does not fit int64"`
 - Throws [`out_of_range.409`](../../home/exceptions.md#jsonexceptionout_of_range409) if a key in the JSON object contains
   a null byte (code point U+0000); example: `"BSON key cannot contain code point U+0000 (at byte 2)"`
 - Throws [`out_of_range.412`](../../home/exceptions.md#jsonexceptionout_of_range412) if the length of a document, array,
@@ -123,5 +119,3 @@ pass before anything is written.
   that is not valid UTF-8 unchanged, as before; `strict` (the default if
   [`JSON_STRICT_BINARY_UTF8`](../macros/json_strict_binary_utf8.md) is enabled) throws `type_error.316` before anything
   is written.
-- Throws `out_of_range.407` for integers that do not fit 64 bits since version 3.13.0; previously, integers of a
-  number type wider than 64 bits were silently truncated.

docs/mkdocs/docs/api/basic_json/to_cbor.md

@@ -46,9 +46,6 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
 
 ## Exceptions
 
-- Throws [`out_of_range.407`](../../home/exceptions.md#jsonexceptionout_of_range407) if `j` contains an integer
-  outside [-2^64, 2^64-1], which is only possible with a number type wider than 64 bits; example:
-  `"integer number 18446744073709551616 cannot be represented by CBOR as it does not fit [-2^64, 2^64-1]"`
 - Throws [type_error.316](../../home/exceptions.md#jsonexceptiontype_error316) if a string or object key in `j` is
   not valid UTF-8 and `error_handler` is `strict` (the default only if
   [`JSON_STRICT_BINARY_UTF8`](../macros/json_strict_binary_utf8.md) is enabled)
@@ -93,5 +90,3 @@ Linear in the size of the JSON value `j`.
   [`JSON_STRICT_BINARY_UTF8`](../macros/json_strict_binary_utf8.md) is enabled) throws `type_error.316`.
 - Throws `type_error.321` for a discarded value since version 3.13.0; previously, a discarded value nested in an
   array or object was silently skipped, producing invalid CBOR.
-- Throws `out_of_range.407` for integers that do not fit 64 bits since version 3.13.0; previously, integers of a
-  number type wider than 64 bits were silently truncated.

docs/mkdocs/docs/api/basic_json/to_msgpack.md

@@ -46,9 +46,6 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
 
 ## Exceptions
 
-- Throws [`out_of_range.407`](../../home/exceptions.md#jsonexceptionout_of_range407) if `j` contains an integer
-  outside [-2^63, 2^64-1], which is only possible with a number type wider than 64 bits; example:
-  `"integer number 18446744073709551616 cannot be represented by MessagePack as it does not fit [-2^63, 2^64-1]"`
 - Throws [`out_of_range.412`](../../home/exceptions.md#jsonexceptionout_of_range412) if the length of a string, binary
   value, array, or object exceeds 4294967295, the maximum MessagePack can store; example:
   `"MessagePack length 4294967296 exceeds maximum of 4294967295"`
@@ -115,5 +112,3 @@ Linear in the size of the JSON value `j`.
   `number_unsigned_t`.
 - Throws `type_error.321` for a discarded value since version 3.13.0; previously, a discarded value nested in an
   array or object was silently skipped, producing invalid MessagePack.
-- Throws `out_of_range.407` for integers that do not fit 64 bits since version 3.13.0; previously, integers of a
-  number type wider than 64 bits were silently truncated.

docs/mkdocs/docs/api/basic_json_document/index.md

@@ -49,21 +49,14 @@ bookkeeping edits need, and calling any of them on one fails to compile (`#!cpp
 
 - **view_type** - the type of view returned by [`root()`](root.md) (`#!cpp basic_json_view<BasicJsonType, Editable>`)
 - **value_t** - the JSON type enumeration, see [`basic_json::value_t`](../basic_json/value_t.md)
-- **image_check** - how [`load()`](load.md) validates an image (`full`, `bounds`, `none`), see [`image_check`](load.md#image_check)
 
 ## Member functions
 
 - [(constructor)](basic_json_document.md)
-
-### Parsing
-
 - [**parse**](parse.md) (_static_) - deserialize from a compatible input, borrowing or owning it as appropriate
 - [**parse_copy**](parse_copy.md) (_static_) - deserialize a copy of a compatible input
 - [**accept**](accept.md) (_static_) - check whether the input is valid JSON
 - [**read**](read.md) - (re-)parse into this document, reusing its memory
-
-### Access
-
 - [**root**](root.md) - the view of the root value
 - [**is_discarded**](is_discarded.md) - return whether the last parse failed
 - [**source**](source.md) - the parsed text
@@ -71,14 +64,6 @@ bookkeeping edits need, and calling any of them on one fails to compile (`#!cpp
 - [**node_count**](node_count.md) - the number of index entries (values plus object keys)
 - [**memory_usage**](memory_usage.md) - the number of bytes held by the document
 - [**shrink_to_fit**](shrink_to_fit.md) - release unused index capacity
-
-### Images
-
-- [**save**](save.md) - the document as an image that `load()` reads without parsing
-- [**load**](load.md) (_static_) - read an image written by `save()`
-
-### Edits
-
 - [**set**](set.md) - replace a value, or set an object member, an array element, or the value a JSON pointer refers
   to (`#!cpp Editable` documents only)
 - [**push_back**](push_back.md) - append to an array (`#!cpp Editable` documents only)

docs/mkdocs/docs/api/basic_json_document/load.md

@@ -1,179 +0,0 @@
-# <small>nlohmann::basic_json_document::</small>load
-
-```cpp
-// (1)
-static basic_json_document load(const std::uint8_t* image, std::size_t size,
-                                 const image_check check = image_check::full);
-
-// (2)
-static basic_json_document load(const std::vector<std::uint8_t>& image,
-                                 const image_check check = image_check::full);
-
-// (3)
-static basic_json_document load(std::vector<std::uint8_t>&& image,
-                                 const image_check check = image_check::full);
-```
-
-1. Reads an image [`save()`](save.md) wrote, from a pointer and a byte count. The image is **borrowed**: `image`
-   must stay alive and unchanged for as long as the returned document, and any view taken from it, is used.
-2. Reads an image from a `#!cpp std::vector`. Also **borrowed** -- equivalent to overload 1 called with
-   `#!cpp image.data()` and `#!cpp image.size()`.
-3. Reads an image, keeping the vector instead of copying it: `image` is moved into the document (no copy), which
-   then owns it for as long as it needs the text and the decoded strings. [`owns_source()`](owns_source.md) is
-   `#!cpp true` afterward.
-
-In every overload, the node index is copied into storage the document itself owns -- so that it is properly aligned,
-and, for an [editable](index.md#edits) document, can be edited -- while the text and the decoded strings stay in
-`image`. The hash indexes [large objects](../../features/json_view.md) use for lookup are rebuilt, exactly as after
-parsing.
-
-## Parameters
-
-`image` (in)
-:   the image [`save()`](save.md) wrote (overloads 1 and 2), or one to take ownership of (overload 3)
-
-`size` (in)
-:   the number of bytes at `image` (overload 1)
-
-`check` (in)
-:   how thoroughly to validate `image` before trusting it; see [`image_check`](#image_check) below (optional,
-    `#!cpp image_check::full` by default)
-
-## Return value
-
-The document read from the image.
-
-## Exception safety
-
-Overloads 1 and 2 give the strong guarantee: `image` is only read, never written, so a thrown exception leaves the
-caller's buffer untouched.
-
-Overload 3 moves `image` into the document *before* validating it, so that a good image is kept without a copy. If
-loading then fails, the partially built document -- and the vector now inside it -- is discarded along with the
-exception, and `image` itself is left **empty**, not restored to what was passed in. Move a copy in instead, or
-validate with overload 2 first, if the original vector must survive a failed load.
-
-## Exceptions
-
-On a big-endian target, throws [`type_error.320`](../../home/exceptions.md#jsonexceptiontype_error320) -- the same
-exception [`save()`](save.md#exceptions) throws there, since the image format is little-endian only.
-
-Otherwise throws [`parse_error.116`](../../home/exceptions.md#jsonexceptionparse_error116) if `image` is not one
-`save()` could have written, or fails the requested `check`:
-
-| message               | when                                                                                                |
-|------------------------|------------------------------------------------------------------------------------------------------|
-| `too short`            | `image` is `#!cpp nullptr`, or `size` is smaller than the 64-byte header                             |
-| `unknown format`       | the header's magic bytes or version do not match, or a reserved header field is not zero             |
-| `sizes out of range`   | the node count, text size, or decoded-string size the header describes does not fit `size`, or the `#!cpp '\0'` after the text or after the decoded strings is missing |
-| `the check failed`     | `check` is not `#!cpp image_check::none`, and the image fails it -- see [`image_check`](#image_check) |
-
-!!! failure "Example messages"
-
-    ```
-    [json.exception.parse_error.116] parse error: invalid json_document image: too short
-    ```
-    ```
-    [json.exception.parse_error.116] parse error: invalid json_document image: unknown format
-    ```
-    ```
-    [json.exception.parse_error.116] parse error: invalid json_document image: sizes out of range
-    ```
-    ```
-    [json.exception.parse_error.116] parse error: invalid json_document image: the check failed
-    ```
-
-## Complexity
-
-Linear in the number of nodes, which are always copied into the document. `#!cpp image_check::none` does not read
-the text or the decoded strings. `#!cpp image_check::bounds` reads one byte of the text for each float token (its sign,
-to check the recorded digits against the token's length), and nothing else of the text or the decoded strings.
-
-With `#!cpp image_check::full`, linear in the size of the image (the nodes, the text, and the decoded strings), plus
-sorting the ranges of the strings and of the float tokens (at most one per node): the contents of each distinct range
-are checked once, however many nodes refer to it.
-
-## Notes
-
-### `image_check` { #image_check }
-
-```cpp
-using image_check = detail::view::image_check;
-
-enum class image_check
-{
-    full,
-    bounds,
-    none
-};
-```
-
-How thoroughly `load()` validates `image` before trusting it.
-
-`full` (the default)
-:   Checks everything the parser itself guarantees: structure and bounds; that every string is valid UTF-8 (and, for a
-    string still in the source text, that it contains no quote, backslash, or control character); and that every number
-    token is well-formed and matches the value stored for it. Strings and float tokens may share a range only if the
-    ranges are identical (as nodes that share a value do), and never overlap otherwise. Reading and serializing a
-    checked image is safe and always produces valid JSON, exactly as for a parsed document. This is the right choice for
-    an image from anything you do not fully control -- a file, a cache shared with other processes, a peer on the
-    network.
-
-`bounds`
-:   Checks structure and bounds only: that every offset and count in the node index stays inside the image. So
-    `load()`, [`root()`](root.md), element access, and [`materialize()`](../basic_json_view/materialize.md) can never
-    read outside the image, even on a damaged one. It does *not* guarantee that the image describes valid JSON: a
-    string that a `full` check would have rejected can make [`dump()`](../basic_json_view/dump.md) write invalid UTF-8
-    or invalid JSON, or throw [`type_error.316`](../../home/exceptions.md#jsonexceptiontype_error316), and a number can
-    read back with a value that does not match how it is spelled. An [editable document](../json_editable_document.md)
-    does not take such a string over: [`set`](set.md), [`push_back`](push_back.md) and [`insert`](insert.md) throw
-    `type_error.316` when they copy it from a view of the loaded document, and leave the editable document unchanged.
-    `bounds` skips scanning the text and the decoded strings, so it fits a cache your own process just wrote and reads
-    straight back, where damage would mean a bug or a hardware fault rather than adversarial input.
-
-`none`
-:   Checks nothing. Reading a damaged image is undefined behavior, so use it only for an image you trust as much as
-    your own memory.
-
-**Lifetime.** Overloads 1 and 2 borrow `image`: it must stay alive and byte-for-byte unchanged for as long as the
-returned document, and any [view](../basic_json_view/index.md) taken from it, is used -- exactly like a document
-[`parse()`](parse.md) borrowed its input for. Overload 3 avoids this by keeping the vector itself; see
-[`owns_source`](owns_source.md).
-
-!!! warning "Experimental"
-
-    The image format is versioned but not yet stable, and may change in an incompatible way before it is declared
-    stable; `load()` already rejects an image written by a different format version with `parse_error.116`
-    ("unknown format"). Use images to cache a document within one build of the library, or to hand one to another
-    process running the *same* build on the *same* (little-endian) machine -- not as a long-term storage format.
-
-## Examples
-
-??? example "Caching a document, ownership, and a rejected image"
-
-    The example below saves a parsed document as an image, checks that `load()` reproduces the original
-    [`dump()`](../basic_json_view/dump.md) without parsing, and shows the difference between
-    `load(std::move(image))` (owned) and `load(image)` (borrowed). It then damages one byte of the image and shows
-    `image_check::full` rejecting it with `parse_error.116`, while `image_check::bounds` -- meant for a cache the
-    process already trusts -- still reads it without going out of bounds.
-
-    ```cpp
-    --8<-- "examples/basic_json_document__load.cpp"
-    ```
-
-    Output:
-
-    ```json
-    --8<-- "examples/basic_json_document__load.output"
-    ```
-
-## See also
-
-- [save](save.md) - write the document as an image
-- [owns_source](owns_source.md) - return whether the document holds its own copy of the text
-- [parse](parse.md) - deserialize from JSON text instead of an image
-- [Images](../../features/json_view.md#images) - why and when to use images
-
-## Version history
-
-- Added in version 3.13.0.

docs/mkdocs/docs/api/basic_json_document/parse.md

@@ -149,7 +149,6 @@ buffer of a given length, pass a pair of pointers: `#!cpp parse(ptr, ptr + len)`
 - [accept](accept.md) - check whether the input is valid JSON
 - [read](read.md) - (re-)parse into this document, reusing its memory
 - [owns_source](owns_source.md) - return whether the document holds its own copy of the text
-- [load](load.md) - read a document from an image instead of parsing JSON text
 - [`BasicJsonType::parse`](../basic_json/parse.md) - the corresponding function of `basic_json`
 
 ## Version history

docs/mkdocs/docs/api/basic_json_document/read.md

@@ -80,7 +80,6 @@ compile; see [`parse`](parse.md#notes).
 
 - [parse](parse.md) - deserialize from a compatible input
 - [root](root.md) - the view of the root value
-- [load](load.md) - read a document from an image instead of parsing JSON text
 
 ## Version history
 

docs/mkdocs/docs/api/basic_json_document/save.md

@@ -1,104 +0,0 @@
-# <small>nlohmann::basic_json_document::</small>save
-
-```cpp
-std::vector<std::uint8_t> save() const;
-```
-
-Writes the document as an *image*: a byte buffer that [`load`](load.md) reads back without parsing. The image holds
-the node index, the source text (plus, for an edited document, the number tokens edits wrote), and the decoded
-strings (plus the strings edits wrote) -- everything [`root()`](root.md) needs, with nothing left to parse.
-
-An edited document is written in its *current* state, with its values in document order, the way the library's own
-parser would have produced them for that JSON text: a member [`set`](set.md) added goes at the end, an
-[`erase`](erase.md)d member leaves no trace, and a float that is not finite (NaN or positive/negative infinity)
-becomes null, the same substitution [`dump()`](../basic_json_view/dump.md) makes. The same document always saves to
-the same bytes -- also across `BasicJsonType` and `#!cpp Editable`, since the image reflects document order and
-values only, not which specialization produced them.
-
-## Return value
-
-The image, as a `#!cpp std::vector<std::uint8_t>`. Pass it, or a pointer to its data together with its size, to
-[`load`](load.md) to read the document back.
-
-## Exception safety
-
-Strong guarantee: `save()` does not modify `#!cpp *this` (it is `#!cpp const`), so if it throws, the document is left
-exactly as it was, and the partially built image is discarded with the exception.
-
-## Exceptions
-
-Throws [`type_error.320`](../../home/exceptions.md#jsonexceptiontype_error320) if the document is
-[discarded](is_discarded.md) -- a default-constructed document, or one a failed [`parse()`](parse.md)/
-[`read()`](read.md) with `allow_exceptions == false` left discarded.
-
-On a big-endian target, throws `type_error.320` with a different message instead: the image format is little-endian
-only (see [Notes](#notes)).
-
-Throws [`out_of_range.416`](../../home/exceptions.md#jsonexceptionout_of_range416) if the node count, the text, or
-the decoded strings of the image would individually reach 4 GiB -- the same 32-bit offsets
-[`parse()`](parse.md#exceptions) and, for edits, [`set`](set.md)/[`push_back`](push_back.md) are already limited to.
-
-!!! failure "Example messages"
-
-    ```
-    [json.exception.type_error.320] cannot save a discarded json_document
-    ```
-    ```
-    [json.exception.type_error.320] json_document images need a little-endian target
-    ```
-    ```
-    [json.exception.out_of_range.416] images of 4 GiB or more are not supported by json_document
-    ```
-
-## Complexity
-
-Linear in the size of the document: the number of nodes, plus the length of the text and the decoded strings that end
-up in the image.
-
-## Notes
-
-**Format.** The image begins with a 64-byte header (the magic bytes `#!cpp "NJVI"`, a version number, the node count,
-and the sizes of the text and the decoded strings, all little-endian), followed by the nodes
-([16 bytes each](../../home/architecture.md#node-index-of-json-views)), the text and a `#!cpp '\0'`, and the decoded
-strings and a `#!cpp '\0'`. [`load`](load.md) checks the header, and the sizes it describes, before reading anything
-else -- see [`load`'s Exceptions](load.md#exceptions).
-
-!!! warning "Experimental"
-
-    The image format is versioned but not yet stable: it may change in an incompatible way before it is declared
-    stable. Use images to cache a document within one build of the library, or to hand one to another process running
-    the *same* build on the *same* (little-endian) machine -- not as a long-term storage format. Keep the original
-    JSON text if you need to read a saved document back with a future library version.
-
-**Little-endian only.** The image is written as raw little-endian bytes, with no byte-swapping. `save()` (and
-[`load`](load.md)) throw `type_error.320` on a big-endian target rather than silently produce bytes a big-endian
-reader could not interpret correctly.
-
-## Examples
-
-??? example "Caching a parsed document as an image"
-
-    The example below saves a parsed configuration as an image -- the way a service might cache one to answer later
-    requests without parsing the text again -- and confirms that loading it back gives exactly the same result as
-    parsing did, and that saving is deterministic.
-
-    ```cpp
-    --8<-- "examples/basic_json_document__save.cpp"
-    ```
-
-    Output:
-
-    ```json
-    --8<-- "examples/basic_json_document__save.output"
-    ```
-
-## See also
-
-- [load](load.md) - read an image written by `save()`
-- [owns_source](owns_source.md) - return whether the document holds its own copy of the text
-- [`basic_json_view::dump`](../basic_json_view/dump.md) - serialize the document to JSON text instead of an image
-- [Images](../../features/json_view.md#images) - why and when to use images
-
-## Version history
-
-- Added in version 3.13.0.

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

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

docs/mkdocs/docs/api/macros/json_disable_unlocked_file_io.md

@@ -10,9 +10,6 @@ earlier, instead of locking the file once and reading it with the unlocked stdio
 It does not change any result: values, exceptions, and the position of the file after parsing are the same either way.
 Only the speed and the locking of the file differ (see the notes on locking below).
 
-Builds with MemorySanitizer use `std::fgetc` automatically, because the inline `getc_unlocked` of glibc reads the stdio
-buffer directly, which glibc (not instrumented) filled, and MemorySanitizer would report it as uninitialized.
-
 ## Default definition
 
 The default value is `0`: the file is locked once and read with the unlocked stdio functions where they are available.

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

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

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

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

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

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

docs/mkdocs/docs/examples/basic_json_document__load.cpp

@@ -1,52 +0,0 @@
-#include <cstdint>
-#include <iostream>
-#include <string>
-#include <vector>
-#include <nlohmann/json_view.hpp>
-
-using json = nlohmann::json;
-using json_document = nlohmann::json_document;
-using image_check = json_document::image_check;
-
-int main()
-{
-    std::cout << std::boolalpha;
-
-    // the image of a parsed document -- as if read back from a cache file or
-    // received from another process running the same build of the library
-    const std::string text = R"({"name": "cache", "note": "caf\u00e9", "replicas": ["db2", "db3"]})";
-    const json_document parsed = json_document::parse(text);
-    const std::vector<std::uint8_t> image = parsed.save();
-
-    // (1)/(2) load() needs no parsing, yet dumps exactly what parsing did
-    const json_document borrowed = json_document::load(image);
-    std::cout << (borrowed.root().dump() == parsed.root().dump()) << '\n';
-    std::cout << borrowed.owns_source() << '\n'; // borrowed: still points into `image`
-
-    // (3) load(std::move(image)) keeps the vector instead of copying it
-    std::vector<std::uint8_t> to_move = image;
-    const json_document owned = json_document::load(std::move(to_move));
-    std::cout << owned.owns_source() << '\n';
-
-    // a damaged image -- the last byte of the decoded string "note" holds
-    // (an escape sequence, so it was unescaped into the document's own
-    // buffer), flipped, as storage or transport corruption might do
-    std::vector<std::uint8_t> damaged = image;
-    damaged[damaged.size() - 2] = 0xFF;
-
-    // image_check::full inspects strings and numbers, so it catches the damage
-    try
-    {
-        static_cast<void>(json_document::load(damaged, image_check::full));
-    }
-    catch (const json::parse_error& e)
-    {
-        std::cout << e.id << '\n';
-    }
-
-    // image_check::bounds only checks structure and bounds, so a cache the
-    // process already trusts loads without the extra scan -- reading a value
-    // the damage did not touch is still safe
-    const json_document trusted = json_document::load(damaged, image_check::bounds);
-    std::cout << trusted.root()["name"].get<std::string>() << '\n';
-}

docs/mkdocs/docs/examples/basic_json_document__load.output

@@ -1,5 +0,0 @@
-true
-false
-true
-116
-cache

docs/mkdocs/docs/examples/basic_json_document__save.cpp

@@ -1,30 +0,0 @@
-#include <cstdint>
-#include <iostream>
-#include <string>
-#include <vector>
-#include <nlohmann/json_view.hpp>
-
-using json_document = nlohmann::json_document;
-
-int main()
-{
-    std::cout << std::boolalpha;
-
-    // a configuration a service parses once and then caches as an image, so
-    // that later requests can load() it instead of parsing the text again
-    const std::string text = R"({"name": "cache", "host": "db1", "port": 6379, "replicas": ["db2", "db3"]})";
-    const json_document config = json_document::parse(text);
-
-    // save() turns the parsed document into a byte buffer: a 64-byte header,
-    // the node index, the source text, and the decoded strings
-    const std::vector<std::uint8_t> image = config.save();
-    std::cout << image.size() << '\n';
-
-    // the same document always saves to the same bytes
-    std::cout << (image == json_document::parse(text).save()) << '\n';
-
-    // loading the image back needs no parsing, yet dumps exactly what
-    // parsing the text produced
-    const json_document reloaded = json_document::load(image);
-    std::cout << (reloaded.root().dump() == config.root().dump()) << '\n';
-}

docs/mkdocs/docs/examples/basic_json_document__save.output

@@ -1,3 +0,0 @@
-316
-true
-true

docs/mkdocs/docs/features/index.md

@@ -14,8 +14,7 @@ C++ types, and finally serialize it again.
   [parsing untrusted input](parsing/untrusted_input.md).
 - [Zero-copy JSON views](json_view.md) — read a JSON text through a flat index instead of building a `json` tree;
   strings and numbers stay in the input and are only decoded when needed.
-- [Editable documents](json_view.md#editing-a-document) — modify a parsed document without building a `json` tree.
-- [Images](json_view.md#images) — save a parsed document and load it again without parsing it.
+  [Editable documents](json_view.md#editing-a-document) can also be modified.
 - [Comments](comments.md) and [trailing commas](trailing_commas.md) — opt-in relaxations of the JSON grammar.
 
 ## Accessing and modifying values

docs/mkdocs/docs/features/json_view.md

@@ -312,57 +312,6 @@ edits. See [`basic_json_document`'s Edits](../api/basic_json_document/index.md#e
 throws (the *basic* guarantee, not the strong one `dump()` and the read-only functions provide). How edits are kept in
 the index is described in the [architecture overview](../home/architecture.md#node-index-of-json-views).
 
-## Images
-
-[`save()`](../api/basic_json_document/save.md) writes a document as an *image*: a byte buffer that
-[`load()`](../api/basic_json_document/load.md) reads back into a document without parsing -- no lexing, no building
-the node index, nothing but copying the nodes and pointing the text and the decoded strings at the image. Where
-[`parse_copy()`](../api/basic_json_document/parse_copy.md) still has to scan the whole input,
-[`load()`](../api/basic_json_document/load.md) turns that scan into a copy of the node index alone.
-
-**Why.** A document that is parsed once and then read many times -- a configuration loaded at startup, a template
-rendered on every request, a large reference dataset a worker process needs in memory -- pays for parsing once but
-can amortize [`save()`](../api/basic_json_document/save.md)'s cost across every later load. That makes images useful
-for a cache: save a document the first time it is parsed (to a file, a shared-memory segment, an in-process cache),
-and [`load()`](../api/basic_json_document/load.md) it on every later use instead of parsing the source text again.
-They are just as useful for handing a parsed document to another process (or a forked worker) running the same build
-of the library, since [`load()`](../api/basic_json_document/load.md) turns the transfer into a copy of the node index
-plus pointers into the received bytes, not a re-parse.
-
-**Choosing a check.** [`load()`](../api/basic_json_document/load.md) takes an
-[`image_check`](../api/basic_json_document/load.md#image_check) that trades validation against speed:
-`image_check::full` (the default) checks everything the parser itself guarantees, so a checked image is exactly as
-safe to read and serialize as a freshly parsed document -- the right choice whenever the image did not come straight
-from this process's own [`save()`](../api/basic_json_document/save.md), such as a file or a network peer.
-`image_check::bounds` only checks structure and bounds -- cheaper, since it skips scanning the text and the decoded
-strings -- and fits a cache the process trusts, one it wrote and reads back itself. `image_check::none` skips
-validation entirely, for an image trusted as much as the process's own memory. See
-[`load()`'s Notes](../api/basic_json_document/load.md#notes) for exactly what each level does and does not guarantee.
-
-??? example "Example: cache a parsed configuration as an image"
-
-    ```cpp
-    --8<-- "examples/basic_json_document__save.cpp"
-    ```
-
-    Output:
-
-    ```json
-    --8<-- "examples/basic_json_document__save.output"
-    ```
-
-!!! warning "Experimental"
-
-    The image format is versioned but not yet stable, and may change in an incompatible way before it is declared
-    stable. It is little-endian only, and tied to the library build that wrote it -- use it to cache a document or to
-    hand one to another process running the *same* build, not as a long-term storage format; keep the original JSON
-    text if a saved document needs to be readable by a future library version.
-
-The idea of a document you can read without parsing comes from zero-copy formats such as
-[FlatBuffers](https://github.com/google/flatbuffers) and [YaFF](https://github.com/yandex/yaff); the check
-[`load()`](../api/basic_json_document/load.md) runs follows the idea of FlatBuffers' Verifier. No code is taken from
-either.
-
 ## Choosing between `json`, `ordered_json`, the SAX interface, and `json_view`
 
 | | [`json`](../api/json.md) / [`ordered_json`](../api/ordered_json.md) | [SAX interface](parsing/sax_interface.md) | [`json_document`](../api/json_document.md) / [`json_view`](../api/json_view.md) | [`json_editable_document`](../api/json_editable_document.md) / [`json_editable_view`](../api/json_editable_view.md) |
@@ -371,7 +320,6 @@ either.
 | **Mutability** | freely mutable | not applicable (a one-shot event stream) | read-only | [`set`](../api/basic_json_document/set.md)/[`push_back`](../api/basic_json_document/push_back.md)/[`insert`](../api/basic_json_document/insert.md)/[`erase`](../api/basic_json_document/erase.md) edit in place; the source text is never rewritten |
 | **What you get** | a full tree you can read, write, and keep as long as you like | a sequence of callbacks; whatever your handler builds from them | a flat index plus, on demand, [`materialize()`](../api/basic_json_view/materialize.md)d `json`/`ordered_json` values for the parts you actually use | the same, plus [`dump()`](../api/basic_json_view/dump.md) of an edited document that keeps the member order and, with [`number_format::source`](../api/basic_json_view/number_format.md), the spelling of every untouched number |
 | **Typical use** | general-purpose JSON handling: config, request/response bodies you build or modify, anything you hold onto | validating or projecting a text into your own data structure without ever holding the whole thing as JSON | large or high-volume input where you only need part of it, or need it repeatedly, and can keep the source text (or a copy) alive for as long as the document lives | a document you read, patch a few fields of, and write back -- a configuration file, for instance -- where the rest of it should come back exactly as it was |
-| **Caching/reload** | not applicable -- re-parse, or roll your own serialization | not applicable | [`save()`](../api/basic_json_document/save.md)/[`load()`](../api/basic_json_document/load.md): cache the parsed index as an image and reload it without parsing | same, saving the document's current -- possibly edited -- state |
 
 ## Version history
 

docs/mkdocs/docs/features/macros.md

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

docs/mkdocs/docs/features/namespace.md

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

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

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

docs/mkdocs/docs/features/performance.md

@@ -20,38 +20,31 @@ below apply on every supported standard. This adapter exposes two optimizations
 
 - it can reconstruct already-consumed input on demand for error messages, instead of copying every character as it is
   read, and
-- the lexer can scan ordinary string characters, numbers, and indentation directly out of the buffer, several bytes at
-  a time, rather than one character (and one function call) at a time.
+- the lexer can scan ordinary string characters directly out of the buffer, several bytes at a time, rather than one
+  character (and one function call) at a time.
 
-A `#!cpp std::istream` (including `#!cpp std::ifstream`) gets the same bulk scanning: `input_stream_adapter` scans the
-characters its stream buffer already holds (the *get area*) and asks the stream buffer for more only when they are used
-up. Nothing is read ahead, so the stream is left exactly where it would be after reading one character at a time, and
-[`operator>>`](../api/operator_gtgt.md) can still read several values from one stream. A stream buffer without a get
-area is read one character at a time. A `#!cpp FILE*` is still read one character at a time, but `file_input_adapter`
-locks the file once per parse instead of once per character. See
-[input sources and performance](parsing/index.md#input-sources-and-performance) for the full table. According to the
-description of [#5828](https://github.com/nlohmann/json/pull/5828), parsing from a stream is within about 10 to 20 % of
-parsing an equivalent `#!cpp std::string`.
+A `#!cpp std::istream` (including `#!cpp std::ifstream`) or `#!cpp FILE*`, by contrast, is read through
+`input_stream_adapter` or `file_input_adapter`, which read one character (or one block, for binary formats) at a time
+and expose neither optimization -- the lexer falls back to the same byte-at-a-time path it uses for any
+non-contiguous, general-purpose iterator range. An iterator pair over non-contiguous but random-access storage (e.g.
+`#!cpp std::deque<char>::iterator`) gets the first optimization but not the second, since the byte-scanning fast path
+additionally requires contiguous storage.
 
-Inputs that are still read one character at a time: iterator ranges that are not contiguous (e.g.
-`#!cpp std::list<char>` or `#!cpp std::istreambuf_iterator<char>`), wide strings, and user-defined adapters. An
-iterator pair over non-contiguous but random-access storage (e.g. `#!cpp std::deque<char>::iterator`) gets the first
-optimization but not the second, since the byte-scanning fast path requires contiguous storage.
-
-Practically: a file can be passed directly to `parse`, which also avoids the memory for a copy of the file. Reading it
-into a string first is no longer necessary for speed:
+Practically: if the JSON text is already in memory, or small enough to read into memory, prefer passing a
+`#!cpp std::string`, a `#!cpp std::vector<char>`, or a pointer range to `parse` over a `#!cpp std::istream`. For a
+file, that means reading it into a string first and then parsing the string, rather than passing a
+`#!cpp std::ifstream` directly to `parse` -- the latter never benefits from either optimization:
 
 ```cpp
-// fast: the stream buffer's get area is scanned in bulk
+// gets the contiguous fast paths
 std::ifstream f("example.json");
-json j = json::parse(f);
-```
+std::string contents((std::istreambuf_iterator<char>(f)), std::istreambuf_iterator<char>());
+json j = json::parse(contents);
 
-Two macros switch the stream optimizations off without changing any result:
-[`JSON_DISABLE_STREAM_BULK_SCAN`](../api/macros/json_disable_stream_bulk_scan.md) for stream buffers that do not follow
-the usual `#!cpp std::streambuf` contract, and
-[`JSON_DISABLE_UNLOCKED_FILE_IO`](../api/macros/json_disable_unlocked_file_io.md) for programs in which another thread
-must use the same `#!cpp FILE` object while it is parsed.
+// does not: input_stream_adapter has no fast path
+std::ifstream f2("example.json");
+json j2 = json::parse(f2);
+```
 
 For contiguous input with many non-ASCII characters, [`JSON_USE_SIMDUTF`](../api/macros/json_use_simdutf.md) can
 additionally speed up UTF-8 validation by using the [simdutf](https://github.com/simdutf/simdutf) library instead of

docs/mkdocs/docs/home/architecture.md

@@ -64,7 +64,7 @@ below are relative to `include/nlohmann`.
 |-----------|----------|
 | Value type enumeration | [`detail/value_t.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/value_t.hpp) |
 | Input adapters | [`detail/input/input_adapters.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/input_adapters.hpp) |
-| Lexer | [`detail/input/lexer.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/lexer.hpp), [`detail/input/number_parse.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/number_parse.hpp), [`detail/input/string_scan.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/string_scan.hpp), [`detail/input/simd_scan.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/simd_scan.hpp) |
+| Lexer | [`detail/input/lexer.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/lexer.hpp), [`detail/input/number_parse.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/number_parse.hpp), [`detail/input/string_scan.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/string_scan.hpp) |
 | Parser | [`detail/input/parser.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/parser.hpp) |
 | SAX interface and DOM builders | [`detail/input/json_sax.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/json_sax.hpp) |
 | Binary format readers | [`detail/input/binary_reader.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/binary_reader.hpp) |
@@ -262,14 +262,6 @@ edited:
 - Views of read-only documents compile without any of this: how views walk the index is a template parameter
   (`navigation<Editable>`).
 
-Images ([`save`](../api/basic_json_document/save.md) and [`load`](../api/basic_json_document/load.md),
-[`detail/view/image.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/view/image.hpp)) store
-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`,
-and `load` then rejects images of other versions (`parse_error.116`) instead of misreading them.
-
 ## Input adapters
 
 Input is read via **input adapters** that abstract a source. Every input adapter provides this interface:
@@ -339,11 +331,6 @@ The `serializer` (used by [`dump`](../api/basic_json/dump.md) and [`operator<<`]
 - `output_stream_adapter` writes to a `std::ostream`.
 - `output_string_adapter` appends to a string.
 
-The `binary_writer` does not call an adapter for every byte. The `to_*` functions that return a `std::vector` write
-into the vector through a sink (`output_vector_sink`) that is not virtual. The functions that take an output adapter
-write through a sink (`output_adapter_sink`) that collects the output in a buffer of one kibibyte and passes it to the
-adapter in blocks, so that the adapter is called (and a stream locked) once per block instead of once per value.
-
 ## Value conversion
 
 Values are converted from and to other types with the `JSONSerializer` template parameter. The default,

docs/mkdocs/docs/home/debugging.md

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

docs/mkdocs/docs/home/exceptions.md

@@ -395,23 +395,6 @@ A UBJSON high-precision number could not be parsed.
     [json.exception.parse_error.115] parse error at byte 5: syntax error while parsing UBJSON high-precision number: invalid number text: 1A
     ```
 
-### json.exception.parse_error.116
-
-[`basic_json_document::load()`](../api/basic_json_document/load.md) rejected an
-[image](../features/json_view.md#images): either the bytes are not one [`save()`](../api/basic_json_document/save.md)
-could have written (too short, an unknown magic number or format version, or sizes that do not fit the buffer), or
-they are, but fail the requested [`image_check`](../api/basic_json_document/load.md#image_check).
-
-!!! failure "Example message"
-
-    ```
-    [json.exception.parse_error.116] parse error: invalid json_document image: the check failed
-    ```
-
-!!! note
-
-    This exception was added in version 3.13.0, together with [images](../features/json_view.md#images).
-
 ## Iterator errors
 
 This exception is thrown if iterators passed to a library function do not match
@@ -848,26 +831,6 @@ from JSON text.
 
     This exception was added in version 3.13.0, together with editable [`json_document`s](../features/json_view.md).
 
-### json.exception.type_error.320
-
-[`basic_json_document::save()`](../api/basic_json_document/save.md) cannot write an
-[image](../features/json_view.md#images) of a [discarded](../api/basic_json_document/is_discarded.md) document.
-[`save()`](../api/basic_json_document/save.md) and [`load()`](../api/basic_json_document/load.md) also throw this
-exception on a big-endian target, since the image format is little-endian only.
-
-!!! failure "Example messages"
-
-    ```
-    [json.exception.type_error.320] cannot save a discarded json_document
-    ```
-    ```
-    [json.exception.type_error.320] json_document images need a little-endian target
-    ```
-
-!!! note
-
-    This exception was added in version 3.13.0, together with [images](../features/json_view.md#images).
-
 ### json.exception.type_error.321
 
 A discarded value (one created by [`parse()`](../api/basic_json/parse.md) with a callback that returns `false` for the
@@ -972,19 +935,9 @@ double-precision number when `number_float_t` is `#!cpp float`.
 
 ### json.exception.out_of_range.407
 
-An integer number cannot be represented by the binary format it is serialized to:
-
-- [BON8](../features/binary_formats/bon8.md) only stores integers that fit into int64, so
-  [`to_bon8`](../api/basic_json/to_bon8.md) throws for unsigned integers greater than 9223372036854775807.
-- [CBOR](../features/binary_formats/cbor.md), [MessagePack](../features/binary_formats/messagepack.md), and
-  [BSON](../features/binary_formats/bson.md) store integers in at most 64 bits. With the default number types, every
-  integer fits, but a [`number_integer_t`](../api/basic_json/number_integer_t.md) or
-  [`number_unsigned_t`](../api/basic_json/number_unsigned_t.md) wider than 64 bits (e.g., `__int128`) can hold values
-  outside the range of the format: [-2^64, 2^64-1] for CBOR, [-2^63, 2^64-1] for MessagePack, and the range of int64
-  (signed integers) or uint64 (unsigned integers) for BSON.
-
-[UBJSON](../features/binary_formats/ubjson.md) and [BJData](../features/binary_formats/bjdata.md) never throw this
-exception, because they serialize integers beyond 64 bits as high-precision numbers.
+An unsigned integer number greater than 9223372036854775807 cannot be represented in the binary format. This exception
+is only thrown by [`to_bon8`](../api/basic_json/to_bon8.md), as [BON8](../features/binary_formats/bon8.md) has no
+unsigned 64-bit integer type.
 
 !!! note "Former occurrences"
 
@@ -993,17 +946,11 @@ exception, because they serialize integers beyond 64 bits as high-precision numb
     - Since version 3.9.0, integer numbers beyond int64 are serialized as high-precision UBJSON numbers.
     - Since version 3.12.0, integer numbers beyond int64 are serialized as uint64 BSON numbers.
 
-    Before version 3.13.0, CBOR, MessagePack, and BSON silently truncated integers wider than 64 bits, and BJData
-    truncated unsigned integers wider than 64 bits.
-
-!!! failure "Example messages"
+!!! failure "Example message"
 
     ```
     integer number 18446744073709551615 cannot be represented by BON8 as it does not fit int64
     ```
-    ```
-    integer number 1267650600228229401496703205376 cannot be represented by CBOR as it does not fit [-2^64, 2^64-1]
-    ```
 
 ### json.exception.out_of_range.408
 
@@ -1141,9 +1088,7 @@ MessagePack's ext type and BSON's binary subtype are each stored in a single byt
 so they do not support an input of 4294967280 bytes (4 GiB minus 16 bytes) or more. The same 32-bit limit applies to an **editable** document's own
 storage: [`set`](../api/basic_json_document/set.md) and [`push_back`](../api/basic_json_document/push_back.md) throw
 this exception once the strings and number tokens written by edits reach 4 GiB in total, or once more than
-4294967295 arrays/objects have had an element set or appended to them. The same limit applies to an
-[image](../features/json_view.md#images): [`save()`](../api/basic_json_document/save.md) throws it if the node
-count, the text, or the decoded strings it would write would individually reach 4 GiB.
+4294967295 arrays/objects have had an element set or appended to them.
 
 !!! failure "Example messages"
 
@@ -1153,9 +1098,6 @@ count, the text, or the decoded strings it would write would individually reach
     ```
     [json.exception.out_of_range.416] edits of 4 GiB or more are not supported by json_document
     ```
-    ```
-    [json.exception.out_of_range.416] images of 4 GiB or more are not supported by json_document
-    ```
 
 !!! note
 

docs/mkdocs/mkdocs.yml

@@ -242,7 +242,6 @@ nav:
           - 'erase': api/basic_json_document/erase.md
           - 'insert': api/basic_json_document/insert.md
           - 'is_discarded': api/basic_json_document/is_discarded.md
-          - 'load': api/basic_json_document/load.md
           - 'memory_usage': api/basic_json_document/memory_usage.md
           - 'node_count': api/basic_json_document/node_count.md
           - 'owns_source': api/basic_json_document/owns_source.md
@@ -251,7 +250,6 @@ nav:
           - 'push_back': api/basic_json_document/push_back.md
           - 'read': api/basic_json_document/read.md
           - 'root': api/basic_json_document/root.md
-          - 'save': api/basic_json_document/save.md
           - 'set': api/basic_json_document/set.md
           - 'shrink_to_fit': api/basic_json_document/shrink_to_fit.md
           - 'source': api/basic_json_document/source.md
@@ -383,7 +381,6 @@ nav:
           - 'JSON_NO_AUTOMATIC_UDLS': api/macros/json_no_automatic_udls.md
           - 'JSON_NOEXCEPTION': api/macros/json_noexception.md
           - 'JSON_NO_IO': api/macros/json_no_io.md
-          - 'JSON_NO_SIMD': api/macros/json_no_simd.md
           - 'JSON_NO_THREAD_LOCAL': api/macros/json_no_thread_local.md
           - 'JSON_PRECISE_STREAM_POSITION': api/macros/json_precise_stream_position.md
           - 'JSON_SKIP_LIBRARY_VERSION_CHECK': api/macros/json_skip_library_version_check.md

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

@@ -6,7 +6,7 @@
     "": {
       "name": "check-mermaid",
       "dependencies": {
-        "jsdom": "30.1.3",
+        "jsdom": "30.1.2",
         "mermaid": "11.17.2"
       }
     },
@@ -40,9 +40,9 @@
       }
     },
     "node_modules/@asamuzakjp/dom-selector": {
-      "version": "10.0.3",
-      "resolved": "https://registry.npmjs.org/@asamuzakjp/dom-selector/-/dom-selector-10.0.3.tgz",
-      "integrity": "sha512-3+777rEPsOOjoy5/sRmIzHnoRDaLpm3XWY2dmWn/N7f/XwDG0bcpnFaKL3X9FYJUbNwLmpcJC1bUYexJRxsFlw==",
+      "version": "9.2.4",
+      "resolved": "https://registry.npmjs.org/@asamuzakjp/dom-selector/-/dom-selector-9.2.4.tgz",
+      "integrity": "sha512-YnVzxDxLaqL0t7Q4wfcgHZjg55Wm6y5EaO7Bhu3q9J7wq/8iw3PhsnWiOQhYekx4VexnbkgWpTT6n+QIV7kczw==",
       "license": "MIT",
       "dependencies": {
         "bidi-js": "^1.1.0",
@@ -1105,9 +1105,9 @@
       }
     },
     "node_modules/dompurify": {
-      "version": "3.4.17",
-      "resolved": "https://registry.npmjs.org/dompurify/-/dompurify-3.4.17.tgz",
-      "integrity": "sha512-B/pSlYVHQ58kqISD/yDjuJ1yfzI34m1gF4lAod2bwSRhiN4K5Cl3H8Af7hqB2PmTL911tdEudnnXn5FnhRoz0w==",
+      "version": "3.4.16",
+      "resolved": "https://registry.npmjs.org/dompurify/-/dompurify-3.4.16.tgz",
+      "integrity": "sha512-sqo+pNp3qRhCIpbgRi1y8Tgk27Bo2Ry7w0dC1NBeNTdZChWjz9Xb/KOoZbRP/R6pQZ80Qw8YhXw13hWWBbMRnQ==",
       "license": "(MPL-2.0 OR Apache-2.0)",
       "optionalDependencies": {
         "@types/trusted-types": "^2.0.7"
@@ -1202,13 +1202,13 @@
       "license": "MIT"
     },
     "node_modules/jsdom": {
-      "version": "30.1.3",
-      "resolved": "https://registry.npmjs.org/jsdom/-/jsdom-30.1.3.tgz",
-      "integrity": "sha512-hQMUPvRgN7KxsfIytDQji7bimuJeRQa6Qo5+iuiZQk5CafeRxLIA10/cG5YCBFNpD9RO3oqIiN4CO1Y44kxqXg==",
+      "version": "30.1.2",
+      "resolved": "https://registry.npmjs.org/jsdom/-/jsdom-30.1.2.tgz",
+      "integrity": "sha512-0FFE/jE1rppmVfUrJUgxqXjcwolZYIGtAgj1pTussMhNZxIxi7W/PvfWaMNroGi2B36X1IKHbexpZ9DhkoOPiQ==",
       "license": "MIT",
       "dependencies": {
         "@asamuzakjp/css-color": "^7.1.3",
-        "@asamuzakjp/dom-selector": "^10.0.3",
+        "@asamuzakjp/dom-selector": "^9.2.4",
         "@bramus/specificity": "^2.4.2",
         "@csstools/css-syntax-patches-for-csstree": "^1.1.15",
         "@exodus/bytes": "^1.16.0",
@@ -1221,7 +1221,7 @@
         "parse5": "^8.0.1",
         "saxes": "^6.0.0",
         "tough-cookie": "^6.0.2",
-        "undici": "^8.12.1",
+        "undici": "^8.11.2",
         "w3c-xmlserializer": "^6.0.0",
         "webidl-conversions": "^8.0.1",
         "whatwg-mimetype": "^5.0.0",
@@ -1241,29 +1241,28 @@
       }
     },
     "node_modules/katex": {
-      "version": "0.18.11",
-      "resolved": "https://registry.npmjs.org/katex/-/katex-0.18.11.tgz",
-      "integrity": "sha512-yvyz/2VMKqoho/35Hat5w37wIEdWJ5ElVMidTAlWrxr5uW4aBGsEpveTmKh18/zw08v/7lGswCPon4OhqmqrTA==",
-      "deprecated": "Accidentally published with breaking changes. Use 0.19.0 instead.",
+      "version": "0.16.47",
+      "resolved": "https://registry.npmjs.org/katex/-/katex-0.16.47.tgz",
+      "integrity": "sha512-Eeo8Ys1doU1z+x8AZsPpQu+p/QcZBI5PeOo7QGQdy2x2m0MU/hYagBbGOmXwr5KVbEfVuWv9LpnQWeehogurjg==",
       "funding": [
         "https://opencollective.com/katex",
         "https://github.com/sponsors/katex"
       ],
       "license": "MIT",
       "dependencies": {
-        "commander": "^15.0.0"
+        "commander": "^8.3.0"
       },
       "bin": {
         "katex": "cli.js"
       }
     },
     "node_modules/katex/node_modules/commander": {
-      "version": "15.0.0",
-      "resolved": "https://registry.npmjs.org/commander/-/commander-15.0.0.tgz",
-      "integrity": "sha512-z67u4ZhzCL/Tydu1lJARtEZYWbWaN7oYLHbsuzocr6y4N6WZAagG3RQ4FW61V1/0+jImpj293XfrcYnd1qxtPg==",
+      "version": "8.3.0",
+      "resolved": "https://registry.npmjs.org/commander/-/commander-8.3.0.tgz",
+      "integrity": "sha512-OkTL9umf+He2DZkUq8f8J9of7yL6RJKI24dVITBmNfZBmri9zYZQrKkuXiKhyfPSu8tUhnVBB1iKXevvnlR4Ww==",
       "license": "MIT",
       "engines": {
-        "node": ">=22.12.0"
+        "node": ">= 12"
       }
     },
     "node_modules/khroma": {
@@ -1522,9 +1521,9 @@
       }
     },
     "node_modules/undici": {
-      "version": "8.12.2",
-      "resolved": "https://registry.npmjs.org/undici/-/undici-8.12.2.tgz",
-      "integrity": "sha512-XtuDWVdqTLr3NAxm2ly9/hU6kUsJOgGh1RASzMBbsw6aWCOaQzHdW+QQDfdERjfJ2V5vL5pRPa4RetO9UfivDg==",
+      "version": "8.11.2",
+      "resolved": "https://registry.npmjs.org/undici/-/undici-8.11.2.tgz",
+      "integrity": "sha512-u4UB2/IrKdU6lFxumHmmo1a3fCQO5tzQllRorfoRS63txhrB7xTpSn1PftwC4qEHkOaqP95fCWW4lJzwErwzhQ==",
       "license": "MIT",
       "engines": {
         "node": ">=22.19.0"

docs/mkdocs/scripts/mermaid/package.json

@@ -4,10 +4,7 @@
   "description": "Validate the Mermaid diagrams of the documentation (see check_mermaid.mjs)",
   "type": "module",
   "dependencies": {
-    "jsdom": "30.1.3",
+    "jsdom": "30.1.2",
     "mermaid": "11.17.2"
-  },
-  "overrides": {
-    "katex": "0.18.11"
   }
 }

include/nlohmann/detail/abi_macros.hpp

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

include/nlohmann/detail/bit_ops.hpp

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

include/nlohmann/detail/conversions/to_chars.hpp

@@ -18,14 +18,17 @@
 #include <limits> // numeric_limits
 #include <type_traits> // conditional
 
+#ifdef _MSC_VER
+    #include <cstdlib> // _byteswap_uint64
+#endif
 
 // SSE2 (every x86-64 CPU) and NEON (every 64-bit Arm CPU) convert the 16
-// digits of a double at once (unless JSON_NO_SIMD selects the portable code)
-#if !defined(JSON_NO_SIMD) && (defined(__x86_64__) || (defined(_M_X64) && !defined(_M_ARM64EC)))
+// digits of a double at once
+#if defined(__x86_64__) || (defined(_M_X64) && !defined(_M_ARM64EC))
     #include <emmintrin.h>
     #define JSON_DTOA_SSE2 1
     #define JSON_DTOA_NEON 0
-#elif !defined(JSON_NO_SIMD) && (defined(__aarch64__) || defined(_M_ARM64)) && !defined(_M_ARM64EC) && !defined(__ARM_BIG_ENDIAN)
+#elif (defined(__aarch64__) || defined(_M_ARM64)) && !defined(_M_ARM64EC) && !defined(__ARM_BIG_ENDIAN)
     #include <arm_neon.h>
     #define JSON_DTOA_SSE2 0
     #define JSON_DTOA_NEON 1
@@ -34,7 +37,6 @@
     #define JSON_DTOA_NEON 0
 #endif
 
-#include <nlohmann/detail/bit_ops.hpp>
 #include <nlohmann/detail/conversions/zmij.hpp>
 #include <nlohmann/detail/macro_scope.hpp>
 
@@ -64,6 +66,16 @@ For a detailed description of the algorithm see:
 namespace dtoa_impl
 {
 
+template<typename Target, typename Source>
+Target reinterpret_bits(const Source source)
+{
+    static_assert(sizeof(Target) == sizeof(Source), "size mismatch");
+
+    Target target;
+    std::memcpy(&target, &source, sizeof(Source));
+    return target;
+}
+
 struct diyfp // f * 2^e
 {
     static constexpr int kPrecision = 64; // = q
@@ -218,7 +230,7 @@ boundaries compute_boundaries(FloatType value)
 
     using bits_type = typename std::conditional<kPrecision == 24, std::uint32_t, std::uint64_t >::type;
 
-    const auto bits = static_cast<std::uint64_t>(bit_cast<bits_type>(value));
+    const auto bits = static_cast<std::uint64_t>(reinterpret_bits<bits_type>(value));
     const std::uint64_t E = bits >> (kPrecision - 1);
     const std::uint64_t F = bits & (kHiddenBit - 1);
 
@@ -1072,10 +1084,13 @@ inline std::uint64_t eight_digit_bytes(std::uint64_t abcdefgh) noexcept
 /// the byte stores once this is inlined)
 inline void store_msb_first(char* p, std::uint64_t v) noexcept
 {
-#if JSON_LITTLE_ENDIAN_TARGET
-    v = byteswap(v);
+#if defined(__BYTE_ORDER__) && defined(__ORDER_LITTLE_ENDIAN__) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+    v = __builtin_bswap64(v);
     std::memcpy(p, &v, sizeof(v));
-#elif JSON_BIG_ENDIAN_TARGET
+#elif defined(__BYTE_ORDER__) && defined(__ORDER_BIG_ENDIAN__) && __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+    std::memcpy(p, &v, sizeof(v));
+#elif defined(_MSC_VER) // (little-endian on all its targets)
+    v = _byteswap_uint64(v);
     std::memcpy(p, &v, sizeof(v));
 #else
     for (unsigned i = 0; i < 8; ++i)
@@ -1327,66 +1342,6 @@ inline char* write_shortest(char* first, const zmij::shortest_decimal d) noexcep
     return end + (three ? 5 : 4);
 }
 
-/// the powers of ten up to 10^19 (all that fit in std::uint64_t)
-inline const std::array<std::uint64_t, 20>& powers_of_ten() noexcept
-{
-    static const std::array<std::uint64_t, 20> powers =
-    {
-        {
-            1u,
-            10u,
-            100u,
-            1000u,
-            10000u,
-            100000u,
-            1000000u,
-            10000000u,
-            100000000u,
-            1000000000u,
-            10000000000u,
-            100000000000u,
-            1000000000000u,
-            10000000000000u,
-            100000000000000u,
-            1000000000000000u,
-            10000000000000000u,
-            100000000000000000u,
-            1000000000000000000u,
-            10000000000000000000u
-        }
-    };
-    return powers;
-}
-
-/*!
-@brief digits * 10^exp, as write_decimal() writes it, for the digits of a
-double that need no conversion (count digits, at most 15, the first not 0;
-trailing zeros allowed): extended to 16 digits and written by write_shortest()
-
-@return a pointer past the text; up to 41 bytes at @a first are written
-        (some beyond the returned end)
-*/
-JSON_HEDLEY_NON_NULL(1)
-JSON_HEDLEY_RETURNS_NON_NULL
-inline char* write_short_decimal(char* first, std::uint64_t digits, int count, int exp) noexcept
-{
-    JSON_ASSERT(digits >= powers_of_ten()[static_cast<std::size_t>(count - 1)] && count <= 15);
-    const int scale = 16 - count;
-    return write_shortest(first, zmij::shortest_decimal{digits * powers_of_ten()[static_cast<std::size_t>(scale)], exp - scale - 1, 0, false});
-}
-
-/// as write_short_decimal(), counting the digits (not 0, less than 10^15)
-JSON_HEDLEY_NON_NULL(1)
-JSON_HEDLEY_RETURNS_NON_NULL
-inline char* write_short_decimal(char* first, std::uint64_t digits, int exp) noexcept
-{
-    JSON_ASSERT(digits != 0 && digits < 1000000000000000u);
-    // floor(log10(2^bits)) + 1 digits, or one less
-    const int log2_bound = ((64 - count_leading_zeros(digits)) * 1233) >> 12;
-    const int count = log2_bound + (digits >= powers_of_ten()[static_cast<std::size_t>(log2_bound)] ? 1 : 0);
-    return write_short_decimal(first, digits, count, exp);
-}
-
 /*!
 @brief whether FloatType is an IEEE 754 binary64 type (a double, or a long double
 that has the same format, as with MSVC and on Apple's Arm CPUs)
@@ -1447,7 +1402,8 @@ char* write_positive_zmij(char* first, const char* last, FloatType value)
 {
     static_assert(is_binary64<FloatType>::value,
                   "internal error: the conversion of Zmij needs IEEE 754 binary64 numbers");
-    const auto bits = bit_cast<std::uint64_t>(value);
+    std::uint64_t bits = 0;
+    std::memcpy(&bits, &value, sizeof(bits));
     const zmij::shortest_decimal d = zmij::to_shortest(bits);
     if (JSON_HEDLEY_LIKELY(last - first >= 41))
     {

include/nlohmann/detail/input/input_adapters.hpp

@@ -8,18 +8,17 @@
 
 #pragma once
 
-#include <algorithm> // count, find, max, min
+#include <algorithm> // count, find, min
 #include <array> // array
 #include <cstddef> // size_t
 #include <cstdint> // uint32_t
 #include <cstring> // strlen
 #include <iterator> // begin, end, iterator_traits, random_access_iterator_tag, distance, next, reverse_iterator
 #include <limits> // numeric_limits
-#include <memory> // unique_ptr
 #include <streambuf> // streambuf
 #include <string> // string, char_traits
 #include <type_traits> // enable_if, is_base_of, is_pointer, is_integral, remove_pointer
-#include <utility> // declval, move, pair
+#include <utility> // pair, declval
 #include <vector> // vector
 
 #ifndef JSON_NO_IO
@@ -39,16 +38,8 @@
     // 2 = Microsoft CRT _lock_file/_fgetc_nolock, 0 = none (std::fgetc, which
     // locks the file for every character). Only C libraries known to declare
     // the functions are listed; the macros are tested after <cstdio>, which
-    // defines __GLIBC__. MemorySanitizer builds always use std::fgetc: glibc's
-    // inline getc_unlocked reads the stdio buffer directly, which glibc (not
-    // instrumented) filled, so MemorySanitizer would report a false positive.
-    #if defined(__has_feature)
-        #if __has_feature(memory_sanitizer)
-            #define JSON_UNLOCKED_FILE_IO_MSAN 1
-        #endif
-    #endif
-
-    #if JSON_DISABLE_UNLOCKED_FILE_IO || defined(JSON_UNLOCKED_FILE_IO_MSAN)
+    // defines __GLIBC__.
+    #if JSON_DISABLE_UNLOCKED_FILE_IO
         #define JSON_UNLOCKED_FILE_IO 0
     #elif defined(_MSC_VER)
         #define JSON_UNLOCKED_FILE_IO 2
@@ -57,7 +48,6 @@
     #else
         #define JSON_UNLOCKED_FILE_IO 0
     #endif
-    #undef JSON_UNLOCKED_FILE_IO_MSAN
 #endif  // JSON_NO_IO
 
 NLOHMANN_JSON_NAMESPACE_BEGIN
@@ -73,82 +63,6 @@ enum class input_format_t { json, cbor, msgpack, ubjson, bson, bjdata, bon8 };
 
 #ifndef JSON_NO_IO
 /*!
-A growable array of characters for the part of a token that an input adapter
-copied out of its window: unlike std::vector<char>::push_back(), appending a
-character takes no reference to a local, and is a few instructions when there
-is room.
-*/
-class token_carry_buffer
-{
-  public:
-    token_carry_buffer() = default;
-    token_carry_buffer(const token_carry_buffer&) = delete;
-    token_carry_buffer& operator=(const token_carry_buffer&) = delete;
-    token_carry_buffer(token_carry_buffer&& rhs) noexcept
-        : m_data(std::move(rhs.m_data)), m_end(rhs.m_end), m_capacity_end(rhs.m_capacity_end)
-    {
-        rhs.m_end = rhs.m_capacity_end = nullptr;
-    }
-    token_carry_buffer& operator=(token_carry_buffer&&) = delete;
-    ~token_carry_buffer() = default;
-
-    void clear() noexcept
-    {
-        m_end = m_data.get();
-    }
-
-    void push_back(char c)
-    {
-        if (JSON_HEDLEY_UNLIKELY(m_end == m_capacity_end))
-        {
-            grow(1);
-        }
-        *m_end++ = c;
-    }
-
-    void append(const char* first, const char* last)
-    {
-        const auto n = static_cast<std::size_t>(last - first);
-        const auto room = static_cast<std::size_t>(m_capacity_end - m_end);
-        if (n > room)
-        {
-            grow(n);
-        }
-        if (n != 0)
-        {
-            std::memcpy(m_end, first, n);
-        }
-        m_end += n;
-    }
-
-    /// replace the contents of @a out
-    void copy_to(std::vector<char>& out) const
-    {
-        out.assign(m_data.get(), m_end);
-    }
-
-  private:
-    /// make room for @a extra more characters
-    JSON_HEDLEY_NEVER_INLINE void grow(std::size_t extra)
-    {
-        const auto size = static_cast<std::size_t>(m_end - m_data.get());
-        const auto capacity = static_cast<std::size_t>(m_capacity_end - m_data.get());
-        const std::size_t new_capacity = (std::max)(capacity < 32 ? static_cast<std::size_t>(32) : 2 * capacity, size + extra);
-        std::unique_ptr<char[]> data(new char[new_capacity]); // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
-        if (size != 0)
-        {
-            std::memcpy(data.get(), m_data.get(), size);
-        }
-        m_data = std::move(data);
-        m_end = m_data.get() + size;
-        m_capacity_end = m_data.get() + new_capacity;
-    }
-
-    std::unique_ptr<char[]> m_data{}; // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays,readability-redundant-member-init)
-    char* m_end = nullptr;
-    char* m_capacity_end = nullptr;
-};
-/*!
 Input adapter for stdio file access. This adapter read only 1 byte and do not use any
  buffer. This adapter is a very low level adapter.
 */
@@ -286,7 +200,6 @@ class input_stream_adapter
         , token_segment(rhs.token_segment)
         , current_in_get_area(rhs.current_in_get_area)
         , tracking_token(rhs.tracking_token)
-        , no_get_area(rhs.no_get_area)
 #endif
     {
         rhs.is = nullptr;
@@ -373,20 +286,37 @@ class input_stream_adapter
     std::char_traits<char>::int_type get_character()
     {
 #if !JSON_DISABLE_STREAM_BULK_SCAN
-        // the character is in the get area: step over it, as sbumpc() does
-        const char* const next = streambuf_access::get_ptr(sb);
-        if (JSON_HEDLEY_LIKELY(next != streambuf_access::get_end(sb)))
+        // sbumpc() refills the get area if it is exhausted
+        const bool refill = streambuf_access::get_ptr(sb) == streambuf_access::get_end(sb);
+        if (JSON_HEDLEY_UNLIKELY(refill))
         {
-            current_in_get_area = true;
-            streambuf_access::bump(sb, 1);
-            return std::char_traits<char>::to_int_type(*next);
-        }
-        if (no_get_area)
-        {
-            return get_character_no_get_area();
+            save_token_segment();
         }
 #endif
-        return get_character_slow();
+
+        auto res = sb->sbumpc();
+        // set eof manually, as we don't use the istream interface.
+        if (JSON_HEDLEY_UNLIKELY(res == std::char_traits<char>::eof()))
+        {
+#if !JSON_DISABLE_STREAM_BULK_SCAN
+            current_in_get_area = false;
+#endif
+            is->clear(is->rdstate() | std::ios::eofbit);
+        }
+#if !JSON_DISABLE_STREAM_BULK_SCAN
+        else if (JSON_HEDLEY_UNLIKELY(refill))
+        {
+            // the consumed character is at gptr() - 1, unless the streambuf
+            // has no get area and returned it from uflow()
+            const char* const next = streambuf_access::get_ptr(sb);
+            after_refill(res, next != nullptr && next != streambuf_access::get_begin(sb));
+        }
+        else
+        {
+            current_in_get_area = true;
+        }
+#endif
+        return res;
     }
 #endif
 
@@ -395,18 +325,6 @@ class input_stream_adapter
     {
 #if JSON_PRECISE_STREAM_POSITION
         commit_lookahead();
-#endif
-#if !JSON_DISABLE_STREAM_BULK_SCAN
-        // the elements are in the get area: copy them, as sgetn() does, but
-        // without the virtual call
-        const char* const first = streambuf_access::get_ptr(sb);
-        const auto available = static_cast<std::size_t>(streambuf_access::get_end(sb) - first);
-        if (JSON_HEDLEY_LIKELY(count * sizeof(T) <= available && count * sizeof(T) <= static_cast<std::size_t>((std::numeric_limits<int>::max)())))
-        {
-            std::memcpy(dest, first, count * sizeof(T));
-            streambuf_access::bump(sb, static_cast<int>(count * sizeof(T)));
-            return count * sizeof(T);
-        }
 #endif
         auto res = static_cast<std::size_t>(sb->sgetn(reinterpret_cast<char*>(dest), static_cast<std::streamsize>(count * sizeof(T))));
         if (JSON_HEDLEY_UNLIKELY(res < count * sizeof(T)))
@@ -494,7 +412,7 @@ class input_stream_adapter
     // last one if @a drop_last.
     void copy_token(std::vector<char>& out, bool drop_last) const
     {
-        token_carry.copy_to(out);
+        out = token_carry;
         if (token_segment != nullptr)
         {
             out.insert(out.end(), token_segment, current_end());
@@ -507,47 +425,6 @@ class input_stream_adapter
 #endif
 
   private:
-#if !JSON_PRECISE_STREAM_POSITION
-    // the get area is exhausted, or there is none
-#if !JSON_DISABLE_STREAM_BULK_SCAN
-    JSON_HEDLEY_NEVER_INLINE
-#endif
-    std::char_traits<char>::int_type get_character_slow()
-    {
-#if !JSON_DISABLE_STREAM_BULK_SCAN
-        // sbumpc() refills the get area if it is exhausted
-        const bool refill = streambuf_access::get_ptr(sb) == streambuf_access::get_end(sb);
-        if (JSON_HEDLEY_UNLIKELY(refill))
-        {
-            save_token_segment();
-        }
-#endif
-
-        auto res = sb->sbumpc();
-        // set eof manually, as we don't use the istream interface.
-        if (JSON_HEDLEY_UNLIKELY(res == std::char_traits<char>::eof()))
-        {
-#if !JSON_DISABLE_STREAM_BULK_SCAN
-            current_in_get_area = false;
-#endif
-            is->clear(is->rdstate() | std::ios::eofbit);
-        }
-#if !JSON_DISABLE_STREAM_BULK_SCAN
-        else if (JSON_HEDLEY_UNLIKELY(refill))
-        {
-            // the consumed character is at gptr() - 1, unless the streambuf
-            // has no get area and returned it from uflow()
-            const char* const next = streambuf_access::get_ptr(sb);
-            after_refill(res, next != nullptr && next != streambuf_access::get_begin(sb));
-        }
-        else
-        {
-            current_in_get_area = true;
-        }
-#endif
-        return res;
-    }
-#endif
 #if !JSON_DISABLE_STREAM_BULK_SCAN
     // Reads the protected get-area pointers of any std::streambuf. Naming the
     // members through a derived class makes forming the member pointers
@@ -571,11 +448,6 @@ class input_stream_adapter
         {
             (s->*(&streambuf_access::gbump))(n);
         }
-        // sbumpc() for an exhausted get area
-        static std::streambuf::int_type next_character(std::streambuf* s)
-        {
-            return (s->*(&streambuf_access::uflow))();
-        }
     };
 
     // one past the character last returned by get_character(), if that is in
@@ -596,53 +468,16 @@ class input_stream_adapter
     {
         if (token_segment != nullptr)
         {
-            token_carry.append(token_segment, streambuf_access::get_end(sb));
+            token_carry.insert(token_carry.end(), token_segment, streambuf_access::get_end(sb));
             token_segment = nullptr;
         }
     }
 
-#if !JSON_PRECISE_STREAM_POSITION
-    // The streambuf has no get area (e.g., std::cin synchronized with stdio):
-    // every character comes from uflow(), and the token is kept by value.
-    JSON_HEDLEY_NEVER_INLINE std::char_traits<char>::int_type get_character_no_get_area()
-    {
-        // the get area is exhausted, so this is what sbumpc() does
-        const auto res = streambuf_access::next_character(sb);
-        if (JSON_HEDLEY_UNLIKELY(res == std::char_traits<char>::eof() || streambuf_access::get_end(sb) != nullptr))
-        {
-            return get_character_no_get_area_other(res);
-        }
-        // current_in_get_area is false: only the first character of a get
-        // area, or the end of the input, is read here
-        if (tracking_token)
-        {
-            token_carry.push_back(std::char_traits<char>::to_char_type(res));
-        }
-        return res;
-    }
-
-    // @a res came from uflow() of a streambuf without a get area: it is the
-    // end of the input, or the streambuf has a get area now
-    JSON_HEDLEY_NEVER_INLINE std::char_traits<char>::int_type get_character_no_get_area_other(std::char_traits<char>::int_type res)
-    {
-        if (res == std::char_traits<char>::eof())
-        {
-            current_in_get_area = false;
-            is->clear(is->rdstate() | std::ios::eofbit);
-            return res;
-        }
-        // the consumed character is at gptr() - 1
-        after_refill(res, streambuf_access::get_ptr(sb) != streambuf_access::get_begin(sb));
-        return res;
-    }
-#endif
-
     // character @a c was just read into a new get area (@a in_get_area) or
     // returned without one
     void after_refill(std::char_traits<char>::int_type c, bool in_get_area)
     {
         current_in_get_area = in_get_area;
-        no_get_area = !in_get_area;
         if (!tracking_token)
         {
             return;
@@ -681,16 +516,13 @@ class input_stream_adapter
 #endif
 #if !JSON_DISABLE_STREAM_BULK_SCAN
     /// the part of the current token that was in earlier get areas
-    token_carry_buffer token_carry{}; // NOLINT(readability-redundant-member-init)
+    std::vector<char> token_carry{}; // NOLINT(readability-redundant-member-init)
     /// start of the current token's part in the get area, or nullptr
     const char* token_segment = nullptr;
     /// whether the character last returned by get_character() is in the get area
     bool current_in_get_area = false;
     /// whether a token is tracked at all; the binary readers never start one
     bool tracking_token = false;
-    /// whether the streambuf had no get area when it was last asked for a
-    /// character
-    bool no_get_area = false;
 #endif
 };
 #endif  // JSON_NO_IO

include/nlohmann/detail/input/json_sax.hpp

@@ -418,9 +418,8 @@ class json_sax_dom_parser
         JSON_ASSERT(!ref_stack.empty());
         JSON_ASSERT(ref_stack.back()->is_object());
 
-        // add null at the given key and store the reference for later; the
-        // key is moved, as the lexer starts the next token with reset()
-        object_element = &(ref_stack.back()->m_data.m_value.object->operator[](std::move(val)));
+        // add null at the given key and store the reference for later
+        object_element = &(ref_stack.back()->m_data.m_value.object->operator[](val));
         return true;
     }
 

include/nlohmann/detail/input/lexer.hpp

@@ -12,7 +12,6 @@
 #include <cstddef> // size_t
 #include <cstdint> // uint32_t
 #include <cstdio> // snprintf
-#include <cstring> // memcmp
 #include <initializer_list> // initializer_list
 #include <string> // char_traits, string
 #include <utility> // move
@@ -418,43 +417,30 @@ class lexer : public lexer_base<BasicJsonType>
     }
 
     /// contiguous input: bulk-append the run of ordinary characters and complete
-    /// well-formed UTF-8 sequences starting at the current read position, then
-    /// read the first byte that needs individual handling (the closing quote, an
-    /// escape, a control character, or an ill-formed UTF-8 byte) like get().
-    /// That byte is taken from the buffer that was just scanned. Through get(),
-    /// Apple Clang merged this read with the other get() calls of the scan
-    /// function, which load the read position again right after it was stored
-    /// (3% of json::accept() on jeopardy.json on Apple M1).
-    char_int_type get_after_string_run(std::true_type /*bulk*/)
+    /// well-formed UTF-8 sequences starting at the current read position, leaving
+    /// the first byte that needs individual handling (the closing quote, an
+    /// escape, a control character, or an ill-formed UTF-8 byte) for get()
+    void scan_string_bulk(std::true_type /*bulk*/)
     {
         // a pending unget must be consumed through the normal path first
         if (next_unget)
         {
-            return get();
+            return;
         }
         const std::size_t remaining = ia.bulk_remaining();
         if (remaining == 0)
         {
-            return get();
+            return;
         }
-        const auto* const raw = ia.bulk_data();
-        const auto* const data = reinterpret_cast<const unsigned char*>(raw);
+        const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
 
-        const std::size_t pos = lexer_string_bulk_run(data, remaining);
-        if (pos != 0)
+        const std::size_t pos = string_bulk_run(data, remaining);
+        if (pos == 0)
         {
-            token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), pos);
-            bulk_consume(reinterpret_cast<const char*>(data), pos);
+            return;
         }
-        if (pos == remaining)
-        {
-            return get(); // end of the contiguous input
-        }
-        // what get() does, with the byte at hand
-        advance_position();
-        ia.bulk_skip(1);
-        current = char_traits<char_type>::to_int_type(raw[pos]);
-        return track_after_read();
+        token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), pos);
+        bulk_consume(reinterpret_cast<const char*>(data), pos);
     }
 
     /// consume @a n characters at @a data (the adapter's bulk_data()) and do
@@ -487,10 +473,7 @@ class lexer : public lexer_base<BasicJsonType>
     }
 
     /// streaming input: no bulk fast path
-    char_int_type get_after_string_run(std::false_type /*bulk*/)
-    {
-        return get();
-    }
+    void scan_string_bulk(std::false_type /*bulk*/) const noexcept {}
 
     /*!
     @brief scan a string literal
@@ -518,8 +501,11 @@ class lexer : public lexer_base<BasicJsonType>
         while (true)
         {
             // bulk-consume ordinary characters from contiguous input, then
-            // get the next character, the one that ends the run
-            switch (get_after_string_run(std::integral_constant<bool, bulk_scan>()))
+            // handle the next special byte through the switch below
+            scan_string_bulk(std::integral_constant<bool, bulk_scan> {});
+
+            // get the next character
+            switch (get())
             {
                 // end of file while parsing the string
                 case char_traits<char_type>::eof():
@@ -1639,12 +1625,9 @@ scan_number_done:
         const std::size_t avail = rem + 1;
 
         // validate + classify the number extent (mirrors scan_number()'s grammar)
-        // and accumulate the mantissa digits on the way, so that tokens with up
-        // to 19 digits need no second pass for their value
         std::size_t i = 0;
         std::size_t dot_index = std::string::npos;
         token_type number_type = token_type::value_unsigned;
-        std::uint64_t w = 0;
         if (data[0] == '-')
         {
             number_type = token_type::value_integer;
@@ -1654,21 +1637,22 @@ scan_number_done:
                 return token_type::uninitialized;
             }
         }
-        const std::size_t integer_begin = i;
         if (data[i] == '0')
         {
             ++i;
         }
         else if (data[i] >= '1' && data[i] <= '9')
         {
-            i = accumulate_digits(data, i, avail, w);
+            ++i;
+            while (i < avail && data[i] >= '0' && data[i] <= '9')
+            {
+                ++i;
+            }
         }
         else
         {
             return token_type::uninitialized;
         }
-        std::size_t digit_count = i - integer_begin;
-        std::size_t fraction_digits = 0;
         if (i < avail && data[i] == '.')
         {
             number_type = token_type::value_float;
@@ -1678,39 +1662,29 @@ scan_number_done:
             {
                 return token_type::uninitialized;
             }
-            const std::size_t fraction_begin = i;
-            i = accumulate_digits(data, i, avail, w);
-            fraction_digits = i - fraction_begin;
-            digit_count += fraction_digits;
+            while (i < avail && data[i] >= '0' && data[i] <= '9')
+            {
+                ++i;
+            }
         }
         // the mantissa ends here, whether or not an exponent part follows
         const std::size_t mantissa_end = i;
-        std::int64_t exponent = 0;
         if (i < avail && (data[i] == 'e' || data[i] == 'E'))
         {
             number_type = token_type::value_float;
             ++i;
-            bool negative_exponent = false;
             if (i < avail && (data[i] == '+' || data[i] == '-'))
             {
-                negative_exponent = data[i] == '-';
                 ++i;
             }
             if (i >= avail || !(data[i] >= '0' && data[i] <= '9'))
             {
                 return token_type::uninitialized;
             }
-            // saturated far beyond every range, see parse_float_exponent()
-            constexpr std::int64_t saturation = 100000000000000000; // 10^17
             while (i < avail && data[i] >= '0' && data[i] <= '9')
             {
-                if (exponent < saturation)
-                {
-                    exponent = (exponent * 10) + (data[i] - '0');
-                }
                 ++i;
             }
-            exponent = negative_exponent ? -exponent : exponent;
         }
         const std::size_t len = i;
         if (number_may_continue(len == avail, std::integral_constant<bool, bulk_window> {}))
@@ -1731,10 +1705,7 @@ scan_number_done:
 #if !JSON_DIAGNOSTIC_POSITIONS
         if (number_type != token_type::value_float)
         {
-            // up to 18 digits always fit into std::uint64_t and std::int64_t
-            const token_type integer_result = (digit_count <= 18)
-                                              ? store_integer(number_type, w)
-                                              : convert_integer(number_type, data, data + len);
+            const token_type integer_result = convert_integer(number_type, data, data + len);
             if (JSON_HEDLEY_LIKELY(integer_result != token_type::uninitialized))
             {
                 bulk_consume(data + 1, len - 1);
@@ -1748,42 +1719,15 @@ scan_number_done:
         }
 #endif
 
+        // materialize the token exactly as scan_number() would. reset() already
+        // cleared token_buffer, so append() fills it (assign() is avoided
+        // because custom string_t types need not provide it)
+        token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), len);
         decimal_point_position = dot_index;
 
         bulk_consume(data + 1, len - 1);
         read_number_terminator(std::integral_constant<bool, bulk_window> {});
 
-        // a float whose digits all fit into w converts from the accumulated
-        // value; longer ones (and other float formats) take the general path
-        if (number_type == token_type::value_float && digit_count <= 19)
-        {
-            float_significand s;
-            s.w = w;
-            s.exponent = exponent - static_cast<std::int64_t>(fraction_digits);
-            s.negative = data[0] == '-';
-            if (convert_accumulated_float(s, std::integral_constant<bool, has_native_float_format<number_float_t>::value> {}))
-            {
-                // the token text is only copied into token_buffer when
-                // get_string() asks for it; the library's own SAX handlers
-                // ignore it. A window into a stream may be refilled by the
-                // next read, so there the text is copied right away.
-                if (bulk_window)
-                {
-                    token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), len);
-                }
-                else
-                {
-                    pending_number_text = data;
-                    pending_number_length = len;
-                }
-                return token_type::value_float;
-            }
-        }
-
-        // materialize the token exactly as scan_number() would. reset() already
-        // cleared token_buffer, so append() fills it (assign() is avoided
-        // because custom string_t types need not provide it)
-        token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), len);
         return convert_number(number_type, mantissa_end);
     }
 
@@ -1812,35 +1756,6 @@ scan_number_done:
     /// the input is not handed back, so the terminator can stay unread
     void read_number_terminator(std::false_type /*window*/) const noexcept {}
 
-    /// binary32/binary64: the value of a float token from its accumulated
-    /// significand (see scan_number_bulk_contiguous())
-    bool convert_accumulated_float(const float_significand& s, std::true_type /*native*/) noexcept
-    {
-        value_float = decimal_to_float<number_float_t>(s);
-        return true;
-    }
-
-    /// other formats (e.g. x87 long double): not instantiated for them, as
-    /// decimal_to_float() only supports binary32/binary64
-    static bool convert_accumulated_float(const float_significand& /*s*/, std::false_type /*native*/) noexcept
-    {
-        return false;
-    }
-
-    /// the value of an integer token with at most 18 digits, accumulated in @a w
-    token_type store_integer(token_type number_type, std::uint64_t w) noexcept
-    {
-        if (number_type == token_type::value_unsigned)
-        {
-            value_unsigned = static_cast<number_unsigned_t>(w);
-            // reject values that do not round-trip into a narrower type
-            return (static_cast<std::uint64_t>(value_unsigned) == w) ? token_type::value_unsigned : token_type::uninitialized;
-        }
-        const std::int64_t x = -static_cast<std::int64_t>(w);
-        value_integer = static_cast<number_integer_t>(x);
-        return (static_cast<std::int64_t>(value_integer) == x) ? token_type::value_integer : token_type::uninitialized;
-    }
-
     /// contiguous input: try the number fast path, else the byte-path scanner
     token_type scan_number_dispatch(std::true_type /*bulk*/)
     {
@@ -1855,23 +1770,18 @@ scan_number_done:
     }
 
     /*!
-    @param[in] rest         the literal text after its first character, which
-                            is current (its length is a template parameter, so
-                            that the comparison of the contiguous fast path is
-                            a fixed-size load, not a call of memcmp)
-    @param[in] return_type  the token type to return on success
+    @param[in] literal_text  the literal text to expect
+    @param[in] length        the length of the passed literal text
+    @param[in] return_type   the token type to return on success
     */
-    template<std::size_t N>
-    JSON_HEDLEY_NEVER_INLINE token_type scan_literal(const char (&rest)[N], token_type return_type) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+    JSON_HEDLEY_NON_NULL(2)
+    token_type scan_literal(const char_type* literal_text, const std::size_t length,
+                            token_type return_type)
     {
-        constexpr std::size_t length = N - 1;
-        if (scan_literal_bulk(rest, length, std::integral_constant<bool, bulk_scan> {}))
+        JSON_ASSERT(char_traits<char_type>::to_char_type(current) == literal_text[0]);
+        for (std::size_t i = 1; i < length; ++i)
         {
-            return return_type;
-        }
-        for (std::size_t i = 0; i < length; ++i)
-        {
-            if (JSON_HEDLEY_UNLIKELY(char_traits<char_type>::to_char_type(get()) != static_cast<char_type>(rest[i])))
+            if (JSON_HEDLEY_UNLIKELY(char_traits<char_type>::to_char_type(get()) != literal_text[i]))
             {
                 error_message = "invalid literal";
                 return token_type::parse_error;
@@ -1880,27 +1790,6 @@ scan_number_done:
         return return_type;
     }
 
-    /// contiguous input: compare the rest of a literal at once; false (and
-    /// nothing consumed) if it does not match, so that the byte path reports
-    /// the error at the right character
-    JSON_HEDLEY_ALWAYS_INLINE bool scan_literal_bulk(const char* rest, const std::size_t length, std::true_type /*bulk*/)
-    {
-        if (next_unget || ia.bulk_remaining() < length
-                || std::memcmp(ia.bulk_data(), rest, length) != 0)
-        {
-            return false;
-        }
-        bulk_consume(reinterpret_cast<const char*>(ia.bulk_data()), length);
-        current = static_cast<char_int_type>(static_cast<unsigned char>(rest[length - 1]));
-        return true;
-    }
-
-    /// streaming input: no bulk fast path
-    bool scan_literal_bulk(const char* /*rest*/, const std::size_t /*length*/, std::false_type /*bulk*/) const noexcept
-    {
-        return false;
-    }
-
     /////////////////////
     // input management
     /////////////////////
@@ -1909,7 +1798,6 @@ scan_number_done:
     void reset() noexcept
     {
         token_buffer.clear();
-        pending_number_text = nullptr;
         decimal_point_position = std::string::npos;
 
 #if JSON_DIAGNOSTIC_POSITIONS
@@ -2169,30 +2057,10 @@ scan_number_done:
     /// return current string value
     string_t& get_string()
     {
-        if (pending_number_text != nullptr)
-        {
-            token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(pending_number_text), pending_number_length);
-            pending_number_text = nullptr;
-        }
         // a number token holds '.' regardless of the locale (#4084)
         return token_buffer;
     }
 
-    /// the value of a string token (key or string), which never has pending
-    /// number text, so get_string()'s check is not needed
-    string_t& get_string_token() noexcept
-    {
-        JSON_ASSERT(pending_number_text == nullptr);
-        return token_buffer;
-    }
-
-    /// the text of a float token for a SAX handler that ignores it (the
-    /// library's own handlers): empty, without copying the token
-    const string_t& get_ignored_number_text() const noexcept
-    {
-        return token_buffer;
-    }
-
     /////////////////////
     // diagnostics
     /////////////////////
@@ -2526,14 +2394,21 @@ scan_number_done:
                 return token_type::value_separator;
 
             // literals
-            // (the text after the first character; no local arrays, which
-            // would give this function a stack canary on every token)
             case 't':
-                return scan_literal("rue", token_type::literal_true);
+            {
+                std::array<char_type, 4> true_literal = {{static_cast<char_type>('t'), static_cast<char_type>('r'), static_cast<char_type>('u'), static_cast<char_type>('e')}};
+                return scan_literal(true_literal.data(), true_literal.size(), token_type::literal_true);
+            }
             case 'f':
-                return scan_literal("alse", token_type::literal_false);
+            {
+                std::array<char_type, 5> false_literal = {{static_cast<char_type>('f'), static_cast<char_type>('a'), static_cast<char_type>('l'), static_cast<char_type>('s'), static_cast<char_type>('e')}};
+                return scan_literal(false_literal.data(), false_literal.size(), token_type::literal_false);
+            }
             case 'n':
-                return scan_literal("ull", token_type::literal_null);
+            {
+                std::array<char_type, 4> null_literal = {{static_cast<char_type>('n'), static_cast<char_type>('u'), static_cast<char_type>('l'), static_cast<char_type>('l')}};
+                return scan_literal(null_literal.data(), null_literal.size(), token_type::literal_null);
+            }
 
             // string
             case '\"':
@@ -2581,11 +2456,6 @@ scan_number_done:
     /// whether the next get() call should just return current
     bool next_unget = false;
 
-    /// the text of the current float token in the input, not yet copied into
-    /// token_buffer (see get_string()), or nullptr
-    const char* pending_number_text = nullptr;
-    std::size_t pending_number_length = 0;
-
     /// the start position of the current token
     position_t position {};
 

include/nlohmann/detail/input/number_parse.hpp

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

include/nlohmann/detail/input/parser.hpp

@@ -51,20 +51,6 @@ template<typename BasicJsonType>
 using parser_callback_t =
     std::function<bool(int /*depth*/, parse_event_t /*event*/, BasicJsonType& /*parsed*/)>;
 
-/// whether a SAX handler ignores the text of float tokens (the library's own
-/// handlers do), so that the parser need not materialize it
-template<typename SAX>
-struct sax_ignores_number_text : std::false_type {};
-
-template<typename BasicJsonType, typename InputAdapterType>
-struct sax_ignores_number_text<json_sax_dom_parser<BasicJsonType, InputAdapterType>> : std::true_type {};
-
-template<typename BasicJsonType, typename InputAdapterType>
-struct sax_ignores_number_text<json_sax_dom_callback_parser<BasicJsonType, InputAdapterType>> : std::true_type {};
-
-template<typename BasicJsonType>
-struct sax_ignores_number_text<json_sax_acceptor<BasicJsonType>> : std::true_type {};
-
 /*!
 @brief syntax analysis
 
@@ -185,23 +171,6 @@ class parser
     }
 
   private:
-    /// the text of the current float token for @a sax (see sax_ignores_number_text)
-    template<typename SAX>
-    const string_t& number_float_text(SAX* /*sax*/)
-    {
-        return number_float_text(std::integral_constant<bool, sax_ignores_number_text<SAX>::value> {});
-    }
-
-    const string_t& number_float_text(std::true_type /*ignored*/) const noexcept
-    {
-        return m_lexer.get_ignored_number_text();
-    }
-
-    string_t& number_float_text(std::false_type /*ignored*/)
-    {
-        return m_lexer.get_string();
-    }
-
     /*!
     @brief run a DOM SAX parser to completion and position the lexer
 
@@ -244,9 +213,8 @@ class parser
     bool sax_parse_internal(SAX* sax)
     {
         // stack to remember the hierarchy of structured values we are parsing
-        // true = array; false = object (bytes, not std::vector<bool>, whose
-        // push_back() is a call with GCC)
-        std::vector<std::uint8_t> states;
+        // true = array; false = object
+        std::vector<bool> states;
         // value to avoid a goto (see comment where set to true)
         bool skip_to_state_evaluation = false;
 
@@ -279,7 +247,7 @@ class parser
                         {
                             return syntax_error(*sax, exception_message(token_type::value_string, "object key"));
                         }
-                        if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string_token())))
+                        if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string())))
                         {
                             return false;
                         }
@@ -291,7 +259,7 @@ class parser
                         }
 
                         // remember we are now inside an object
-                        states.push_back(0);
+                        states.push_back(false);
 
                         // parse values
                         get_token();
@@ -316,7 +284,7 @@ class parser
                         }
 
                         // remember we are now inside an array
-                        states.push_back(1);
+                        states.push_back(true);
 
                         // parse values (no need to call get_token)
                         continue;
@@ -333,7 +301,7 @@ class parser
                                                     out_of_range::create(exception_id::number_overflow, concat("number overflow parsing '", m_lexer.get_token_string(), '\''), nullptr));
                         }
 
-                        if (JSON_HEDLEY_UNLIKELY(!sax->number_float(res, number_float_text(sax))))
+                        if (JSON_HEDLEY_UNLIKELY(!sax->number_float(res, m_lexer.get_string())))
                         {
                             return false;
                         }
@@ -379,7 +347,7 @@ class parser
 
                     case token_type::value_string:
                     {
-                        if (JSON_HEDLEY_UNLIKELY(!sax->string(m_lexer.get_string_token())))
+                        if (JSON_HEDLEY_UNLIKELY(!sax->string(m_lexer.get_string())))
                         {
                             return false;
                         }
@@ -433,7 +401,7 @@ class parser
                 return true;
             }
 
-            if (states.back() != 0)  // array
+            if (states.back())  // array
             {
                 // comma -> next value
                 // or end of array (ignore_trailing_commas = true)
@@ -488,7 +456,7 @@ class parser
                         return syntax_error(*sax, exception_message(token_type::value_string, "object key"));
                     }
 
-                    if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string_token())))
+                    if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string())))
                     {
                         return false;
                     }

include/nlohmann/detail/input/simd_scan.hpp

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

include/nlohmann/detail/input/string_scan.hpp

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

include/nlohmann/detail/macro_scope.hpp

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

include/nlohmann/detail/macro_unscope.hpp

@@ -24,15 +24,6 @@
 #undef JSON_UNLOCKED_FILE_IO
 #undef JSON_DTOA_SSE2
 #undef JSON_DTOA_NEON
-#undef JSON_LITTLE_ENDIAN_TARGET
-#undef JSON_BIG_ENDIAN_TARGET
-#undef JSON_SCAN_NEON
-#undef JSON_SCAN_SSE2
-#undef JSON_SCAN_SSSE3
-#undef JSON_SCAN_SSSE3_DISPATCH
-#undef JSON_SCAN_SSSE3_TARGET
-#undef JSON_SCAN_VECTOR
-#undef JSON_SCAN_VECTOR_UTF8
 
 #ifndef JSON_TEST_KEEP_MACROS
     #undef JSON_CATCH

include/nlohmann/detail/meta/cpp_future.hpp

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

include/nlohmann/detail/meta/type_traits.hpp

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

include/nlohmann/detail/output/output_adapters.hpp

@@ -8,10 +8,7 @@
 
 #pragma once
 
-#include <algorithm> // max
-#include <array> // array
 #include <cstddef> // size_t
-#include <cstring> // memcpy
 #include <memory> // shared_ptr, make_shared
 #include <string> // basic_string
 #include <type_traits> // conditional, integral_constant, is_same
@@ -51,258 +48,32 @@ template<typename CharType> struct output_adapter_protocol
 template<typename CharType>
 using output_adapter_t = std::shared_ptr<output_adapter_protocol<CharType>>;
 
-/// the largest number of characters a writer may reserve() from a sink at once;
-/// output_vector_sink also appends writes of at least this size with insert()
-constexpr std::size_t max_reserve_size = 256;
-
-/// @brief copy @a length characters, at most 32, without a call of memcpy()
-///
-/// Short strings are the typical payload of a binary value, and a call of
-/// memcpy() costs more than copying them. A copy of 16 to 32 characters is two
-/// possibly overlapping 16-byte copies, one of 8 to 15 two 8-byte copies, and
-/// so on down to a single character; each is a fixed-size load and store.
-/// Nothing outside of [src, src + length) is read or written.
-template<typename CharType>
-inline void copy_short(CharType* dst, const CharType* src, const std::size_t length, std::true_type /*is_byte*/) noexcept
-{
-    JSON_ASSERT(length <= 32);
-    if (length >= 16)
-    {
-        std::array<char, 16> first; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
-        std::array<char, 16> last; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
-        std::memcpy(first.data(), src, 16);
-        std::memcpy(last.data(), src + (length - 16), 16);
-        std::memcpy(dst, first.data(), 16);
-        std::memcpy(dst + (length - 16), last.data(), 16);
-    }
-    else if (length >= 8)
-    {
-        std::array<char, 8> first; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
-        std::array<char, 8> last; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
-        std::memcpy(first.data(), src, 8);
-        std::memcpy(last.data(), src + (length - 8), 8);
-        std::memcpy(dst, first.data(), 8);
-        std::memcpy(dst + (length - 8), last.data(), 8);
-    }
-    else if (length >= 4)
-    {
-        std::array<char, 4> first; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
-        std::array<char, 4> last; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
-        std::memcpy(first.data(), src, 4);
-        std::memcpy(last.data(), src + (length - 4), 4);
-        std::memcpy(dst, first.data(), 4);
-        std::memcpy(dst + (length - 4), last.data(), 4);
-    }
-    else if (length != 0)
-    {
-        // 1 to 3: the first, the middle, and the last character
-        const CharType a = src[0];
-        const CharType b = src[length >> 1];
-        const CharType c = src[length - 1];
-        dst[0] = a;
-        dst[length >> 1] = b;
-        dst[length - 1] = c;
-    }
-}
-
-/// @brief copy @a length characters, of a character type wider than a byte
-template<typename CharType>
-inline void copy_short(CharType* dst, const CharType* src, const std::size_t length, std::false_type /*is_byte*/) noexcept
-{
-    std::memcpy(dst, src, length * sizeof(CharType));
-}
-
-/// the number of characters an empty vector is grown to by output_vector_sink
-constexpr std::size_t min_vector_sink_capacity = 64;
-
 /// @brief non-virtual output sink writing into a std::vector
 ///
 /// This sink is not part of the virtual output_adapter_protocol hierarchy: it is
 /// passed to binary_writer by value as a template parameter, so
 /// write_character()/write_characters() are ordinary (inlinable) calls with no
 /// vtable lookup and no shared_ptr. It is used for the common
-/// `to_cbor`/`to_msgpack`/... into a std::vector.
-///
-/// Most writes are a few bytes - a type marker, or a number of 1, 2, 4, or 8
-/// bytes - and appending those with push_back() or insert() cost more than
-/// encoding them: insert() is an out-of-line call into a routine that can insert
-/// anywhere, and resize() is one as well with libstdc++. The sink therefore keeps
-/// its own write position: it grows the vector geometrically ahead of the
-/// position and copies each write to it, so a write is a capacity check and a
-/// short copy. The destructor shrinks the vector to the bytes actually written,
-/// also when a write throws; shrinking a vector never allocates. The sink owns
-/// that trim, so it can be moved but not copied, and the vector must not be used
-/// while the sink is alive.
+/// `to_cbor`/`to_msgpack`/... into a std::vector. output_vector_adapter below
+/// wraps this same sink to provide the virtual interface.
 template<typename CharType, typename AllocatorType = std::allocator<CharType>>
 class output_vector_sink
 {
   public:
     explicit output_vector_sink(std::vector<CharType, AllocatorType>& vec) noexcept
-        : v(&vec), cursor(vec.data() + vec.size()), limit(cursor)
-    {}
-
-    output_vector_sink(const output_vector_sink&) = delete;
-    output_vector_sink& operator=(const output_vector_sink&) = delete;
-    output_vector_sink& operator=(output_vector_sink&&) = delete;
-
-    output_vector_sink(output_vector_sink&& other) noexcept
-        : v(other.v), cursor(other.cursor), limit(other.limit)
-    {
-        other.v = nullptr;
-    }
-
-    ~output_vector_sink()
-    {
-        if (v != nullptr)
-        {
-            v->resize(position());
-        }
-    }
-
-    // always inlined: GCC otherwise keeps these out of line in a large
-    // translation unit, and a call per byte or number costs more than the write
-    JSON_HEDLEY_ALWAYS_INLINE
-    void write_character(CharType c)
-    {
-        if (JSON_HEDLEY_UNLIKELY(cursor == limit))
-        {
-            grow(1);
-        }
-        *cursor++ = c;
-    }
-
-    // no JSON_HEDLEY_NON_NULL here: binary_writer legitimately passes a null
-    // pointer with length 0 for empty strings/binary values; memcpy must not
-    // see it.
-    JSON_HEDLEY_ALWAYS_INLINE
-    void write_characters(const CharType* s, std::size_t length)
-    {
-        if (JSON_HEDLEY_UNLIKELY(space() < length))
-        {
-            if (length >= max_reserve_size)
-            {
-                append(s, length);
-                return;
-            }
-            grow(length);
-        }
-        if (length <= 32)
-        {
-            copy_short(cursor, s, length, std::integral_constant<bool, sizeof(CharType) == 1>());
-            cursor += length;
-        }
-        else
-        {
-            std::memcpy(cursor, s, length * sizeof(CharType));
-            cursor += length;
-        }
-    }
-
-    /// @brief space for writing up to @a length characters directly
-    ///
-    /// Returns a pointer to at least @a length (at most @ref max_reserve_size)
-    /// writable characters at the write position; @ref commit then keeps the
-    /// first ones of them. A writer can store whole words there and keep only
-    /// the bytes it needs, and keep its write pointer in a register across many
-    /// values instead of updating the sink after each.
-    JSON_HEDLEY_ALWAYS_INLINE
-    CharType* reserve(const std::size_t length)
-    {
-        JSON_ASSERT(length <= max_reserve_size);
-        if (JSON_HEDLEY_UNLIKELY(space() < length))
-        {
-            grow(length);
-        }
-        return cursor;
-    }
-
-    /// keep the first @a length characters written to the space from reserve()
-    JSON_HEDLEY_ALWAYS_INLINE
-    void commit(const std::size_t length) noexcept
-    {
-        cursor += length;
-    }
-
-    /// nothing to pass on: the characters are in the vector (see output_adapter_sink)
-    void flush() noexcept
-    {}
-
-  private:
-    /// number of characters of *v written so far
-    std::size_t position() const noexcept
-    {
-        return static_cast<std::size_t>(cursor - v->data());
-    }
-
-    /// number of characters that fit the vector behind the write position
-    std::size_t space() const noexcept
-    {
-        return static_cast<std::size_t>(limit - cursor);
-    }
-
-    /// make room for at least @a length more characters after the position;
-    /// kept out of line so that the write functions stay small enough for
-    /// GCC to inline them into the writer
-    JSON_HEDLEY_NEVER_INLINE
-    void grow(const std::size_t length)
-    {
-        // use the capacity the vector already has, else at least double it;
-        // never less than min_vector_sink_capacity, so that a small value does not
-        // reallocate for every few bytes
-        const std::size_t written = position();
-        const std::size_t needed = written + length;
-        v->resize((std::max)(min_vector_sink_capacity, needed <= v->capacity()
-                             ? v->capacity()
-                             : (std::max)(needed, v->capacity() * 2)));
-        cursor = v->data() + written;
-        limit = v->data() + v->size();
-    }
-
-    /// append @a length (at least max_reserve_size) characters that do not fit
-    /// the space ahead of the position: insert() copies them once into the
-    /// grown vector, where grow() would first zero the new space and then copy
-    /// over it - noticeable for a large string or binary value
-    JSON_HEDLEY_NEVER_INLINE
-    void append(const CharType* s, const std::size_t length)
-    {
-        const std::size_t written = position();
-        v->resize(written);
-        if (v->capacity() - written < length)
-        {
-            // grow geometrically, with room for the writes that follow, so
-            // that the next grow() need not reallocate right away
-            v->reserve((std::max)(v->capacity() * 2, written + length + max_reserve_size));
-        }
-        v->insert(v->end(), s, s + length);
-        cursor = v->data() + v->size();
-        limit = cursor;
-    }
-
-    std::vector<CharType, AllocatorType>* v;
-    /// the write position: in *v, at the number of characters written so far
-    CharType* cursor;
-    /// the end of *v
-    CharType* limit;
-};
-
-/// output adapter for byte vectors
-template<typename CharType, typename AllocatorType = std::allocator<CharType>>
-class output_vector_adapter : public output_adapter_protocol<CharType>
-{
-  public:
-    explicit output_vector_adapter(std::vector<CharType, AllocatorType>& vec) noexcept
         : v(vec)
     {}
 
-    void write_character(CharType c) override
+    void write_character(CharType c)
     {
         v.push_back(c);
     }
 
     // no JSON_HEDLEY_NON_NULL here: binary_writer legitimately passes a null
-    // pointer with length 0 for empty strings/binary values; appending an empty
-    // range is a no-op
-    void write_characters(const CharType* s, std::size_t length) override
+    // pointer with length 0 for empty strings/binary values. Appending an empty
+    // range is a no-op; the type-erased path tolerates this via the (unattributed)
+    // virtual base, and the concrete sink must do the same.
+    void write_characters(const CharType* s, std::size_t length)
     {
         v.insert(v.end(), s, s + length);
     }
@@ -311,6 +82,33 @@ class output_vector_adapter : public output_adapter_protocol<CharType>
     std::vector<CharType, AllocatorType>& v;
 };
 
+/// output adapter for byte vectors
+///
+/// The appending itself lives in output_vector_sink; this class only adds the
+/// virtual output_adapter_protocol interface on top of it, so both the
+/// type-erased and the templated path share one implementation.
+template<typename CharType, typename AllocatorType = std::allocator<CharType>>
+class output_vector_adapter : public output_adapter_protocol<CharType>
+{
+  public:
+    explicit output_vector_adapter(std::vector<CharType, AllocatorType>& vec) noexcept
+        : sink(vec)
+    {}
+
+    void write_character(CharType c) override
+    {
+        sink.write_character(c);
+    }
+
+    void write_characters(const CharType* s, std::size_t length) override
+    {
+        sink.write_characters(s, length);
+    }
+
+  private:
+    output_vector_sink<CharType, AllocatorType> sink;
+};
+
 #ifndef JSON_NO_IO
 /// output adapter for output streams
 template<typename CharType>
@@ -365,17 +163,9 @@ class output_string_adapter : public output_adapter_protocol<CharType>
 ///
 /// Wraps the polymorphic output_adapter_t so the same binary_writer template can
 /// also target arbitrary adapters (output streams, strings, user-provided
-/// adapters) via the `output_adapter`-based overloads.
-///
-/// A write through the adapter is a virtual call, and for a stream a call with
-/// a sentry on top, which costs more than encoding the few bytes of most values.
-/// The sink therefore collects what is written in a buffer and passes it on in
-/// one piece when it is full, a write is too large for it, or @ref flush is
-/// called. Everything written reaches the adapter in the same order and with
-/// the same bytes; the destructor passes on what is left, so that a write that
-/// throws leaves the adapter with exactly the bytes written before it. Only
-/// @ref flush can report an error of the adapter (the destructor must not
-/// throw), so it has to be called once the value is written.
+/// adapters) via the `output_adapter`-based overloads. Each write still goes
+/// through one virtual call, exactly as before; only the concrete sinks above
+/// avoid it.
 template<typename CharType>
 class output_adapter_sink
 {
@@ -386,121 +176,20 @@ class output_adapter_sink
         JSON_ASSERT(oa);
     }
 
-    output_adapter_sink(const output_adapter_sink&) = delete;
-    output_adapter_sink& operator=(const output_adapter_sink&) = delete;
-    output_adapter_sink& operator=(output_adapter_sink&&) = delete;
-
-    output_adapter_sink(output_adapter_sink&& other) noexcept
-        : oa(std::move(other.oa)), used(other.used)
-    {
-        std::memcpy(buffer.data(), other.buffer.data(), other.used * sizeof(CharType));
-        other.used = 0;
-    }
-
-    ~output_adapter_sink()
-    {
-        // a normal return has flushed already, so this is for a write that threw
-        if (used != 0)
-        {
-            JSON_TRY
-            {
-                flush();
-            }
-            JSON_CATCH(...)
-            {
-                // nothing can be done about an adapter that throws here
-            }
-        }
-    }
-
-    JSON_HEDLEY_ALWAYS_INLINE
     void write_character(CharType c)
     {
-        if (JSON_HEDLEY_UNLIKELY(used == buffer_size))
-        {
-            flush();
-        }
-        buffer[used++] = c;
+        oa->write_character(c);
     }
 
     // no JSON_HEDLEY_NON_NULL: forwards (null, 0) for empty payloads, exactly as
     // the type-erased path already did before this sink existed
-    JSON_HEDLEY_ALWAYS_INLINE
     void write_characters(const CharType* s, std::size_t length)
     {
-        if (JSON_HEDLEY_UNLIKELY(buffer_size - used < length))
-        {
-            write_large(s, length);
-            return;
-        }
-        if (length <= 32)
-        {
-            copy_short(buffer.data() + used, s, length, std::integral_constant<bool, sizeof(CharType) == 1>());
-            used += length;
-        }
-        else
-        {
-            std::memcpy(buffer.data() + used, s, length * sizeof(CharType));
-            used += length;
-        }
-    }
-
-    /// space for writing up to @a length characters (see
-    /// output_vector_sink::reserve)
-    JSON_HEDLEY_ALWAYS_INLINE
-    CharType* reserve(const std::size_t length)
-    {
-        JSON_ASSERT(length <= max_reserve_size);
-        if (JSON_HEDLEY_UNLIKELY(buffer_size - used < length))
-        {
-            flush();
-        }
-        return buffer.data() + used;
-    }
-
-    /// keep the first @a length characters written to the space from reserve()
-    JSON_HEDLEY_ALWAYS_INLINE
-    void commit(const std::size_t length) noexcept
-    {
-        used += length;
-    }
-
-    /// pass everything written so far on to the adapter
-    void flush()
-    {
-        if (used != 0)
-        {
-            // reset first: the characters count as written even if the adapter throws
-            const std::size_t length = used;
-            used = 0;
-            oa->write_characters(buffer.data(), length);
-        }
+        oa->write_characters(s, length);
     }
 
   private:
-    /// a write that does not fit the space left in the buffer
-    JSON_HEDLEY_NEVER_INLINE
-    void write_large(const CharType* s, const std::size_t length)
-    {
-        flush();
-        if (length >= buffer_size)
-        {
-            oa->write_characters(s, length);
-        }
-        else
-        {
-            std::memcpy(buffer.data(), s, length * sizeof(CharType));
-            used = length;
-        }
-    }
-
-    /// large enough for reserve() at any time
-    static constexpr std::size_t buffer_size = 4 * max_reserve_size;
-
     output_adapter_t<CharType> oa;
-    /// number of characters of @ref buffer not yet passed on
-    std::size_t used = 0;
-    std::array<CharType, buffer_size> buffer{};
 };
 
 /// @brief whether std::basic_string<CharType> has a non-deprecated std::char_traits

include/nlohmann/detail/value_t.hpp

@@ -14,6 +14,7 @@
 #include <cstdint> // uint8_t
 #include <limits> // numeric_limits
 #include <string> // string
+#include <type_traits> // is_signed
 
 #include <nlohmann/detail/macro_scope.hpp>
 #if JSON_HAS_THREE_WAY_COMPARISON
@@ -207,16 +208,13 @@ FloatType compare_integer_with_float(const IntegerType i, const FloatType f) noe
 
     // values of IntegerType lie in [-bound, bound) when signed and in
     // [0, bound) when unsigned; digits excludes the sign bit, so bound is a
-    // power of two that the float represents exactly; the signedness comes
-    // from numeric_limits as well, because std::is_signed is false for class
-    // types such as 128-bit or multiprecision integers
-    using limits = std::numeric_limits<IntegerType>;
-    const FloatType bound = std::ldexp(static_cast<FloatType>(1), limits::digits);
+    // power of two that the float represents exactly
+    const FloatType bound = std::ldexp(static_cast<FloatType>(1), std::numeric_limits<IntegerType>::digits);
     if (f >= bound)
     {
         return ordered(-1);
     }
-    if (limits::is_signed ? (f < -bound) : (f < static_cast<FloatType>(0)))
+    if (std::is_signed<IntegerType>::value ? (f < -bound) : (f < static_cast<FloatType>(0)))
     {
         return ordered(1);
     }

include/nlohmann/detail/view/document_data.hpp

@@ -10,7 +10,7 @@
 
 #include <array> // array
 #include <cstddef> // size_t
-#include <cstdint> // uint8_t, uint32_t
+#include <cstdint> // uint32_t
 #include <cstring> // memcmp, memcpy
 #include <limits> // numeric_limits
 #include <map> // map
@@ -42,9 +42,7 @@ struct document_data
     std::size_t inline_capacity = 0;
     std::size_t max_depth = 0; ///< deepest nesting of arrays and objects (the root container is depth 1)
     std::vector<char> arena; ///< decoded strings that contained escapes (no terminator: they are handed out with their length)
-    std::size_t arena_size = 0; ///< bytes of decoded strings at base[1] (the arena, or those of a loaded image)
     std::string owned; ///< owned copy of the input, if any (a std::string, so that its NUL serves as the parser's sentinel)
-    std::vector<std::uint8_t> owned_image; ///< a loaded image the document owns (the text and the decoded strings point into it)
 
     // hash indexes of the keys of large objects (see object_index.hpp)
     static constexpr std::uint32_t index_min_members = 128;
@@ -121,7 +119,6 @@ struct document_data
     document_data() noexcept
         : arena() // NOLINT(readability-redundant-member-init)
         , owned() // NOLINT(readability-redundant-member-init)
-        , owned_image() // NOLINT(readability-redundant-member-init)
         , indexes() // NOLINT(readability-redundant-member-init)
         , index_slots() // NOLINT(readability-redundant-member-init)
         , large_objects() // NOLINT(readability-redundant-member-init)

include/nlohmann/detail/view/image.hpp

@@ -1,744 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-License-Identifier: MIT
-
-#pragma once
-
-#include <algorithm> // min, sort
-#include <array> // array
-#include <cstddef> // offsetof, size_t
-#include <cstdint> // int64_t, uint8_t, uint16_t, uint32_t, uint64_t
-#include <cstring> // memcmp, memcpy, memset
-#include <limits> // numeric_limits
-#include <string> // string
-#include <vector> // vector
-
-#include <nlohmann/json.hpp>
-#include <nlohmann/detail/view/document_data.hpp>
-#include <nlohmann/detail/view/errors.hpp>
-#include <nlohmann/detail/view/macro_scope.hpp>
-#include <nlohmann/detail/view/node.hpp>
-#include <nlohmann/detail/view/number.hpp>
-#include <nlohmann/detail/view/object_index.hpp>
-#include <nlohmann/detail/view/scan.hpp>
-
-// Images: a document stored so that loading it needs no parsing.
-//
-// Layout (little-endian): a 64-byte header, the nodes, the text (the source,
-// followed by the number tokens written by edits), a NUL, the decoded strings
-// (followed by the strings written by edits), a NUL. The idea is that of
-// zero-copy formats such as FlatBuffers (https://github.com/google/flatbuffers)
-// and YaFF (https://github.com/yandex/yaff); no code is taken from them.
-// check_image follows the idea of FlatBuffers' Verifier (bounds and
-// structure) and also checks what the parser guarantees about strings and
-// numbers, so that reading and serializing a checked image is safe and yields
-// valid JSON.
-
-NLOHMANN_JSON_NAMESPACE_BEGIN
-namespace detail
-{
-namespace view
-{
-
-/// how load() checks an image
-enum class image_check
-{
-    /// everything the parser guarantees: structure and bounds, strings (valid
-    /// UTF-8; source strings without quotes, backslashes, and control
-    /// characters), and numbers (well-formed, matching the stored values)
-    full,
-    /// structure and bounds only: reading and serializing are safe, but a
-    /// crafted image can yield invalid UTF-8, strings that serialize to
-    /// invalid JSON, or numbers that differ from their text
-    bounds,
-    /// none: for images from a trusted source only (a damaged image is
-    /// undefined behavior)
-    none,
-};
-
-struct image_header
-{
-    std::array<char, 4> magic;              ///< "NJVI"
-    std::uint32_t version;                  ///< 1
-    std::uint64_t node_count;
-    std::uint64_t text_size;
-    std::uint64_t arena_size;
-    std::array<std::uint64_t, 4> reserved;  ///< zero (for later versions)
-};
-static_assert(sizeof(image_header) == 64, "the image header must be 64 bytes");
-
-constexpr std::uint32_t image_version = 1;
-
-/// the largest node count and text or string size of an image (as for parsed
-/// documents, offsets and counts must fit 32 bits)
-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.
-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
-    {
-        const node* cur;
-        const node* end;
-        std::size_t index; ///< the container's node in out
-        std::uint32_t count;
-        bool object;
-    };
-    std::vector<frame> stack;
-    const auto string_node = [&](const node & s)
-    {
-        node r = s;
-        r.extra = 0;
-        r.flags = static_cast<std::uint8_t>(s.flags & node_flags::storage);
-        if (r.flags == node_flags::edited)
-        {
-            r.off = static_cast<std::uint32_t>(arena_size + arena_tail.size());
-            arena_tail.append(d.str(s), s.len);
-            r.flags = node_flags::escaped;
-        }
-        return r;
-    };
-    const auto copy_node = [&](const node * v)
-    {
-        node r = *v;
-        switch (static_cast<value_t>(v->kind))
-        {
-            case value_t::object:
-            case value_t::array:
-                r.flags = 0;
-                r.extra = 0;
-                r.off = (v->flags & (node_flags::moved | node_flags::is_new)) != 0 ? 0 : v->off;
-                r.len = 0;  // counted below
-                r.next = 0; // set when the container is complete
-                stack.push_back(frame{d.first_child_edited(v), d.child_end_edited(v), out.size(), 0, v->kind == static_cast<std::uint8_t>(value_t::object)});
-                break;
-            case value_t::string:
-                r = string_node(*v);
-                break;
-            case value_t::number_integer:
-            case value_t::number_unsigned:
-                if ((v->flags & node_flags::storage) == node_flags::edited)
-                {
-                    r.off = static_cast<std::uint32_t>(d.size + text_tail.size());
-                    text_tail.append(d.str(*v), number_length(*v));
-                }
-                r.flags = 0;
-                break;
-            case value_t::number_float:
-                if ((v->flags & node_flags::storage) == node_flags::edited)
-                {
-                    const char* const t = d.str(*v);
-                    if (t[0] == 'n' || t[0] == 'i' || (v->len > 1 && t[1] == 'i'))
-                    {
-                        r = node{}; // nan and infinity: null, as dump() writes them
-                        r.kind = static_cast<std::uint8_t>(value_t::null);
-                        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;
-                break;
-            case value_t::boolean:
-                r.flags = static_cast<std::uint8_t>(v->flags & node_flags::is_true);
-                break;
-            case value_t::null:
-            case value_t::binary:
-            case value_t::discarded:
-            default:
-                r.flags = 0;
-                break;
-        }
-        out.push_back(r);
-    };
-    copy_node(d.nodes);
-    while (!stack.empty())
-    {
-        const frame top = stack.back();
-        if (top.cur == top.end)
-        {
-            node& c = out[top.index];
-            c.len = top.count;
-            c.next = static_cast<std::uint32_t>(out.size() - top.index);
-            stack.pop_back();
-            continue;
-        }
-        if (top.object)
-        {
-            out.push_back(string_node(*top.cur));
-        }
-        const node* const value = top.cur + (top.object ? 1 : 0);
-        stack.back().cur = document_data::after(value);
-        ++stack.back().count;
-        copy_node(document_data::deref(value)); // may grow the stack
-    }
-}
-
-/// the document as an image
-inline std::vector<std::uint8_t> save_image(const document_data& d)
-{
-#if !NLOHMANN_VIEW_LITTLE_ENDIAN
-    throw_type_error(320, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
-#endif
-    const std::size_t arena_size = d.arena_size;
-    std::vector<node> compacted;
-    std::string text_tail;
-    std::string arena_tail;
-    if (d.edits)
-    {
-        compact_nodes(d, arena_size, compacted, text_tail, arena_tail);
-    }
-    const node* const nodes = d.edits ? compacted.data() : d.nodes;
-    const std::size_t count = d.edits ? compacted.size() : d.node_count;
-    const std::size_t text_size = d.size + text_tail.size();
-    const std::size_t total_arena = arena_size + arena_tail.size();
-    if (NLOHMANN_VIEW_UNLIKELY(text_size >= image_limit || total_arena >= image_limit || count >= image_limit))
-    {
-        // LCOV_EXCL_START (4 GiB)
-        throw_out_of_range(416, "images of 4 GiB or more are not supported by json_document");
-        // LCOV_EXCL_STOP
-    }
-    image_header h{};
-    h.magic = {{'N', 'J', 'V', 'I'}};
-    h.version = image_version;
-    h.node_count = count;
-    h.text_size = text_size;
-    h.arena_size = total_arena;
-    std::vector<std::uint8_t> image(sizeof(h) + (count * sizeof(node)) + text_size + 1 + total_arena + 1);
-    std::uint8_t* o = image.data();
-    std::memcpy(o, &h, sizeof(h));
-    o += sizeof(h);
-    std::memcpy(o, nodes, count * sizeof(node));
-    // the hash indexes are rebuilt by load(), whose check rejects any other
-    // extra of an object, and the same document saves to the same bytes
-    for (std::size_t i = 0; i < count; ++i)
-    {
-        if (nodes[i].kind == static_cast<std::uint8_t>(value_t::object) && nodes[i].extra != 0)
-        {
-            std::memset(o + (i * sizeof(node)) + offsetof(node, extra), 0, sizeof(nodes[i].extra));
-        }
-    }
-    o += count * sizeof(node);
-    const auto append = [&o](const char* s, std::size_t n)
-    {
-        if (n != 0)
-        {
-            std::memcpy(o, s, n);
-            o += n;
-        }
-    };
-    append(d.src, d.size);
-    append(text_tail.data(), text_tail.size());
-    *o++ = 0;
-    append(d.base[1], arena_size);
-    append(arena_tail.data(), arena_tail.size());
-    *o = 0;
-    return image;
-}
-
-/// the parts of a number token that the checks need
-struct number_token
-{
-    const unsigned char* int_start;
-    std::size_t int_digits;
-    std::size_t frac_digits;
-    std::int64_t exponent;
-    bool negative;
-    bool is_float; ///< a fraction or an exponent
-};
-
-/// 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)
-{
-    const unsigned char* const e = s + len;
-    const unsigned char* p = s;
-    t.negative = p != e && *p == '-';
-    p += t.negative ? 1 : 0;
-    if (p == e)
-    {
-        return false;
-    }
-    t.int_start = p;
-    if (*p == '0')
-    {
-        ++p;
-    }
-    else if (*p >= '1' && *p <= '9')
-    {
-        do
-        {
-            ++p;
-        }
-        while (p != e && is_digit(*p));
-    }
-    else
-    {
-        return false;
-    }
-    t.int_digits = static_cast<std::size_t>(p - t.int_start);
-    t.frac_digits = 0;
-    t.is_float = false;
-    if (p != e && *p == '.')
-    {
-        const unsigned char* const f0 = ++p;
-        while (p != e && is_digit(*p))
-        {
-            ++p;
-        }
-        if (p == f0)
-        {
-            return false;
-        }
-        t.frac_digits = static_cast<std::size_t>(p - f0);
-        t.is_float = true;
-    }
-    t.exponent = 0;
-    if (p != e && (*p | 0x20u) == 'e')
-    {
-        ++p;
-        const bool exp_negative = p != e && *p == '-';
-        p += (p != e && (*p == '+' || *p == '-')) ? 1 : 0;
-        if (p == e || !is_digit(*p))
-        {
-            return false;
-        }
-        do
-        {
-            t.exponent = t.exponent < 100000 ? (t.exponent * 10) + (*p - '0') : t.exponent;
-            ++p;
-        }
-        while (p != e && is_digit(*p));
-        t.exponent = exp_negative ? -t.exponent : t.exponent;
-        t.is_float = true;
-    }
-    return p == e;
-}
-
-/// the digit layout the parser records for a float token (compaction
-/// writes "many" instead; the caller accepts both)
-inline std::uint16_t float_layout(const number_token& t)
-{
-    return static_cast<std::uint16_t>((std::min)(t.int_digits, std::size_t{255}) | ((std::min)(t.frac_digits, std::size_t{255}) << 8u));
-}
-
-/// whether a float token (well-formed, per scan_number_token) is finite as
-/// double; parse() rejects floats that overflow, and as there, only a number
-/// whose magnitude could reach 1e308 needs the conversion
-inline bool float_token_finite(const unsigned char* s, std::size_t len, const number_token& t)
-{
-    if (static_cast<std::int64_t>(t.int_digits) + t.exponent > 300)
-    {
-        node n{};
-        n.kind = static_cast<std::uint8_t>(value_t::number_float);
-        n.len = static_cast<std::uint32_t>(len);
-        const auto v = float_value<double>(reinterpret_cast<const char*>(s), n); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-        return v <= (std::numeric_limits<double>::max)() && v >= -(std::numeric_limits<double>::max)();
-    }
-    return true;
-}
-
-/// whether an integer node matches its token the way the parser records it
-/// (after the bounds check; the token has at most 256 characters)
-inline bool check_integer(const node& n, const unsigned char* text)
-{
-    const std::size_t len = number_length(n);
-    const unsigned char* const s = text + n.off;
-    number_token t{};
-    if (!scan_number_token(s, len, t))
-    {
-        return false;
-    }
-    // the token's value is the stored one; number_integer nodes of edits can
-    // be non-negative (as basic_json keeps the type of a value)
-    const bool integer = n.kind == static_cast<std::uint8_t>(value_t::number_integer);
-    if (t.is_float || t.int_digits > 20 || (t.negative && !integer))
-    {
-        return false;
-    }
-    // (at most 19 digits cannot overflow; 20 digits are compared with 2^64 - 1)
-    if (t.int_digits == 20 && std::memcmp(t.int_start, "18446744073709551615", 20) > 0)
-    {
-        return false;
-    }
-    std::uint64_t m = 0;
-    for (const unsigned char* d = t.int_start; d != t.int_start + t.int_digits; ++d)
-    {
-        m = (m * 10) + static_cast<std::uint64_t>(*d - '0');
-    }
-    if (integer && m > (t.negative ? std::uint64_t{1} << 63u : (std::uint64_t{1} << 63u) - 1))
-    {
-        return false;
-    }
-    return integer_bits(n) == (t.negative ? 0 - m : m);
-}
-
-/// a byte range of the text or of the decoded strings
-struct byte_range
-{
-    std::uint32_t off;
-    std::uint32_t len;
-};
-
-/// a float token and the digit layout its node records
-struct float_range
-{
-    std::uint32_t off;
-    std::uint32_t len;
-    std::uint16_t extra;
-};
-
-/// Run check once for each distinct range of ranges (which are within bounds
-/// and not empty). Ranges that are not identical must not overlap: save()
-/// writes every string and token to a place of its own, and nodes that share
-/// a value (copies within a document) share the whole range. This bounds the
-/// work by the size of the text, however many nodes point to the same bytes.
-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)
-    {
-        return a.off != b.off ? a.off < b.off : a.len < b.len;
-    });
-    std::size_t end = 0;
-    for (std::size_t i = 0; i < ranges.size(); ++i)
-    {
-        const byte_range r = ranges[i];
-        if (i != 0 && r.off == ranges[i - 1].off && r.len == ranges[i - 1].len)
-        {
-            continue;
-        }
-        if (r.off < end || !check(r))
-        {
-            return false;
-        }
-        end = static_cast<std::size_t>(r.off) + r.len;
-    }
-    return true;
-}
-
-/// Check the float nodes: each token once (nodes of the same token must
-/// 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)
-    {
-        if (a.off != b.off)
-        {
-            return a.off < b.off;
-        }
-        if (a.len != b.len)
-        {
-            return a.len < b.len;
-        }
-        return a.extra < b.extra;
-    });
-    std::size_t end = 0;
-    std::size_t i = 0;
-    while (i < ranges.size())
-    {
-        const float_range r = ranges[i];
-        if (r.off < end)
-        {
-            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))
-        {
-            return false;
-        }
-        // 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)
-            {
-                return false;
-            }
-        }
-        end = static_cast<std::size_t>(r.off) + r.len;
-    }
-    return true;
-}
-
-/// the content checks of check_image: source strings as the parser leaves
-/// them (no quotes, backslashes, or control characters), decoded strings
-/// (valid UTF-8), and float tokens
-inline bool check_contents(const unsigned char* text, const unsigned char* arena,
-                           std::vector<byte_range>& source_strings, std::vector<byte_range>& decoded_strings,
-                           std::vector<float_range>& floats)
-{
-    return check_distinct_ranges(source_strings, [text](const byte_range & r)
-    {
-        const unsigned char* const b = text + r.off;
-        return scan_string_run(b, b + r.len) == b + r.len;
-    })
-    && check_distinct_ranges(decoded_strings, [arena](const byte_range & r)
-    {
-        return valid_utf8_prefix(arena + r.off, r.len) == r.len;
-    })
-    && check_float_ranges(floats, text);
-}
-
-/// Check the nodes of a loaded image against its text and decoded strings:
-/// kinds, flags, and `extra`; extents and element counts of arrays and
-/// objects; keys; bounds; string contents (source strings as the parser
-/// leaves them: no quotes, backslashes, or control characters; all strings
-/// valid UTF-8); and number tokens.
-///
-/// The structure and the bounds are checked node by node. The contents of
-/// strings and of float tokens are checked afterwards, once for each distinct
-/// range (see check_distinct_ranges), so that the full check is linear in the
-/// size of the image plus the sorting of the ranges, and not in the number of
-/// nodes times the size of the text.
-inline bool check_image(const node* nodes, std::size_t count, const unsigned char* text, std::size_t text_size,
-                        const unsigned char* arena, std::size_t arena_size, bool full)
-{
-    struct frame
-    {
-        std::size_t end;
-        std::uint32_t len;
-        std::uint32_t seen;
-        bool object;
-        bool expect_key;
-    };
-    std::vector<frame> stack;
-    std::vector<byte_range> source_strings;
-    std::vector<byte_range> decoded_strings;
-    std::vector<float_range> floats;
-    const auto check_string = [&](const node & n) -> bool
-    {
-        if ((n.flags & ~node_flags::escaped) != 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)
-        {
-            return false;
-        }
-        if (full && n.len != 0)
-        {
-            (decoded ? decoded_strings : source_strings).push_back(byte_range{n.off, n.len});
-        }
-        return true;
-    };
-    // bounds of a number token; the recorded digit layout must lie within it
-    const auto number_in_bounds = [&](const node & n) -> bool
-    {
-        const std::size_t len = number_length(n);
-        if (len == 0 || n.off > text_size || len > text_size - n.off)
-        {
-            return false;
-        }
-        if (n.kind != static_cast<std::uint8_t>(value_t::number_float))
-        {
-            return (n.extra >> 8u) == 0;
-        }
-        // float_value() reads the sign, the integer digits, and the point and
-        // fraction digits the layout records (a layout of more than 19 digits
-        // means the general conversion, which stays within the token)
-        const std::size_t int_digits = n.extra & 0xFFu;
-        const std::size_t frac_digits = n.extra >> 8u;
-        const std::size_t need = (text[n.off] == '-' ? 1u : 0u) + int_digits + (frac_digits != 0 ? frac_digits + 1 : 0);
-        return int_digits + frac_digits > 19 || need <= len;
-    };
-    std::size_t i = 0;
-    for (;;)
-    {
-        // close finished arrays and objects
-        while (!stack.empty() && i == stack.back().end)
-        {
-            const frame f = stack.back();
-            if (f.seen != f.len || (f.object && !f.expect_key))
-            {
-                return false;
-            }
-            stack.pop_back();
-            if (!stack.empty())
-            {
-                ++stack.back().seen;
-                stack.back().expect_key = true;
-            }
-        }
-        if (i == count)
-        {
-            return stack.empty() && (!full || check_contents(text, arena, source_strings, decoded_strings, floats));
-        }
-        if (i != 0 && stack.empty())
-        {
-            return false; // nodes after the root
-        }
-        const node& n = nodes[i];
-        if (!stack.empty() && stack.back().object && stack.back().expect_key)
-        {
-            if (n.kind != static_cast<std::uint8_t>(value_t::string) || !check_string(n))
-            {
-                return false;
-            }
-            stack.back().expect_key = false;
-            ++i;
-            continue;
-        }
-        bool complete = true;
-        switch (static_cast<value_t>(n.kind))
-        {
-            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)
-                {
-                    return false;
-                }
-                break;
-            case value_t::boolean:
-                if ((n.flags & ~node_flags::is_true) != 0 || n.extra != 0 || n.off > text_size)
-                {
-                    return false;
-                }
-                break;
-            case value_t::string:
-                if (!check_string(n))
-                {
-                    return false;
-                }
-                break;
-            case value_t::number_integer:
-            case value_t::number_unsigned:
-            case value_t::number_float:
-                if (n.flags != 0 || !number_in_bounds(n))
-                {
-                    return false;
-                }
-                if (full)
-                {
-                    // (the contents of float tokens are checked later; the token of an
-                    // integer has at most 256 characters)
-                    if (n.kind == static_cast<std::uint8_t>(value_t::number_float))
-                    {
-                        floats.push_back(float_range{n.off, n.len, n.extra});
-                    }
-                    else if (!check_integer(n, text))
-                    {
-                        return false;
-                    }
-                }
-                break;
-            case value_t::array:
-            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)
-                {
-                    return false;
-                }
-                stack.push_back(frame{i + n.next, n.len, 0, n.kind == static_cast<std::uint8_t>(value_t::object), true});
-                complete = false;
-                break;
-            }
-            case value_t::binary:
-            case value_t::discarded:
-            default:
-                return false;
-        }
-        ++i;
-        if (complete && !stack.empty())
-        {
-            ++stack.back().seen;
-            stack.back().expect_key = true;
-        }
-    }
-}
-
-[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_invalid_image(const char* what)
-{
-    throw_parse_error(116, concat("invalid json_document image: ", what));
-}
-
-/// Read an image into d. The text and the decoded strings stay in the image;
-/// the nodes are copied (so that they are aligned, and edits can change them).
-inline void load_image(document_data& d, const std::uint8_t* image, std::size_t size, image_check check)
-{
-#if !NLOHMANN_VIEW_LITTLE_ENDIAN
-    throw_type_error(320, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
-#endif
-    if (image == nullptr || size < sizeof(image_header))
-    {
-        throw_invalid_image("too short");
-    }
-    image_header h{};
-    std::memcpy(&h, image, sizeof(h));
-    // (the reserved fields are for later versions)
-    if (std::memcmp(h.magic.data(), "NJVI", 4) != 0 || h.version != image_version
-            || (h.reserved[0] | h.reserved[1] | h.reserved[2] | h.reserved[3]) != 0)
-    {
-        throw_invalid_image("unknown format");
-    }
-    const std::size_t room = size - sizeof(h);
-    if (h.node_count == 0 || h.node_count > room / sizeof(node) || h.node_count >= image_limit || h.text_size >= image_limit || h.arena_size >= image_limit)
-    {
-        throw_invalid_image("sizes out of range");
-    }
-    const auto count = static_cast<std::size_t>(h.node_count);
-    const auto text_size = static_cast<std::size_t>(h.text_size);
-    const auto arena_size = static_cast<std::size_t>(h.arena_size);
-    const std::size_t text_at = sizeof(h) + (count * sizeof(node));
-    // the text, a NUL, the decoded strings, a NUL, and nothing after them
-    if (size - text_at < 2 || text_size > size - text_at - 2 || arena_size != size - text_at - text_size - 2
-            || image[text_at + text_size] != 0 || image[size - 1] != 0)
-    {
-        throw_invalid_image("sizes out of range");
-    }
-
-    d.discarded = true;
-    d.edits.reset();
-    d.base[2] = nullptr;
-    d.owned.clear();
-    if (d.owned_image.empty() || image != d.owned_image.data())
-    {
-        d.owned_image.clear();
-    }
-    d.arena.clear();
-    d.indexes.clear();
-    d.index_slots.clear();
-    d.large_objects.clear();
-    d.node_count = 0;
-    d.reserve(count);
-    std::memcpy(d.nodes, image + sizeof(h), count * sizeof(node));
-    d.node_count = count;
-    const std::uint8_t* const text = image + text_at;
-    const std::uint8_t* const arena = text + text_size + 1;
-    d.src = reinterpret_cast<const char*>(text); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-    d.size = text_size;
-    d.base[0] = d.src;
-    d.base[1] = reinterpret_cast<const char*>(arena); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-    d.arena_size = arena_size;
-    if (check != image_check::none && !check_image(d.nodes, count, text, text_size, arena, arena_size, check == image_check::full))
-    {
-        throw_invalid_image("the check failed");
-    }
-    // the hash indexes of large objects, as after parsing
-    for (std::size_t i = 0; i < count; ++i)
-    {
-        const node& n = d.nodes[i];
-        if (n.kind == static_cast<std::uint8_t>(value_t::object) && n.len >= document_data::index_min_members)
-        {
-            d.large_objects.push_back(static_cast<std::uint32_t>(i));
-        }
-    }
-    build_object_indexes(d);
-    std::vector<std::uint32_t>().swap(d.large_objects); // (only needed while building)
-    d.discarded = false;
-}
-
-}  // namespace view
-}  // namespace detail
-NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/detail/view/number.hpp

@@ -26,79 +26,43 @@ namespace detail
 namespace view
 {
 
-/*!
-@brief locate the decimal point and the end of the mantissa of a float token
-
-Also checks that the token is a JSON number. Tokens of the parser and of edits
-always are; an image loaded with image_check::bounds can hold any bytes, which
-must not reach the conversion (it expects a well-formed token).
-*/
-inline bool float_token_layout(const char* first, const char* last, std::size_t& dot, std::size_t& mantissa_end) noexcept
-{
-    const auto digit = [last](const char* q)
-    {
-        return q != last && is_digit(static_cast<unsigned char>(*q));
-    };
-    const char* p = first;
-    p += (p != last && *p == '-') ? 1 : 0;
-    if (!digit(p) || (*p == '0' && digit(p + 1)))
-    {
-        return false;
-    }
-    do
-    {
-        ++p;
-    }
-    while (digit(p));
-    dot = std::string::npos;
-    if (p != last && *p == '.')
-    {
-        dot = static_cast<std::size_t>(p - first);
-        if (!digit(++p))
-        {
-            return false;
-        }
-        do
-        {
-            ++p;
-        }
-        while (digit(p));
-    }
-    mantissa_end = static_cast<std::size_t>(p - first);
-    if (p != last && (*p == 'e' || *p == 'E'))
-    {
-        ++p;
-        p += (p != last && (*p == '+' || *p == '-')) ? 1 : 0;
-        if (!digit(p))
-        {
-            return false;
-        }
-        do
-        {
-            ++p;
-        }
-        while (digit(p));
-    }
-    return p == last;
-}
-
 /*!
 @brief the value of the float token of a node, as parse() converts it
 
 Uses the lexer's conversion (detail::convert_float), so that the values are
 bit-identical to parse(): float and double are converted without allocation
-and independent of the locale. A token that is not a JSON number (only in a
-damaged image loaded with image_check::bounds) yields 0.
+and independent of the locale. The digit layout recorded while parsing locates
+the decimal point and the exponent without scanning the token.
 */
 template<typename FloatType>
 NLOHMANN_VIEW_NOINLINE FloatType float_value(const char* first, const node& n)
 {
     const char* const last = first + n.len;
-    std::size_t dot = 0;
-    std::size_t mantissa_end = 0;
-    if (NLOHMANN_VIEW_UNLIKELY(!float_token_layout(first, last, dot, mantissa_end)))
+    const std::size_t neg = first[0] == '-' ? 1 : 0;
+    const std::size_t int_digits = n.extra & 0xFFu;
+    const std::size_t frac_digits = n.extra >> 8u;
+    std::size_t dot = std::string::npos;
+    std::size_t mantissa_end = n.len;
+    if (int_digits != 255 && frac_digits != 255)
     {
-        return FloatType{};
+        dot = frac_digits != 0 ? neg + int_digits : std::string::npos;
+        mantissa_end = neg + int_digits + (frac_digits != 0 ? 1 + frac_digits : 0);
+    }
+    else
+    {
+        // more digits than the layout records: locate them
+        for (std::size_t i = 0; i < n.len; ++i)
+        {
+            if (first[i] == '.')
+            {
+                dot = i;
+            }
+            else if (first[i] == 'e' || first[i] == 'E')
+            {
+                mantissa_end = i;
+                break;
+            }
+        }
     }
     return convert_float<FloatType>(first, last, dot, mantissa_end);
 }
@@ -129,20 +93,16 @@ NLOHMANN_VIEW_ALWAYS_INLINE float_significand layout_decimal(const unsigned char
     }
     if (p != e)
     {
-        // [eE][+-]digits; huge exponents saturate (the parser rejected
-        // overflow). The token is not read beyond e, and the digits are taken
-        // as unsigned, so that a token that is not well-formed (a damaged
-        // image loaded with image_check::bounds) yields a wrong value, but no
-        // overflow.
+        // [eE][+-]digits; huge exponents saturate (the parser rejected overflow)
         ++p;
-        const bool exp_negative = p != e && *p == '-';
-        p += (p != e && (*p == '-' || *p == '+')) ? 1 : 0;
+        const bool exp_negative = *p == '-';
+        p += (*p == '-' || *p == '+') ? 1 : 0;
         std::int64_t exp_value = 0;
         for (; p != e; ++p)
         {
             if (exp_value < 0x10000000)
             {
-                exp_value = (exp_value * 10) + static_cast<unsigned char>(*p - '0');
+                exp_value = (exp_value * 10) + (*p - '0');
             }
         }
         q += exp_negative ? -exp_value : exp_value;

include/nlohmann/detail/view/scan.hpp

@@ -175,7 +175,32 @@ NLOHMANN_VIEW_ALWAYS_INLINE const unsigned char* skip_digits(const unsigned char
 /// powers of ten up to 10^19 as integers
 inline std::uint64_t int_pow10(unsigned k) noexcept
 {
-    return ::nlohmann::detail::dtoa_impl::powers_of_ten()[k];
+    static const std::array<std::uint64_t, 20> table =
+    {
+        {
+            1u,
+            10u,
+            100u,
+            1000u,
+            10000u,
+            100000u,
+            1000000u,
+            10000000u,
+            100000000u,
+            1000000000u,
+            10000000000u,
+            100000000000u,
+            1000000000000u,
+            10000000000000u,
+            100000000000000u,
+            1000000000000000u,
+            10000000000000000u,
+            100000000000000000u,
+            1000000000000000000u,
+            10000000000000000000u
+        }
+    };
+    return table[k];
 }
 
 /// value of 0 < k < 8 digits at p in one step if [p, p + 8) lies below

include/nlohmann/detail/view/serializer.hpp

@@ -31,11 +31,7 @@ namespace view
 {
 
 /// append-only output buffer: writes through a raw pointer into a string that
-/// is resized ahead, and trimmed by finish(). The estimate is reserved, and the
-/// string grows in steps of 64 KiB within it: resize() fills the new bytes
-/// with zeros (before C++23, a string cannot grow without), and a small step
-/// is filled while the writer is about to use it, in the cache, instead of
-/// filling the whole estimate in memory first.
+/// is resized ahead, and trimmed by finish()
 template<typename StringType>
 class output_buffer
 {
@@ -87,46 +83,17 @@ class output_buffer
         m_pos += n;
     }
 
-    /// the write position and the end of the writable space, for a writer
-    /// that keeps the position in a local variable (set_cursor() hands it back)
-    char* cursor() const noexcept
-    {
-        return m_pos;
-    }
-
-    char* limit() const noexcept
-    {
-        return m_end;
-    }
-
-    void set_cursor(char* p) noexcept
-    {
-        m_pos = p;
-    }
-
   private:
-    /// the size of a growth step
-    static constexpr std::size_t step = 0x10000;
-
     static StringType& sized(StringType& out, std::size_t estimate)
     {
-        out.reserve(estimate);
-        out.resize(detail::clamp(estimate, std::size_t{64}, step));
+        out.resize((std::max)(estimate, static_cast<std::size_t>(64)));
         return out;
     }
 
     NLOHMANN_VIEW_NOINLINE void grow(std::size_t n)
     {
         const auto used = static_cast<std::size_t>(m_pos - m_out.data());
-        // (a step does not go beyond the reserved estimate, so that a good
-        // estimate is never copied to a larger allocation; not a clamp: the
-        // lower bound used + n + 256 can exceed capacity(), and then it must win)
-        const std::size_t size = (std::max)((std::min)(m_out.size() + step, m_out.capacity()), used + n + 256);
-        if (size > m_out.capacity())
-        {
-            m_out.reserve((std::max)(m_out.capacity() * 2, size));
-        }
-        m_out.resize(size);
+        m_out.resize((std::max)(m_out.size() * 2, used + n + 256));
         m_pos = &m_out[0] + used;
         m_end = &m_out[0] + m_out.size();
     }
@@ -136,145 +103,6 @@ class output_buffer
     char* m_end;
 };
 
-/// The length of the run at s that dump() writes unchanged without
-/// ensure_ascii: all bytes but quotes, backslashes, and control characters.
-/// Unlike detail::string_bulk_run(), non-ASCII bytes are not validated: the
-/// strings of a document are valid UTF-8 (a damaged image loaded with
-/// image_check::bounds can have others, which are then written unchanged).
-inline std::size_t plain_output_run(const unsigned char* s, std::size_t n) noexcept
-{
-    constexpr std::uint64_t ones = 0x0101010101010101ull;
-    constexpr std::uint64_t high = 0x8080808080808080ull;
-    std::size_t i = 0;
-    for (; i + 8 <= n; i += 8)
-    {
-        const std::uint64_t v = read_eight_bytes(s + i);
-        const std::uint64_t q = v ^ 0x2222222222222222ull; // '"'
-        const std::uint64_t b = v ^ 0x5C5C5C5C5C5C5C5Cull; // '\\'
-        const std::uint64_t stop = (((q - ones) & ~q) | ((b - ones) & ~b) | ((v - 0x2020202020202020ull) & ~v)) & high;
-        if (stop != 0)
-        {
-            // the lowest flagged byte is the first stop: borrows only flag bytes above a true one
-            return i + (static_cast<std::size_t>(count_trailing_zeros(stop)) / 8);
-        }
-    }
-    for (; i < n; ++i)
-    {
-        if (s[i] == '"' || s[i] == '\\' || s[i] < 0x20)
-        {
-            return i;
-        }
-    }
-    return n;
-}
-
-/// Whether dump() with ensure_ascii writes the string at s unchanged, for a
-/// string of the source without escape sequences (which has no quote,
-/// backslash, or control character): no byte is DEL (0x7F) or above. Adding 1
-/// to each byte sets its high bit exactly for 0x7F, and a carry into the next
-/// byte only comes from 0xFF, whose own high bit is set anyway.
-inline bool is_ascii_without_delete(const char* s, std::size_t n) noexcept
-{
-    constexpr std::uint64_t ones = 0x0101010101010101ull;
-    constexpr std::uint64_t high = 0x8080808080808080ull;
-    std::size_t i = 0;
-    for (; i + 8 <= n; i += 8)
-    {
-        const std::uint64_t v = read_eight_bytes(s + i);
-        if (((v | (v + ones)) & high) != 0)
-        {
-            return false;
-        }
-    }
-    for (; i < n; ++i)
-    {
-        if (static_cast<unsigned char>(s[i]) >= 0x7F)
-        {
-            return false;
-        }
-    }
-    return true;
-}
-
-/// A stack that starts in a buffer of the caller (a local array) and moves to
-/// the heap (a vector of the caller) only when that is full, so that dumps of
-/// shallow documents need no allocation. The top is a pointer, as in
-/// std::vector. grow() is static and out of line: it gets the vector and the
-/// used range and returns the new storage, so the address of the stack never
-/// reaches a call. Otherwise the compiler would have to keep the three
-/// pointers in memory and load and store them on every push_back() and
-/// pop_back(), not just when growing.
-template<typename T>
-class small_stack
-{
-  public:
-    small_stack(T* buffer, std::size_t capacity, std::vector<T>& heap) noexcept
-        : m_begin(buffer), m_top(buffer), m_end(buffer + capacity), m_heap(heap)
-    {}
-    small_stack(const small_stack&) = delete;
-    small_stack(small_stack&&) = delete;
-    small_stack& operator=(const small_stack&) = delete;
-    small_stack& operator=(small_stack&&) = delete;
-    ~small_stack() = default;
-
-    NLOHMANN_VIEW_ALWAYS_INLINE void push_back(const T& x)
-    {
-        if (NLOHMANN_VIEW_UNLIKELY(m_top == m_end))
-        {
-            const std::size_t used = size();
-            const std::size_t capacity = 2 * static_cast<std::size_t>(m_end - m_begin);
-            m_begin = grow(m_heap, m_begin, used, capacity);
-            m_top = m_begin + used;
-            m_end = m_begin + capacity;
-        }
-        *m_top++ = x;
-    }
-
-    NLOHMANN_VIEW_ALWAYS_INLINE T& back() noexcept
-    {
-        return m_top[-1];
-    }
-
-    NLOHMANN_VIEW_ALWAYS_INLINE void pop_back() noexcept
-    {
-        --m_top;
-    }
-
-    NLOHMANN_VIEW_ALWAYS_INLINE bool empty() const noexcept
-    {
-        return m_top == m_begin;
-    }
-
-    NLOHMANN_VIEW_ALWAYS_INLINE std::size_t size() const noexcept
-    {
-        return static_cast<std::size_t>(m_top - m_begin);
-    }
-
-  private:
-    /// the used entries moved to heap storage of the given capacity
-    NLOHMANN_VIEW_NOINLINE static T* grow(std::vector<T>& heap, const T* begin, std::size_t used, std::size_t capacity)
-    {
-        std::vector<T> bigger(capacity);
-        std::copy(begin, begin + used, bigger.begin());
-        heap.swap(bigger);
-        return heap.data();
-    }
-
-    T* m_begin;
-    T* m_top;
-    T* m_end;
-    std::vector<T>& m_heap;
-};
-
-/// a string literal at w, without its terminating NUL (after room())
-/// @return a pointer past it
-template<std::size_t N>
-NLOHMANN_VIEW_ALWAYS_INLINE char* put_literal(char* w, const char (&s)[N]) noexcept // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
-{
-    std::memcpy(w, s, N - 1);
-    return w + N - 1;
-}
-
 /// how the view's dump() writes a value
 struct dump_style
 {
@@ -301,8 +129,6 @@ class view_serializer
     using nav = navigation<Editable>;
     using string_t = typename BasicJsonType::string_t;
     using number_float_t = typename BasicJsonType::number_float_t;
-    /// doubles that are IEEE 754 binary64 are written from their bits (Zmij)
-    using fast_double = std::integral_constant < bool, std::is_same<number_float_t, double>::value && ::nlohmann::detail::dtoa_impl::is_binary64<double>::value >;
 
   public:
     view_serializer(const document_data& d, string_t& out, std::size_t estimate, const dump_style& style)
@@ -311,22 +137,6 @@ class view_serializer
 
     void dump(const node* root)
     {
-        if (!m_style.pretty)
-        {
-            if (m_style.ensure_ascii)
-            {
-                dump_compact_ascii(root);
-            }
-            else if (m_style.source_numbers)
-            {
-                dump_compact<true, false>(root);
-            }
-            else
-            {
-                dump_compact<false, false>(root);
-            }
-            return;
-        }
         struct frame
         {
             const node* pos; ///< next element, or key of the next member
@@ -334,9 +144,7 @@ class view_serializer
             bool object;
             bool first;  ///< nothing written yet
         };
-        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);
+        std::vector<frame> stack;
         const node* n = root;
         for (;;)
         {
@@ -407,337 +215,6 @@ class view_serializer
     }
 
   private:
-    /// a string that is not a plain string of the source (decoded, or written
-    /// by an edit), without ensure_ascii: runs without characters to escape
-    /// are copied
-    NLOHMANN_VIEW_NOINLINE void write_decoded(const node& n)
-    {
-        const auto* const s = reinterpret_cast<const unsigned char*>(m_doc.str(n)); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-        m_out.put('"');
-        for (std::size_t i = 0; i < n.len;)
-        {
-            const std::size_t run = plain_output_run(s + i, n.len - i);
-            if (run != 0)
-            {
-                m_out.put(reinterpret_cast<const char*>(s + i), run); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-                i += run;
-                continue;
-            }
-            write_codepoint<false>(s[i], s + i, 1); // a quote, a backslash, or a control character
-            ++i;
-        }
-        m_out.put('"');
-    }
-
-    /// dump_compact() with ensure_ascii, out of line: the walk without it is
-    /// faster when it is not merged with this one into dump()
-    NLOHMANN_VIEW_NOINLINE void dump_compact_ascii(const node* root)
-    {
-        if (m_style.source_numbers)
-        {
-            dump_compact<true, true>(root);
-        }
-        else
-        {
-            dump_compact<false, true>(root);
-        }
-    }
-
-    /// whether dump_compact() copies a string or key from the source: one of
-    /// the source, and with ensure_ascii one without bytes >= 0x7F (an overload
-    /// each, so that the walk without ensure_ascii is compiled exactly as
-    /// before: with GCC, a condition that only folds away later changed its
-    /// block layout and made it 4-6% slower)
-    static bool copied(const node& n, const char* /*src*/, std::false_type /*ensure_ascii*/) noexcept
-    {
-        return (n.flags & node_flags::storage) == 0;
-    }
-
-    static bool copied(const node& n, const char* src, std::true_type /*ensure_ascii*/) noexcept
-    {
-        return (n.flags & node_flags::storage) == 0 && is_ascii_without_delete(src + n.off, n.len);
-    }
-
-    /// a string with ensure_ascii (dump_compact()), out of line
-    NLOHMANN_VIEW_NOINLINE void write_ascii_string(const node& n)
-    {
-        write_string(n);
-    }
-
-    /// the copies of dump_compact() that are not fixed-size moves (long
-    /// strings, or near the end of the source); out of line, so that the
-    /// compiler does not merge the fixed-size moves into this call
-    NLOHMANN_VIEW_NOINLINE static void copy_long(char* to, const char* from, std::size_t n) noexcept
-    {
-        std::memcpy(to, from, n);
-    }
-
-    /// a compile-time option as a runtime condition: testing the template
-    /// argument directly makes a condition like `Editable && c` constant when
-    /// the option is off, which MSVC reports as C4127
-    static NLOHMANN_VIEW_ALWAYS_INLINE bool enabled(bool option) noexcept
-    {
-        return option;
-    }
-
-    /*!
-    @brief the compact output (the default dump(), or with ensure_ascii)
-
-    The same walk as dump(), with the write position in a local variable
-    (stores through char pointers would otherwise force a reload of the
-    buffer's members after each one), and with strings and number tokens of
-    the source copied by fixed-size moves of 32 bytes where the source has
-    that many bytes left, instead of a library call per token. The buffer
-    keeps 64 bytes of slack for the overshoot. With ensure_ascii (Ascii), a
-    string of the source is copied only if it has no byte >= 0x7F (see
-    is_ascii_without_delete()); any other string is written by write_string().
-    */
-    template<bool SourceNumbers, bool Ascii>
-    void dump_compact(const node* root)
-    {
-        struct frame
-        {
-            const node* pos; ///< (editable documents) next element, or key of the next member
-            const node* end;
-            bool object;
-        };
-        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);
-        const char* const src = m_doc.src;
-        const char* const src_end = src + m_doc.size;
-        char* w = m_out.cursor();
-        char* lim = m_out.limit();
-        // room for n bytes and the slack
-        const auto room = [&](std::size_t n)
-        {
-            if (NLOHMANN_VIEW_UNLIKELY(static_cast<std::size_t>(lim - w) < n + 64))
-            {
-                m_out.set_cursor(w);
-                m_out.reserve(n + 64);
-                w = m_out.cursor();
-                lim = m_out.limit();
-            }
-        };
-        // copy n bytes of the source (after room(n))
-        const auto copy = [&](const char* from, std::size_t n)
-        {
-            if (n <= 32 && static_cast<std::size_t>(src_end - from) >= 32)
-            {
-                std::memcpy(w, from, 32);
-            }
-            else if (n <= 256 && static_cast<std::size_t>(src_end - from) >= n + 32)
-            {
-                for (std::size_t i = 0; i < n; i += 32)
-                {
-                    std::memcpy(w + i, from + i, 32);
-                }
-            }
-            else
-            {
-                copy_long(w, from, n);
-            }
-            w += n;
-        };
-        // a string that is not a plain string of the source (out of line, so
-        // that the cursor stays in a register here)
-        const auto escaped = [&](const node & n)
-        {
-            m_out.set_cursor(w);
-            if (enabled(Ascii))
-            {
-                write_ascii_string(n);
-            }
-            else
-            {
-                write_decoded(n);
-            }
-            w = m_out.cursor();
-            lim = m_out.limit();
-        };
-
-        // Read-only documents: the elements of a container follow it in the
-        // node array, so the walk goes through the array in order, and a
-        // frame only needs the end of its container. Editable documents: the
-        // elements of a moved container live elsewhere, so a frame keeps the
-        // position of the next element (see navigation).
-        // The innermost open container is kept in registers (cur; end ==
-        // nullptr: none), the stack holds the ones around it.
-        frame cur{nullptr, nullptr, false};
-        const node* n = root;
-        for (;;)
-        {
-            // write the value at n (read-only documents: and advance n)
-            bool opened = false;
-            // 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))
-            {
-                case value_t::string:
-                    if (copied(*n, src, std::integral_constant<bool, Ascii>()))
-                    {
-                        room(n->len + 2);
-                        *w++ = '"';
-                        copy(src + n->off, n->len);
-                        *w++ = '"';
-                    }
-                    else
-                    {
-                        escaped(*n);
-                    }
-                    break;
-                case value_t::number_integer:
-                case value_t::number_unsigned:
-                {
-                    const std::uint32_t len = number_length(*n);
-                    room(len);
-                    if (enabled(Editable) && (n->flags & node_flags::storage) != 0)
-                    {
-                        copy_long(w, m_doc.str(*n), len); // a canonical token written by an edit
-                        w += len;
-                        break;
-                    }
-                    const char* const token = src + n->off;
-                    if (!enabled(SourceNumbers) && NLOHMANN_VIEW_UNLIKELY(len == 2 && token[0] == '-' && token[1] == '0'))
-                    {
-                        *w++ = '0'; // parse() reads -0 as the integer 0
-                    }
-                    else
-                    {
-                        copy(token, len);
-                    }
-                    break;
-                }
-                case value_t::number_float:
-                    if (enabled(SourceNumbers) && (n->flags & node_flags::storage) != node_flags::edited)
-                    {
-                        room(n->len);
-                        copy(src + n->off, n->len);
-                    }
-                    else if (enabled(fast_double::value))
-                    {
-                        room(64);
-                        w = write_double_at(w, *n);
-                    }
-                    else
-                    {
-                        m_out.set_cursor(w);
-                        write_float_node(*n);
-                        w = m_out.cursor();
-                        lim = m_out.limit();
-                    }
-                    break;
-                case value_t::boolean:
-                    room(8);
-                    if ((n->flags & node_flags::is_true) != 0)
-                    {
-                        w = put_literal(w, "true");
-                    }
-                    else
-                    {
-                        w = put_literal(w, "false");
-                    }
-                    break;
-                case value_t::object:
-                case value_t::array:
-                {
-                    const bool object = n->kind == static_cast<std::uint8_t>(value_t::object);
-                    room(8);
-                    if (n->len == 0)
-                    {
-                        w = object ? put_literal(w, "{}") : put_literal(w, "[]");
-                    }
-                    else
-                    {
-                        *w++ = object ? '{' : '[';
-                        stack.push_back(cur);
-                        if (Editable)
-                        {
-                            cur = frame{nav::first(m_doc, n), nav::end(m_doc, n), object};
-                        }
-                        else
-                        {
-                            cur = frame{nullptr, n + n->next, object};
-                        }
-                        opened = true;
-                    }
-                    break;
-                }
-                case value_t::null:
-                    room(8);
-                    w = put_literal(w, "null");
-                    break;
-                case value_t::binary:    // LCOV_EXCL_LINE (not in a document)
-                case value_t::discarded: // LCOV_EXCL_LINE
-                default:                 // LCOV_EXCL_LINE
-                    break;               // LCOV_EXCL_LINE
-            }
-            if (!Editable)
-            {
-                ++n; // the next node: the first element of an opened container, or the node after a scalar
-            }
-
-            // go to the next value: close finished containers, then separate
-            // (a container just opened has an element)
-            if (!opened)
-            {
-                for (;;)
-                {
-                    if (cur.end == nullptr)
-                    {
-                        m_out.set_cursor(w);
-                        m_out.finish();
-                        return;
-                    }
-                    if ((Editable ? cur.pos : n) != cur.end)
-                    {
-                        break;
-                    }
-                    room(1);
-                    *w++ = cur.object ? '}' : ']';
-                    cur = stack.back();
-                    stack.pop_back();
-                }
-                room(1);
-                *w++ = ',';
-            }
-            const node* const at = Editable ? cur.pos : n;
-            if (cur.object)
-            {
-                const node& key = *at;
-                if (copied(key, src, std::integral_constant<bool, Ascii>()))
-                {
-                    room(key.len + 3);
-                    *w++ = '"';
-                    copy(src + key.off, key.len);
-                    w[0] = '"';
-                    w[1] = ':';
-                    w += 2;
-                }
-                else
-                {
-                    escaped(key);
-                    room(1);
-                    *w++ = ':';
-                }
-                if (Editable)
-                {
-                    n = nav::value(at + 1);
-                    cur.pos = document_data::after(at + 1);
-                }
-                else
-                {
-                    ++n;
-                }
-            }
-            else if (Editable)
-            {
-                n = nav::value(at);
-                cur.pos = document_data::after(at);
-            }
-        }
-    }
-
     void newline(std::size_t level)
     {
         if (m_style.pretty)
@@ -789,7 +266,7 @@ class view_serializer
                 }
                 else
                 {
-                    write_float_node(n);
+                    write_float(float_value<number_float_t>(m_doc, n));
                 }
                 break;
             case value_t::object:    // LCOV_EXCL_LINE (containers are written by dump())
@@ -801,87 +278,6 @@ class view_serializer
         }
     }
 
-    /// a float node as dump() writes it
-    void write_float_node(const node& n)
-    {
-        write_float_node(n, fast_double {});
-    }
-
-    void write_float_node(const node& n, std::false_type /*other*/)
-    {
-        write_float(float_value<number_float_t>(m_doc, n));
-    }
-
-    void write_float_node(const node& n, std::true_type /*double*/)
-    {
-        m_out.reserve(64);
-        m_out.set_cursor(write_double_at(m_out.cursor(), n));
-    }
-
-    /*!
-    @brief (doubles) the float at n as dump() writes it, at w (64 bytes of room)
-
-    A token of at most 15 significant digits is written from its digits,
-    without a conversion: two decimals of at most 15 digits are farther
-    apart than the rounding interval of a (normal) double (the argument
-    behind DBL_DIG), so the token's digits are the shortest ones of its
-    double, which the library's conversion writes (Zmij). Other tokens are
-    converted from the digits already read.
-    */
-    char* write_double_at(char* w, const node& n)
-    {
-        const unsigned int_digits = n.extra & 0xFFu;
-        const unsigned frac_digits = n.extra >> 8u;
-        if ((n.flags & node_flags::storage) != node_flags::edited && int_digits + frac_digits <= 19)
-        {
-            const auto* const first = reinterpret_cast<const unsigned char*>(m_doc.src + n.off); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-            const float_significand d = layout_decimal(first, first + n.len, int_digits, frac_digits, reinterpret_cast<const unsigned char*>(m_doc.src + m_doc.size)); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-            // (the exponent keeps the value far from subnormals and overflow)
-            if (d.w != 0 && d.w < 1000000000000000u && d.exponent >= -290 && d.exponent <= 290)
-            {
-                *w = '-';
-                w += d.negative ? 1 : 0;
-                // (without leading zeros, all digits of the token count; the
-                // check also keeps an image that was only checked for bounds,
-                // whose token may not be made of digits, from the counted
-                // overload)
-                const auto& powers = ::nlohmann::detail::dtoa_impl::powers_of_ten();
-                const unsigned count = int_digits + frac_digits;
-                return count - 1u < 15u && d.w >= powers[count - 1u] && d.w < powers[count]
-                       ? ::nlohmann::detail::dtoa_impl::write_short_decimal(w, d.w, static_cast<int>(count), static_cast<int>(d.exponent))
-                       : ::nlohmann::detail::dtoa_impl::write_short_decimal(w, d.w, static_cast<int>(d.exponent));
-            }
-            return write_double_value_at(w, decimal_to_float<double>(d)); // (without reading the token again)
-        }
-        return write_double_value_at(w, static_cast<double>(float_value<number_float_t>(m_doc, n)));
-    }
-
-    /// n bytes of text at w
-    static char* write_text_at(char* w, const char* text, std::size_t n) noexcept
-    {
-        std::memcpy(w, text, n);
-        return w + n;
-    }
-
-    /// a double as dump() writes it, at w (64 bytes of room)
-    static char* write_double_value_at(char* w, double x)
-    {
-        // (from the bits: without the checks of to_chars())
-        auto bits = bit_cast<std::uint64_t>(x);
-        if (NLOHMANN_VIEW_UNLIKELY((bits & 0x7FF0000000000000u) == 0x7FF0000000000000u))
-        {
-            return write_text_at(w, "null", 4);
-        }
-        *w = '-';
-        w += bits >> 63u;
-        bits &= ~(std::uint64_t{1} << 63u);
-        if (bits == 0)
-        {
-            return write_text_at(w, "0.0", 3);
-        }
-        return ::nlohmann::detail::dtoa_impl::write_shortest(w, ::nlohmann::detail::zmij::to_shortest(bits));
-    }
-
     /// as serializer::dump_float()
     void write_float(number_float_t x)
     {
@@ -915,10 +311,9 @@ class view_serializer
     {
         const char* const s = m_doc.str(n);
         m_out.put('"');
-        if ((n.flags & node_flags::storage) == 0 && (!m_style.ensure_ascii || is_ascii_without_delete(s, n.len)))
+        if ((n.flags & node_flags::storage) == 0 && !m_style.ensure_ascii)
         {
-            // a string of the source without escape sequences has nothing to
-            // escape (with ensure_ascii, if it is printable ASCII)
+            // a string of the source without escape sequences has nothing to escape
             m_out.put(s, n.len);
         }
         else if (m_style.ensure_ascii)
@@ -932,9 +327,7 @@ class view_serializer
         m_out.put('"');
     }
 
-    /// as serializer::dump_escaped(); strings of a document are valid UTF-8,
-    /// except in a damaged image loaded with image_check::bounds, for which
-    /// this throws what basic_json::dump() throws for the string
+    /// as serializer::dump_escaped() for valid UTF-8 (the view has no other)
     template<bool EnsureAscii>
     void write_escaped(const unsigned char* s, std::size_t n)
     {
@@ -958,13 +351,12 @@ class view_serializer
             }
             std::uint32_t codepoint = s[i];
             std::size_t len = 1;
-            if (codepoint >= 0x80)
+            if (codepoint >= 0xC0)
             {
-                len = validate_one_utf8(s + i, n - i);
-                if (NLOHMANN_VIEW_UNLIKELY(len == 0))
+                len = 2;
+                if (codepoint >= 0xE0)
                 {
-                    invalid_utf8(s, n);
-                    return;
+                    len = codepoint >= 0xF0 ? 4 : 3;
                 }
                 codepoint &= 0xFFu >> (len + 1);
                 for (std::size_t k = 1; k < len; ++k)
@@ -977,13 +369,6 @@ class view_serializer
         }
     }
 
-    /// throw what basic_json::dump() throws for a string that is not valid UTF-8
-    NLOHMANN_VIEW_NOINLINE static void invalid_utf8(const unsigned char* s, std::size_t n)
-    {
-        const string_t dumped = BasicJsonType(string_t(reinterpret_cast<const char*>(s), n)).dump(); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-        static_cast<void>(dumped);
-    }
-
     template<bool EnsureAscii>
     void write_codepoint(std::uint32_t codepoint, const unsigned char* bytes, std::size_t len)
     {

include/nlohmann/detail/view/simd.hpp

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

include/nlohmann/json.hpp

@@ -19,7 +19,6 @@
 #define INCLUDE_NLOHMANN_JSON_HPP_
 
 #include <algorithm> // all_of, find, for_each, none_of
-#include <array> // array
 #include <cmath> // isnan
 #include <cstddef> // nullptr_t, ptrdiff_t, size_t
 #include <cstdint> // uint8_t
@@ -6322,7 +6321,7 @@ public:
             const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
         std::vector<std::uint8_t> result;
-        result.reserve(detail::binary_initial_capacity(j));
+        result.reserve(detail::binary_reserve_hint(j));
         vector_writer(result, error_handler).write_cbor(j);
         return result;
     }
@@ -6332,9 +6331,7 @@ public:
     static void to_cbor(const basic_json& j, detail::output_adapter<std::uint8_t> o,
                         const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
-        binary_writer<std::uint8_t> writer(o, error_handler);
-        writer.write_cbor(j);
-        writer.flush();
+        binary_writer<std::uint8_t>(o, error_handler).write_cbor(j);
     }
 
     /// @brief create a CBOR serialization of a given JSON value
@@ -6342,9 +6339,7 @@ public:
     static void to_cbor(const basic_json& j, detail::output_adapter<char> o,
                         const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
-        binary_writer<char> writer(o, error_handler);
-        writer.write_cbor(j);
-        writer.flush();
+        binary_writer<char>(o, error_handler).write_cbor(j);
     }
 
     /// @brief create a MessagePack serialization of a given JSON value
@@ -6353,7 +6348,7 @@ public:
             const error_handler_t error_handler = error_handler_t::keep)
     {
         std::vector<std::uint8_t> result;
-        result.reserve(detail::binary_initial_capacity(j));
+        result.reserve(detail::binary_reserve_hint(j));
         vector_writer(result, error_handler).write_msgpack(j);
         return result;
     }
@@ -6363,9 +6358,7 @@ public:
     static void to_msgpack(const basic_json& j, detail::output_adapter<std::uint8_t> o,
                            const error_handler_t error_handler = error_handler_t::keep)
     {
-        binary_writer<std::uint8_t> writer(o, error_handler);
-        writer.write_msgpack(j);
-        writer.flush();
+        binary_writer<std::uint8_t>(o, error_handler).write_msgpack(j);
     }
 
     /// @brief create a MessagePack serialization of a given JSON value
@@ -6373,9 +6366,7 @@ public:
     static void to_msgpack(const basic_json& j, detail::output_adapter<char> o,
                            const error_handler_t error_handler = error_handler_t::keep)
     {
-        binary_writer<char> writer(o, error_handler);
-        writer.write_msgpack(j);
-        writer.flush();
+        binary_writer<char>(o, error_handler).write_msgpack(j);
     }
 
     /// @brief create a UBJSON serialization of a given JSON value
@@ -6386,7 +6377,7 @@ public:
             const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
         std::vector<std::uint8_t> result;
-        result.reserve(detail::binary_initial_capacity(j));
+        result.reserve(detail::binary_reserve_hint(j));
         vector_writer(result, error_handler).write_ubjson(j, use_size, use_type);
         return result;
     }
@@ -6397,9 +6388,7 @@ public:
                           const bool use_size = false, const bool use_type = false,
                           const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
-        binary_writer<std::uint8_t> writer(o, error_handler);
-        writer.write_ubjson(j, use_size, use_type);
-        writer.flush();
+        binary_writer<std::uint8_t>(o, error_handler).write_ubjson(j, use_size, use_type);
     }
 
     /// @brief create a UBJSON serialization of a given JSON value
@@ -6408,9 +6397,7 @@ public:
                           const bool use_size = false, const bool use_type = false,
                           const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
-        binary_writer<char> writer(o, error_handler);
-        writer.write_ubjson(j, use_size, use_type);
-        writer.flush();
+        binary_writer<char>(o, error_handler).write_ubjson(j, use_size, use_type);
     }
 
     /// @brief create a BJData serialization of a given JSON value
@@ -6422,7 +6409,7 @@ public:
             const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
         std::vector<std::uint8_t> result;
-        result.reserve(detail::binary_initial_capacity(j));
+        result.reserve(detail::binary_reserve_hint(j));
         vector_writer(result, error_handler).write_ubjson(j, use_size, use_type, true, true, version);
         return result;
     }
@@ -6434,9 +6421,7 @@ public:
                           const bjdata_version_t version = bjdata_version_t::draft2,
                           const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
-        binary_writer<std::uint8_t> writer(o, error_handler);
-        writer.write_ubjson(j, use_size, use_type, true, true, version);
-        writer.flush();
+        binary_writer<std::uint8_t>(o, error_handler).write_ubjson(j, use_size, use_type, true, true, version);
     }
 
     /// @brief create a BJData serialization of a given JSON value
@@ -6446,9 +6431,7 @@ public:
                           const bjdata_version_t version = bjdata_version_t::draft2,
                           const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
-        binary_writer<char> writer(o, error_handler);
-        writer.write_ubjson(j, use_size, use_type, true, true, version);
-        writer.flush();
+        binary_writer<char>(o, error_handler).write_ubjson(j, use_size, use_type, true, true, version);
     }
 
     /// @brief create a BSON serialization of a given JSON value
@@ -6457,7 +6440,7 @@ public:
             const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
         std::vector<std::uint8_t> result;
-        result.reserve(detail::binary_initial_capacity(j));
+        result.reserve(detail::binary_reserve_hint(j));
         vector_writer(result, error_handler).write_bson(j);
         return result;
     }
@@ -6467,9 +6450,7 @@ public:
     static void to_bson(const basic_json& j, detail::output_adapter<std::uint8_t> o,
                         const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
-        binary_writer<std::uint8_t> writer(o, error_handler);
-        writer.write_bson(j);
-        writer.flush();
+        binary_writer<std::uint8_t>(o, error_handler).write_bson(j);
     }
 
     /// @brief create a BSON serialization of a given JSON value
@@ -6477,9 +6458,7 @@ public:
     static void to_bson(const basic_json& j, detail::output_adapter<char> o,
                         const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
-        binary_writer<char> writer(o, error_handler);
-        writer.write_bson(j);
-        writer.flush();
+        binary_writer<char>(o, error_handler).write_bson(j);
     }
 
     /// @brief create a BON8 serialization of a given JSON value
@@ -6487,7 +6466,7 @@ public:
     static std::vector<std::uint8_t> to_bon8(const basic_json& j)
     {
         std::vector<std::uint8_t> result;
-        result.reserve(detail::binary_initial_capacity(j));
+        result.reserve(detail::binary_reserve_hint(j));
         vector_writer(result).write_bon8(j);
         return result;
     }
@@ -6496,18 +6475,14 @@ public:
     /// @sa https://json.nlohmann.me/api/basic_json/to_bon8/
     static void to_bon8(const basic_json& j, detail::output_adapter<std::uint8_t> o)
     {
-        binary_writer<std::uint8_t> writer(o);
-        writer.write_bon8(j);
-        writer.flush();
+        binary_writer<std::uint8_t>(o).write_bon8(j);
     }
 
     /// @brief create a BON8 serialization of a given JSON value
     /// @sa https://json.nlohmann.me/api/basic_json/to_bon8/
     static void to_bon8(const basic_json& j, detail::output_adapter<char> o)
     {
-        binary_writer<char> writer(o);
-        writer.write_bon8(j);
-        writer.flush();
+        binary_writer<char>(o).write_bon8(j);
     }
 
     /// @brief create a JSON value from an input in CBOR format
@@ -6903,72 +6878,6 @@ public:
     /// @name JSON Patch functions
     /// @{
 
-  private:
-    /// the members of an operation of a JSON patch that are of interest
-    struct patch_members
-    {
-        basic_json* op = nullptr;
-        basic_json* path = nullptr;
-        basic_json* value = nullptr;
-        basic_json* from = nullptr;
-    };
-
-    /// @brief find the members "op", "path", "value", and "from" of the object @a val in one pass
-    static patch_members find_patch_members(const basic_json& val, std::true_type /*key_type is string_t*/)
-    {
-        patch_members members;
-        for (auto& member : *val.m_data.m_value.object)
-        {
-            const string_t& key = member.first;
-            switch (key.size())
-            {
-                case 2:
-                    if (key == "op")
-                    {
-                        members.op = &member.second;
-                    }
-                    break;
-                case 4:
-                    if (key == "path")
-                    {
-                        members.path = &member.second;
-                    }
-                    else if (key == "from")
-                    {
-                        members.from = &member.second;
-                    }
-                    break;
-                case 5:
-                    if (key == "value")
-                    {
-                        members.value = &member.second;
-                    }
-                    break;
-                default:
-                    break;
-            }
-        }
-        return members;
-    }
-
-    /// @brief find the members by lookup for key types other than string_t
-    static patch_members find_patch_members(const basic_json& val, std::false_type /*key_type is not string_t*/)
-    {
-        const auto find_member = [&val](const char* name) -> basic_json *
-        {
-            const auto it = val.m_data.m_value.object->find(string_t(name));
-            return it != val.m_data.m_value.object->end() ? &it->second : nullptr;
-        };
-
-        patch_members members;
-        members.op = find_member("op");
-        members.path = find_member("path");
-        members.value = find_member("value");
-        members.from = find_member("from");
-        return members;
-    }
-
-  public:
     /// @brief applies a JSON patch in-place without copying the object
     /// @sa https://json.nlohmann.me/api/basic_json/patch/
     void patch_inplace(const basic_json& json_patch)
@@ -7136,155 +7045,31 @@ public:
             detail::throw_patch_not_an_array(json_patch);
         }
 
-        // the usual patch operations "add", "remove", "replace" and "test" on
-        // a pointer without escapes that denotes existing array elements and
-        // object members (as "add" does for the parent of the new value), as
-        // a diff creates them: apply the operation and return true; return
-        // false, with nothing changed, for all others
-        string_t token;
-        typename json_pointer::template plain_steps<basic_json> steps;
-        const auto try_plain = [&result, &token, &steps](patch_operations operation, const string_t& path, const patch_members & members, const basic_json & val)
-        {
-            if (path.empty())
-            {
-                return false;
-            }
-
-            // a missing "value" is reported below
-            const basic_json* const value_ptr = members.value;
-            const basic_json& value = value_ptr != nullptr ? *value_ptr : val;
-            if (operation != patch_operations::remove && value_ptr == nullptr)
-            {
-                return false;
-            }
-
-            switch (operation)
-            {
-                case patch_operations::replace:
-                {
-                    basic_json* const target = json_pointer::resolve_plain(&result, path, path.size(), token, steps);
-                    if (target == nullptr)
-                    {
-                        return false;
-                    }
-                    *target = value;
-                    return true;
-                }
-
-                case patch_operations::test:
-                {
-                    const basic_json* const target = json_pointer::resolve_plain(&result, path, path.size(), token, steps);
-                    // a failing test is reported below
-                    return target != nullptr && *target == value;
-                }
-
-                case patch_operations::add:
-                case patch_operations::remove:
-                {
-                    // the parent of the pointer and its last reference token
-                    std::size_t slash = path.size();
-                    while (slash > 0 && path[slash - 1] != '/')
-                    {
-                        --slash;
-                    }
-                    if (slash == 0)
-                    {
-                        return false;
-                    }
-                    --slash;
-
-                    basic_json* const parent = json_pointer::resolve_plain(&result, path, slash, token, steps);
-                    if (parent == nullptr)
-                    {
-                        return false;
-                    }
-                    token.clear();
-                    token.append(path.data() + slash + 1, path.size() - slash - 1);
-                    if (token.find_first_of('~') != string_t::npos)
-                    {
-                        return false;
-                    }
-
-                    if (operation == patch_operations::add)
-                    {
-                        if (parent->is_object())
-                        {
-                            (*parent)[token] = value;
-                            return true;
-                        }
-                        if (parent->is_array())
-                        {
-                            typename basic_json::size_type idx{};
-                            if (token == "-")
-                            {
-                                parent->push_back(value);
-                                return true;
-                            }
-                            if (json_pointer::template parse_array_index<basic_json_t>(token, idx) == json_pointer::array_index_status::ok && idx <= parent->size())
-                            {
-                                parent->insert(parent->begin() + static_cast<difference_type>(idx), value);
-                                return true;
-                            }
-                        }
-                        return false;
-                    }
-
-                    if (parent->is_object())
-                    {
-                        const auto it = parent->find(token);
-                        if (it == parent->end())
-                        {
-                            return false;
-                        }
-                        parent->erase(it);
-                        return true;
-                    }
-                    if (parent->is_array())
-                    {
-                        typename basic_json::size_type idx{};
-                        if (json_pointer::template parse_array_index<basic_json_t>(token, idx) == json_pointer::array_index_status::ok && idx < parent->size())
-                        {
-                            parent->erase(idx);
-                            return true;
-                        }
-                    }
-                    return false;
-                }
-
-                case patch_operations::move:
-                case patch_operations::copy:
-                case patch_operations::invalid:
-                default:
-                    return false;
-            }
-        };
-
-        // the name of the first member to check
-        const string_t op_member = "op";
-
         // iterate and apply the operations
         for (const auto& val : json_patch)
         {
             // wrapper to get a value for an operation
-            const auto get_value = [&val](basic_json * found,
-                                          const string_t& op,
-                                          const char* member,
+            const auto get_value = [&val](const string_t& op,
+                                          const string_t& member,
                                           bool string_type) -> basic_json &
             {
+                // find value
+                auto it = val.m_data.m_value.object->find(member);
+
                 // check if the desired value is present
-                if (JSON_HEDLEY_UNLIKELY(found == nullptr))
+                if (JSON_HEDLEY_UNLIKELY(it == val.m_data.m_value.object->end()))
                 {
-                    detail::throw_patch_missing_member(op, string_t(member), false, val);
+                    detail::throw_patch_missing_member(op, member, false, val);
                 }
 
                 // check if the result is of type string
-                if (JSON_HEDLEY_UNLIKELY(string_type && !found->is_string()))
+                if (JSON_HEDLEY_UNLIKELY(string_type && !it->second.is_string()))
                 {
-                    detail::throw_patch_missing_member(op, string_t(member), true, val);
+                    detail::throw_patch_missing_member(op, member, true, val);
                 }
 
                 // no error: return value
-                return *found;
+                return it->second;
             };
 
             // type check: every element of the array must be an object
@@ -7293,30 +7078,16 @@ public:
                 detail::throw_patch_not_an_array(val);
             }
 
-            const patch_members members = find_patch_members(val, std::is_same<typename object_t::key_type, string_t> {});
-
             // collect mandatory members
-            const string_t& op = *get_value(members.op, op_member, "op", true).m_data.m_value.string;
-            const string_t& path = *get_value(members.path, op, "path", true).m_data.m_value.string;
-            const patch_operations operation = get_op(op);
-
-            // the usual operations on a plain pointer are applied without
-            // building the pointer's reference tokens; anything else (and
-            // every error) is handled below
-            if (try_plain(operation, path, members, val))
-            {
-                continue;
-            }
-
-            // the general operations may change any container
-            steps.reset();
+            const string_t& op = *get_value("op", "op", true).m_data.m_value.string;
+            const string_t& path = *get_value(op, "path", true).m_data.m_value.string;
             json_pointer ptr(path);
 
-            switch (operation)
+            switch (get_op(op))
             {
                 case patch_operations::add:
                 {
-                    operation_add(ptr, get_value(members.value, "add", "value", false));
+                    operation_add(ptr, get_value("add", "value", false));
                     break;
                 }
 
@@ -7329,13 +7100,13 @@ public:
                 case patch_operations::replace:
                 {
                     // the "path" location must exist - use at()
-                    result.at(ptr) = get_value(members.value, "replace", "value", false);
+                    result.at(ptr) = get_value("replace", "value", false);
                     break;
                 }
 
                 case patch_operations::move:
                 {
-                    const string_t& from_path = *get_value(members.from, "move", "from", true).m_data.m_value.string;
+                    const string_t& from_path = *get_value("move", "from", true).m_data.m_value.string;
                     json_pointer from_ptr(from_path);
 
                     if (JSON_HEDLEY_UNLIKELY(is_proper_prefix(from_ptr, ptr)))
@@ -7358,7 +7129,7 @@ public:
 
                 case patch_operations::copy:
                 {
-                    const string_t& from_path = *get_value(members.from, "copy", "from", true).m_data.m_value.string;
+                    const string_t& from_path = *get_value("copy", "from", true).m_data.m_value.string;
                     const json_pointer from_ptr(from_path);
 
                     // The copy is functionally identical to an "add"
@@ -7376,7 +7147,7 @@ public:
                     {
                         // check if "value" matches the one at "path"
                         // the "path" location must exist - use at()
-                        success = (result.at(ptr) == get_value(members.value, "test", "value", false));
+                        success = (result.at(ptr) == get_value("test", "value", false));
                     }
                     JSON_INTERNAL_CATCH (out_of_range&)
                     {
@@ -7420,8 +7191,7 @@ public:
     {
         // the patch
         basic_json result(value_t::array);
-        string_t buffer = path;
-        diff_recursively(result, source, target, buffer, 0);
+        diff_recursively(result, source, target, path, 0);
         return result;
     }
 
@@ -7465,130 +7235,31 @@ public:
     // function it appears in. In diff_recursively, which is on the call stack
     // once per nesting level, that made every level cost kilobytes of stack.
 
-    /// @brief append an operation @a op for @a path to @a result, with @a value if it is not null
-    static void diff_operation(basic_json& result, const char* op, const string_t& path, const basic_json* value)
-    {
-        // the keys are distinct and in the order of std::map; the members are
-        // added without looking them up
-        basic_json entry(value_t::object);
-        auto& members = *entry.m_data.m_value.object;
-        auto hint = members.end();
-        json_pointer::add_flattened(members, hint, string_t("op"), string_t(op), detail::priority_tag<2> {});
-        json_pointer::add_flattened(members, hint, string_t("path"), path, detail::priority_tag<2> {});
-        if (value != nullptr)
-        {
-            json_pointer::add_flattened(members, hint, string_t("value"), *value, detail::priority_tag<2> {});
-        }
-        entry.set_parents();
-        result.push_back(std::move(entry));
-    }
-
     /// @brief append a "replace" operation for @a path with @a value to @a result
     static void diff_replace(basic_json& result, const string_t& path, const basic_json& value)
     {
-        diff_operation(result, "replace", path, &value);
+        result.push_back(
+        {
+            {"op", "replace"}, {"path", path}, {"value", value}
+        });
     }
 
     /// @brief append a "remove" operation for @a path to @a result
     static void diff_remove(basic_json& result, const string_t& path)
     {
-        diff_operation(result, "remove", path, nullptr);
+        result.push_back(object(
+        {
+            {"op", "remove"}, {"path", path}
+        }));
     }
 
     /// @brief append an "add" operation for @a path with @a value to @a result
     static void diff_add(basic_json& result, const string_t& path, const basic_json& value)
     {
-        diff_operation(result, "add", path, &value);
-    }
-
-    /// @brief the values in the target of the members of a source object, for the
-    ///        objects of up to 16 members without allocating
-    ///
-    /// reserve() must be called with the number of values that are added.
-    class diff_target_values
-    {
-      public:
-        diff_target_values() noexcept
-            : inline_items() // NOLINT(readability-redundant-member-init)
-        {}
-        diff_target_values(const diff_target_values&) = delete;
-        diff_target_values& operator=(const diff_target_values&) = delete;
-        diff_target_values(diff_target_values&&) = delete;
-        diff_target_values& operator=(diff_target_values&&) = delete;
-        ~diff_target_values() = default;
-
-        void reserve(const std::size_t n)
+        result.push_back(
         {
-            if (n > inline_size)
-            {
-                large.resize(n);
-                items = large.data();
-            }
-        }
-
-        void push_back(const basic_json* value)
-        {
-            items[count++] = value;
-        }
-
-        std::size_t size() const noexcept
-        {
-            return count;
-        }
-
-        const basic_json* operator[](const std::size_t i) const noexcept
-        {
-            return items[i];
-        }
-
-      private:
-        static constexpr std::size_t inline_size = 16;
-        /// the values of a small object, left uninitialized: they are written
-        /// before they are read (the user-provided constructor keeps the
-        /// member initialization, which -Weffc++ asks for, from zeroing them)
-        struct uninitialized_items : std::array<const basic_json*, inline_size>
-        {
-            uninitialized_items() noexcept {} // NOLINT(modernize-use-equals-default,hicpp-use-equals-default,cppcoreguidelines-pro-type-member-init,hicpp-member-init): see above
-        };
-
-        std::size_t count = 0;
-        std::vector<const basic_json*> large{}; // NOLINT(readability-redundant-member-init)
-        uninitialized_items inline_items;
-        const basic_json** items = inline_items.data();
-    };
-
-    /// @brief append "/" and the decimal representation of @a index to @a path
-    static void diff_append_index(string_t& path, std::size_t index)
-    {
-        path.push_back('/');
-        json_pointer::append_index(path, index);
-    }
-
-    /// @brief append "/" and the escaped @a key to @a path
-    static void diff_append_key(string_t& path, const string_t& key)
-    {
-        path.push_back('/');
-        detail::escape_into(path, key);
-    }
-
-    /// @brief the path of the member @a key of the value at @a path
-    static string_t diff_key_path(const string_t& path, const string_t& key)
-    {
-        string_t result;
-        result.reserve(path.size() + key.size() + 1);
-        result.append(path.data(), path.size());
-        diff_append_key(result, key);
-        return result;
-    }
-
-    /// @brief the path of the element @a index of the value at @a path
-    static string_t diff_index_path(const string_t& path, const std::size_t index)
-    {
-        string_t result;
-        result.reserve(path.size() + 8);
-        result.append(path.data(), path.size());
-        diff_append_index(result, index);
-        return result;
+            {"op", "add"}, {"path", path}, {"value", value}
+        });
     }
 
     /// @brief append the "remove" operations for the elements of array
@@ -7601,18 +7272,13 @@ public:
         // in that order avoids the quadratic reinsertion done before
         for (std::size_t j = source.size(); j > index; --j)
         {
-            diff_remove(result, diff_index_path(path, j - 1));
+            diff_remove(result, detail::concat<string_t>(path, '/', detail::to_string<string_t>(j - 1)));
         }
 
         // add other remaining elements
-        if (source.size() < target.size())
+        for (std::size_t i = source.size(); i < target.size(); ++i)
         {
-            string_t tail_path = path;
-            tail_path.append("/-", 2);
-            for (std::size_t i = source.size(); i < target.size(); ++i)
-            {
-                diff_add(result, tail_path, target[i]);
-            }
+            diff_add(result, detail::concat<string_t>(path, "/-"), target[i]);
         }
     }
 
@@ -7621,7 +7287,7 @@ public:
     {
         for (const auto& it : added)
         {
-            diff_add(result, diff_key_path(path, it.key()), it.value());
+            diff_add(result, detail::concat<string_t>(path, '/', detail::escape(it.key())), it.value());
         }
     }
 
@@ -7637,31 +7303,15 @@ public:
     operations that remove every member of @a source and add every member of
     @a target to @a result, and returns false.
     */
-    template<typename TargetValues>
     static bool diff_object_keys(basic_json& result, const basic_json& source, const basic_json& target,
-                                 const string_t& path, TargetValues& target_values,
+                                 const string_t& path, std::vector<const basic_json*>& target_values,
                                  std::vector<const_iterator>& added)
     {
         // first pass: one lookup per source key
-        // Objects of the same size usually have the same keys, in the same
-        // order: walk them together as long as that holds, which takes no lookups.
         target_values.reserve(source.size());
         std::size_t common = 0;
-        bool together = source.size() == target.size();
-        for (auto it = source.cbegin(), partner = target.cbegin(); it != source.cend(); ++it)
+        for (auto it = source.cbegin(); it != source.cend(); ++it)
         {
-            if (together)
-            {
-                if (it.key() == partner.key())
-                {
-                    target_values.push_back(&partner.value());
-                    ++common;
-                    ++partner;
-                    continue;
-                }
-                together = false;
-            }
-
             const auto found = target.find(it.key());
             if (found != target.cend())
             {
@@ -7674,12 +7324,6 @@ public:
             }
         }
 
-        // the same keys in the same order
-        if (together)
-        {
-            return true;
-        }
-
         // second pass: find the keys only target has. An object type that
         // keeps its members in insertion order, such as the one backing
         // ordered_json, also needs the common keys to be in the same order
@@ -7745,13 +7389,6 @@ public:
             return true;
         }
 
-        // equal objects, whose members are in a different order, need no
-        // operations
-        if (source == target)
-        {
-            return false;
-        }
-
         // slow path: the common keys are in a different relative
         // order in source and target (only possible for a
         // reorderable object_t like ordered_map). Building a
@@ -7768,7 +7405,7 @@ public:
         // it moves it to the end, fixing its position.
         for (auto it = source.cbegin(); it != source.cend(); ++it)
         {
-            diff_remove(result, diff_key_path(path, it.key()));
+            diff_remove(result, detail::concat<string_t>(path, '/', detail::escape(it.key())));
         }
 
         // add every key that is either common (just removed
@@ -7777,7 +7414,7 @@ public:
         // target exactly
         for (auto it = target.cbegin(); it != target.cend(); ++it)
         {
-            diff_add(result, diff_key_path(path, it.key()), it.value());
+            diff_add(result, detail::concat<string_t>(path, '/', detail::escape(it.key())), it.value());
         }
         return false;
     }
@@ -7786,9 +7423,6 @@ public:
     @brief @ref diff, for values at nesting level @a depth, appending the
            operations to @a result
 
-    @a path is the path of the values; it is a buffer that is extended and
-    shortened again below, and is the same when the function returns.
-
     Diffing two arrays or objects calls this function again, once per nesting
     level, so values nested deeply enough used to exhaust the call stack and
     terminate the process. The descent is bounded here: once @ref
@@ -7796,7 +7430,7 @@ public:
     diff_iteratively diffs what is left without the call stack.
     */
     static void diff_recursively(basic_json& result, const basic_json& source, const basic_json& target,
-                                 string_t& path, const std::size_t depth)
+                                 const string_t& path, const std::size_t depth)
     {
         // if the values are the same, there is nothing to do
         if (source == target)
@@ -7808,9 +7442,9 @@ public:
     }
 
     /// @brief @ref diff_recursively for values known to be unequal; callers
-    ///        compare first so they extend the path only for unequal ones
+    ///        compare first so they build no path for equal ones
     static void diff_unequal(basic_json& result, const basic_json& source, const basic_json& target,
-                             string_t& path, const std::size_t depth)
+                             const string_t& path, const std::size_t depth)
     {
         if (JSON_HEDLEY_UNLIKELY(depth >= detail::recursion_depth_limit()))
         {
@@ -7829,8 +7463,6 @@ public:
         {
             case value_t::array:
             {
-                const std::size_t path_length = path.size();
-
                 // first pass: traverse common elements
                 std::size_t i = 0;
                 while (i < source.size() && i < target.size())
@@ -7838,9 +7470,7 @@ public:
                     // recursive call to compare array values at index i
                     if (!(source[i] == target[i]))
                     {
-                        diff_append_index(path, i);
-                        diff_unequal(result, source[i], target[i], path, depth + 1);
-                        path.resize(path_length);
+                        diff_unequal(result, source[i], target[i], detail::concat<string_t>(path, '/', detail::to_string<string_t>(i)), depth + 1);
                     }
                     ++i;
                 }
@@ -7853,7 +7483,7 @@ public:
 
             case value_t::object:
             {
-                diff_target_values target_values;
+                std::vector<const basic_json*> target_values;
                 std::vector<const_iterator> added;
                 if (diff_object_keys(result, source, target, path, target_values, added))
                 {
@@ -7862,7 +7492,6 @@ public:
                     // lookup is needed. Deleted keys are interleaved here
                     // too, in source's original order, to match the
                     // historical (pre-reordering-aware) output order.
-                    const std::size_t path_length = path.size();
                     std::size_t i = 0;
                     for (auto it = source.cbegin(); it != source.cend(); ++it, ++i)
                     {
@@ -7870,15 +7499,13 @@ public:
                         {
                             if (!(it.value() == *target_values[i]))
                             {
-                                diff_append_key(path, it.key());
-                                diff_unequal(result, it.value(), *target_values[i], path, depth + 1);
-                                path.resize(path_length);
+                                diff_unequal(result, it.value(), *target_values[i], detail::concat<string_t>(path, '/', detail::escape(it.key())), depth + 1);
                             }
                         }
                         else
                         {
                             // found a key that is not in target -> remove it
-                            diff_remove(result, diff_key_path(path, it.key()));
+                            diff_remove(result, detail::concat<string_t>(path, '/', detail::escape(it.key())));
                         }
                     }
 
@@ -8009,7 +7636,7 @@ public:
                 if (i < source_array.size() && i < target_array.size())
                 {
                     ++stack.back().index;
-                    diff_append_index(current_path, i);
+                    detail::concat_into(current_path, '/', detail::to_string<string_t>(i));
                     enter(source_array[i], target_array[i]);
                     if (stack.size() == depth)
                     {
@@ -8032,7 +7659,7 @@ public:
                     if (target_value_ptr != nullptr)
                     {
                         const basic_json& target_value = *target_value_ptr;
-                        diff_append_key(current_path, it.key());
+                        detail::concat_into(current_path, '/', detail::escape(it.key()));
                         enter(it.value(), target_value);
                         if (stack.size() == depth)
                         {
@@ -8042,7 +7669,7 @@ public:
                     else
                     {
                         // found a key that is not in target -> remove it
-                        diff_remove(result, diff_key_path(current_path, it.key()));
+                        diff_remove(result, detail::concat<string_t>(current_path, '/', detail::escape(it.key())));
                     }
                     continue;
                 }

include/nlohmann/json_view.hpp

@@ -29,7 +29,7 @@
 #include <algorithm> // all_of, min
 #include <array> // array
 #include <cstddef> // nullptr_t, size_t // IWYU pragma: keep
-#include <cstdint> // uint8_t, uint32_t
+#include <cstdint> // uint32_t
 #include <cstring> // memcpy, strlen
 #include <istream> // istream // IWYU pragma: keep
 #include <iterator> // distance, input_iterator_tag, iterator_traits
@@ -71,7 +71,6 @@
 #include <nlohmann/detail/view/document_data.hpp>
 #include <nlohmann/detail/view/edit.hpp>
 #include <nlohmann/detail/view/errors.hpp>
-#include <nlohmann/detail/view/image.hpp>
 #include <nlohmann/detail/view/input.hpp>
 #include <nlohmann/detail/view/iterator.hpp>
 #include <nlohmann/detail/view/lookup.hpp>
@@ -623,10 +622,8 @@ class basic_json_view
         style.indent_char = indent_char;
         style.ensure_ascii = ensure_ascii;
         style.source_numbers = numbers == number_format::source;
-        // the compact text is about as long as the source text of the value;
-        // the compact writer keeps 64 bytes of slack, so that it does not grow
-        // the buffer just before the end
-        const std::size_t estimate = source_extent() + (style.pretty ? source_extent() / 2 : 0) + 160;
+        // the compact text is about as long as the source text of the value
+        const std::size_t estimate = source_extent() + (style.pretty ? source_extent() / 2 : 0) + 64;
         detail::view::view_serializer<BasicJsonType, Editable>(*m_doc, out, estimate, style).dump(m_node);
         return out;
     }
@@ -1031,7 +1028,7 @@ class basic_json_document
     /// whether the document holds its own copy of the text
     bool owns_source() const noexcept
     {
-        return m_data && ((!m_data->owned.empty() && m_data->src == m_data->owned.data()) || !m_data->owned_image.empty());
+        return m_data && !m_data->owned.empty() && m_data->src == m_data->owned.data();
     }
 
     /// number of index nodes (values plus object keys)
@@ -1040,7 +1037,7 @@ class basic_json_document
         return m_data ? m_data->node_count : 0;
     }
 
-    /// bytes held by the document (index, decoded strings, and owned text or image)
+    /// bytes held by the document (index, decoded strings, owned text)
     std::size_t memory_usage() const noexcept
     {
         if (!m_data)
@@ -1049,7 +1046,7 @@ class basic_json_document
         }
         return sizeof(document_data) + (m_data->inline_capacity * sizeof(detail::view::node))
                + (m_data->nodes != m_data->inline_nodes ? m_data->node_capacity * sizeof(detail::view::node) : 0)
-               + m_data->arena.capacity() + m_data->owned.capacity() + m_data->owned_image.capacity()
+               + m_data->arena.capacity() + m_data->owned.capacity()
                + (m_data->indexes.capacity() * sizeof(document_data::object_index)) + (m_data->index_slots.capacity() * sizeof(std::uint32_t))
                + (m_data->large_objects.capacity() * sizeof(std::uint32_t))
                + (m_data->edits != nullptr ? m_data->edits->bytes : 0);
@@ -1069,10 +1066,8 @@ class basic_json_document
 
         // allocate everything first, so that an exception leaves the document
         // unchanged
-        // (the decoded strings of a loaded image stay in the image)
-        const bool arena_in_use = d.base[1] == d.arena.data();
         const bool shrink_arena = d.arena.capacity() > d.arena.size();
-        std::vector<char> arena(shrink_arena && arena_in_use ? d.arena : std::vector<char>());
+        std::vector<char> arena(shrink_arena ? d.arena : std::vector<char>());
         // (edits link to the nodes of the index, which then stays in place)
         const bool shrink_nodes = d.nodes != d.inline_nodes && d.node_count != d.node_capacity && d.edits == nullptr;
         const bool into_header = d.node_count <= d.inline_capacity;
@@ -1093,10 +1088,7 @@ class basic_json_document
         if (shrink_arena)
         {
             d.arena.swap(arena);
-            if (arena_in_use)
-            {
-                d.base[1] = d.arena.data();
-            }
+            d.base[1] = d.arena.data();
         }
         if (d.indexes.capacity() > d.indexes.size())
         {
@@ -1108,55 +1100,6 @@ class basic_json_document
         }
     }
 
-    ////////////
-    // images //
-    ////////////
-
-    /// how load() checks an image (full, bounds, or none)
-    using image_check = detail::view::image_check;
-
-    /// The document as an image that load() reads without parsing: the node
-    /// index, the text, and the decoded strings. An edited document is
-    /// written in its current state (floats that are not finite become null,
-    /// as in dump()).
-    std::vector<std::uint8_t> save() const
-    {
-        if (NLOHMANN_VIEW_UNLIKELY(!m_data || m_data->discarded))
-        {
-            detail::view::throw_type_error(320, "cannot save a discarded json_document");
-        }
-        return detail::view::save_image(*m_data);
-    }
-
-    /// Read an image written by save(). The image is borrowed: it must stay
-    /// alive and unchanged while the document is used.
-    NLOHMANN_VIEW_NODISCARD
-    static basic_json_document load(const std::uint8_t* image, std::size_t size, const image_check check = image_check::full)
-    {
-        basic_json_document d;
-        d.ensure_data(nullptr, 0);
-        detail::view::load_image(*d.m_data, image, size, check);
-        return d;
-    }
-
-    /// read an image (borrowed)
-    NLOHMANN_VIEW_NODISCARD
-    static basic_json_document load(const std::vector<std::uint8_t>& image, const image_check check = image_check::full)
-    {
-        return load(image.data(), image.size(), check);
-    }
-
-    /// read an image and keep it (no copy)
-    NLOHMANN_VIEW_NODISCARD
-    static basic_json_document load(std::vector<std::uint8_t>&& image, const image_check check = image_check::full)
-    {
-        basic_json_document d;
-        d.ensure_data(nullptr, 0);
-        d.m_data->owned_image = std::move(image);
-        detail::view::load_image(*d.m_data, d.m_data->owned_image.data(), d.m_data->owned_image.size(), check);
-        return d;
-    }
-
     ///////////
     // edits //
     ///////////
@@ -1391,7 +1334,6 @@ class basic_json_document
         {
             d.owned.clear();
         }
-        d.owned_image.clear();
         d.src = src;
         d.size = size;
         d.node_count = 0;
@@ -1416,7 +1358,6 @@ class basic_json_document
         {
             d.base[0] = d.src;
             d.base[1] = d.arena.data();
-            d.arena_size = d.arena.size();
             detail::view::build_object_indexes(d);
             std::vector<std::uint32_t>().swap(d.large_objects); // (only needed while parsing)
             d.discarded = false;

single_include/nlohmann/json_fwd.hpp

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

tests/CMakeLists.txt

@@ -373,25 +373,6 @@ json_test_add_test_for(src/unit-diagnostic-positions.cpp
     MAIN test_main CXX_STANDARDS ${test_cxx_standards} ${test_force}
 )
 
-# the lexer again with the portable string scanning instead of SSE2/NEON, and on
-# x86-64 with SSSE3 compiled in (no check of the CPU)
-json_test_set_test_options(test-class_lexer_no_simd
-    COMPILE_DEFINITIONS JSON_NO_SIMD
-)
-json_test_add_test_for(src/unit-class_lexer.cpp
-    NAME test-class_lexer_no_simd
-    MAIN test_main CXX_STANDARDS ${test_cxx_standards} ${test_force}
-)
-if(CMAKE_SYSTEM_PROCESSOR MATCHES "^(x86_64|AMD64|amd64)$" AND NOT MSVC)
-    json_test_set_test_options(test-class_lexer_ssse3
-        COMPILE_OPTIONS -mssse3
-    )
-    json_test_add_test_for(src/unit-class_lexer.cpp
-        NAME test-class_lexer_ssse3
-        MAIN test_main CXX_STANDARDS ${test_cxx_standards} ${test_force}
-    )
-endif()
-
 # test reading from a std::istream again without scanning the get area in bulk
 json_test_set_test_options(test-stream-bulk-scan_disabled
     COMPILE_DEFINITIONS JSON_DISABLE_STREAM_BULK_SCAN=1

tests/Makefile

@@ -10,7 +10,7 @@ CXXFLAGS += -std=c++11
 CPPFLAGS += -I ../single_include
 
 FUZZER_ENGINE = src/fuzzer-driver_afl.cpp
-FUZZERS = parse_afl_fuzzer parse_bson_fuzzer parse_cbor_fuzzer parse_msgpack_fuzzer parse_ubjson_fuzzer parse_bjdata_fuzzer parse_bon8_fuzzer parse_json_view_fuzzer json_view_image_fuzzer
+FUZZERS = parse_afl_fuzzer parse_bson_fuzzer parse_cbor_fuzzer parse_msgpack_fuzzer parse_ubjson_fuzzer parse_bjdata_fuzzer parse_bon8_fuzzer parse_json_view_fuzzer
 fuzzers: $(FUZZERS)
 
 parse_afl_fuzzer:
@@ -19,9 +19,6 @@ parse_afl_fuzzer:
 parse_json_view_fuzzer:
 	$(CXX) $(CXXFLAGS) $(CPPFLAGS) $(FUZZER_ENGINE) src/fuzzer-parse_json_view.cpp -o $@
 
-json_view_image_fuzzer:
-	$(CXX) $(CXXFLAGS) $(CPPFLAGS) $(FUZZER_ENGINE) src/fuzzer-json_view_image.cpp -o $@
-
 parse_bson_fuzzer:
 	$(CXX) $(CXXFLAGS) $(CPPFLAGS) $(FUZZER_ENGINE) src/fuzzer-parse_bson.cpp -o $@
 

tests/abi/config/CMakeLists.txt

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

tests/abi/config/default.cpp

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

tests/abi/config/noversion.cpp

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

tests/benchmarks/README.md

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

tests/benchmarks/json_view/.gitignore

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

tests/benchmarks/json_view/README.md

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

tests/benchmarks/json_view/bench_corpus.cpp

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

tests/benchmarks/json_view/bench_edit.cpp

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

tests/benchmarks/json_view/bench_view.cpp

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

tests/benchmarks/json_view/compare.py

@@ -1,342 +0,0 @@
-#!/usr/bin/env python3
-#     __ _____ _____ _____
-#  __|  |   __|     |   | |  JSON for Modern C++ (supporting code)
-# |  |  |__   |  |  | | | |  version 3.12.0
-# |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-#
-# SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-# SPDX-License-Identifier: MIT
-
-"""Compare json_view with yyjson, simdjson, Boost.JSON, and json::parse.
-
-Builds bench_view.cpp, bench_corpus.cpp, and bench_edit.cpp against the include/ directory of
-this checkout, runs them, and writes the results with everything needed to
-reproduce them (date, commit, CPU, OS, compiler, library versions, flags) to
-results/<date>-<host>.md and .csv next to this script.
-
-The other libraries come from the system (--system, the default: pkg-config
-or Homebrew) or are downloaded as pinned releases and checked against their
-SHA-256 (--download). Boost.JSON is optional: without Boost headers, its
-columns are skipped, and the results say so.
-
-Only the Python 3 standard library is used; a C++17 compiler is needed.
-"""
-
-import argparse
-import datetime
-import hashlib
-import os
-import platform
-import re
-import shlex
-import shutil
-# runs only the compilers and benchmark binaries this script builds
-import subprocess  # nosec B404
-import sys
-import tarfile
-import tempfile
-import urllib.request
-
-HERE = os.path.dirname(os.path.abspath(__file__))
-REPO = os.path.abspath(os.path.join(HERE, '..', '..', '..'))
-
-# seconds without data after which a download fails
-DOWNLOAD_TIMEOUT = 60
-
-# pinned releases for --download; the hashes are those of the archives
-#
-# The yyjson and simdjson archives are the tag archives GitHub generates
-# (archive/refs/tags/...), whose bytes GitHub does not guarantee to be stable. A SHA-256
-# mismatch for one of them means that GitHub regenerated the archive: check the upstream
-# tag, then pin the new hash.
-PINNED = {
-    'yyjson': {
-        'version': '0.13.0',
-        'url': 'https://github.com/ibireme/yyjson/archive/refs/tags/0.13.0.tar.gz',
-        'sha256': '34e0f62a2bc11ab20d601e8ca1cc2b2079503aa45119a19133d89d19b94a0fae',
-        'dir': 'yyjson-0.13.0',
-    },
-    'simdjson': {
-        'version': '4.6.11',
-        'url': 'https://github.com/simdjson/simdjson/archive/refs/tags/v4.6.11.tar.gz',
-        'sha256': '61d948fc24f0d793829ad658058e7597d064988a89b4607ea02e401a82df98ff',
-        'dir': 'simdjson-4.6.11',
-    },
-    'boost': {
-        'version': '1.92.0',
-        'url': 'https://archives.boost.io/release/1.92.0/source/boost_1_92_0.tar.gz',
-        'sha256': 'c4a3b310ddd2472416e091067166b0713be97c63f38c212c484ada022fd296ce',
-        'dir': 'boost_1_92_0',
-    },
-}
-
-# the documents of bench_view.cpp, relative to the json_test_data directory
-DEFAULT_CORPUS = [
-    'nativejson-benchmark/twitter.json',
-    'nativejson-benchmark/citm_catalog.json',
-    'nativejson-benchmark/canada.json',
-    'jeopardy/jeopardy.json',
-]
-
-
-def run(cmd, **kwargs):
-    print('+ ' + ' '.join(shlex.quote(c) for c in cmd), flush=True)
-    # cmd is an argument list built by this script, never a shell string
-    return subprocess.run(cmd, check=True, **kwargs)  # nosec B603
-
-
-def output(cmd):
-    try:
-        # cmd is an argument list built by this script, never a shell string
-        return subprocess.run(cmd, check=True, capture_output=True, text=True).stdout.strip()  # nosec B603
-    except (OSError, subprocess.CalledProcessError):
-        return ''
-
-
-# ---------------------------------------------------------------------------
-# libraries
-# ---------------------------------------------------------------------------
-
-class Library:
-    """include directories, sources to compile, and linker flags of a library"""
-
-    def __init__(self, name, include=None, sources=None, link=None, version=''):
-        self.name = name
-        self.include = include or []
-        self.sources = sources or []
-        self.link = link or []
-        self.version = version
-
-
-def header_version(path, pattern):
-    try:
-        with open(path, encoding='utf-8', errors='replace') as f:
-            m = re.search(pattern, f.read())
-        return m.group(1) if m else ''
-    except OSError:
-        return ''
-
-
-def library_version(name, include_dirs):
-    patterns = {
-        'yyjson': ('yyjson.h', r'#define\s+YYJSON_VERSION_STRING\s+"([^"]+)"'),
-        'simdjson': ('simdjson.h', r'#define\s+SIMDJSON_VERSION\s+"?([0-9.]+)"?'),
-        'boost': (os.path.join('boost', 'version.hpp'), r'#define\s+BOOST_LIB_VERSION\s+"([^"]+)"'),
-    }
-    header, pattern = patterns[name]
-    for d in include_dirs:
-        v = header_version(os.path.join(d, header), pattern)
-        if v:
-            return v.replace('_', '.')
-    return ''
-
-
-def system_library(name):
-    """a library found with pkg-config or Homebrew, or None"""
-    flags = output(['pkg-config', '--cflags', '--libs', name]).split()
-    if flags:
-        include = [f[2:] for f in flags if f.startswith('-I')]
-        link = [f for f in flags if f.startswith('-L') or f.startswith('-l')]
-        libdirs = [f[2:] for f in link if f.startswith('-L')]
-        link += ['-Wl,-rpath,' + d for d in libdirs]
-        return Library(name, include, [], link, library_version(name, include))
-    prefix = output(['brew', '--prefix', name]) if shutil.which('brew') else ''
-    if prefix and os.path.isdir(os.path.join(prefix, 'include')):
-        include = [os.path.join(prefix, 'include')]
-        link = []
-        if name != 'boost':
-            lib = os.path.join(prefix, 'lib')
-            link = ['-L' + lib, '-l' + name, '-Wl,-rpath,' + lib]
-        return Library(name, include, [], link, library_version(name, include))
-    if name == 'boost':
-        for d in ['/usr/include', '/usr/local/include']:
-            if os.path.isfile(os.path.join(d, 'boost', 'json.hpp')):
-                return Library(name, [d], [], [], library_version(name, [d]))
-    return None
-
-
-def sha256_file(path):
-    """SHA-256 of a file, read in chunks (the Boost archive is more than 100 MB)"""
-    h = hashlib.sha256()
-    with open(path, 'rb') as f:
-        for chunk in iter(lambda: f.read(1 << 20), b''):
-            h.update(chunk)
-    return h.hexdigest()
-
-
-def download_library(name, work):
-    """a pinned release, downloaded and checked, or an error"""
-    pin = PINNED[name]
-    archive = os.path.join(work, 'download', os.path.basename(pin['url']))
-    os.makedirs(os.path.dirname(archive), exist_ok=True)
-    if not os.path.isfile(archive):
-        print(f'downloading {pin["url"]}', flush=True)
-        # the URLs are the https constants in PINNED, and the SHA-256 is checked below
-        # (into a .part file first, so that an interrupted download is not kept)
-        with urllib.request.urlopen(pin['url'], timeout=DOWNLOAD_TIMEOUT) as response:  # nosec B310
-            with open(archive + '.part', 'wb') as f:
-                shutil.copyfileobj(response, f)
-        os.replace(archive + '.part', archive)
-    digest = sha256_file(archive)
-    if digest != pin['sha256']:
-        os.remove(archive)  # downloaded again by the next run
-        sys.exit(f'error: SHA-256 of {archive} is {digest}, expected {pin["sha256"]} (removed)')
-    src = os.path.join(work, 'download', pin['dir'])
-    if not os.path.isdir(src):
-        # extracted into a temporary directory first, so that an interrupted extraction
-        # is not mistaken for a complete one
-        tmp = tempfile.mkdtemp(prefix=pin['dir'] + '.part-', dir=os.path.join(work, 'download'))
-        try:
-            with tarfile.open(archive) as t:
-                # (the 'data' filter rejects links and paths outside the target where Python has it)
-                kwargs = {'filter': 'data'} if hasattr(tarfile, 'data_filter') else {}
-                t.extractall(tmp, **kwargs)  # noqa: S202 (checked archive)  # nosec B202
-            os.rename(os.path.join(tmp, pin['dir']), src)
-        finally:
-            shutil.rmtree(tmp, ignore_errors=True)
-    if name == 'yyjson':
-        return Library(name, [os.path.join(src, 'src')], [os.path.join(src, 'src', 'yyjson.c')], [], pin['version'])
-    if name == 'simdjson':
-        single = os.path.join(src, 'singleheader')
-        return Library(name, [single], [os.path.join(single, 'simdjson.cpp')], [], pin['version'])
-    return Library(name, [src], [], [], pin['version'])
-
-
-# ---------------------------------------------------------------------------
-# machine description
-# ---------------------------------------------------------------------------
-
-def cpu_model():
-    if sys.platform == 'darwin':
-        return output(['sysctl', '-n', 'machdep.cpu.brand_string'])
-    try:
-        with open('/proc/cpuinfo', encoding='utf-8') as f:
-            for line in f:
-                if line.startswith('model name') or line.startswith('Model'):
-                    return line.split(':', 1)[1].strip()
-    except OSError:
-        pass
-    # (AArch64 Linux: /proc/cpuinfo has no model name, lscpu knows it)
-    for line in output(['lscpu']).splitlines():
-        if line.startswith('Model name:'):
-            return line.split(':', 1)[1].strip()
-    return platform.processor() or platform.machine()
-
-
-def git_commit():
-    commit = output(['git', '-C', REPO, 'rev-parse', '--short=12', 'HEAD'])
-    dirty = output(['git', '-C', REPO, 'status', '--porcelain', '--untracked-files=no'])
-    return commit + (' (with local changes)' if dirty else '')
-
-
-# ---------------------------------------------------------------------------
-# main
-# ---------------------------------------------------------------------------
-
-def main():
-    ap = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
-    ap.add_argument('--data', required=True, help='json_test_data directory (with nativejson-benchmark/ and jeopardy/)')
-    ap.add_argument('--download', action='store_true', help='use pinned downloads instead of system libraries')
-    ap.add_argument('--no-boost', action='store_true', help='skip Boost.JSON')
-    ap.add_argument('--native', action='store_true', help='compile for this CPU (-march=native / -mcpu=native)')
-    ap.add_argument('--rounds', type=int, default=30, help='rounds of bench_view (default: 30)')
-    ap.add_argument('--corpus', nargs='*', default=[], help='more files for bench_corpus')
-    ap.add_argument('--build-dir', default=os.path.join(HERE, 'build'), help='where to build (default: build/ next to this script)')
-    args = ap.parse_args()
-    # the benchmarks run in the build directory: make the paths absolute
-    args.data = os.path.abspath(args.data)
-    args.corpus = [os.path.abspath(f) for f in args.corpus]
-    args.build_dir = os.path.abspath(args.build_dir)
-
-    # (CXX and CC may contain arguments, e.g. 'ccache g++')
-    cxx = shlex.split(os.environ.get('CXX', 'c++'))
-    cc = shlex.split(os.environ.get('CC', 'cc'))
-    os.makedirs(args.build_dir, exist_ok=True)
-
-    libs = {}
-    for name in ['yyjson', 'simdjson', 'boost']:
-        if name == 'boost' and args.no_boost:
-            continue
-        lib = download_library(name, args.build_dir) if args.download else system_library(name)
-        if lib is None and name != 'boost':
-            sys.exit(f'error: {name} not found; install it, or use --download')
-        if lib is not None:
-            libs[name] = lib
-    with_boost = 'boost' in libs
-    if not with_boost:
-        print('Boost.JSON not found: its columns are skipped', flush=True)
-
-    flags = ['-std=c++17', '-O3', '-DNDEBUG', f'-DJSON_VIEW_BENCH_BOOST={1 if with_boost else 0}']
-    if args.native:
-        flags.append('-mcpu=native' if platform.machine().lower() in ('arm64', 'aarch64') else '-march=native')
-    include = ['-I' + os.path.join(REPO, 'include')] + ['-I' + d for lib in libs.values() for d in lib.include]
-    link = [f for lib in libs.values() for f in lib.link]
-
-    # C sources of downloaded libraries are compiled once
-    objects = []
-    for lib in libs.values():
-        for src in lib.sources:
-            obj = os.path.join(args.build_dir, os.path.basename(src) + '.o')
-            is_c = src.endswith('.c')
-            run((cc if is_c else cxx) + ([] if is_c else ['-std=c++17']) + ['-O3', '-DNDEBUG', '-c', src, '-o', obj]
-                + ['-I' + d for d in lib.include])
-            objects.append(obj)
-
-    binaries = {}
-    for bench in ['bench_view', 'bench_corpus', 'bench_edit']:
-        exe = os.path.join(args.build_dir, bench)
-        run(cxx + flags + include + [os.path.join(HERE, bench + '.cpp')] + objects + link + ['-o', exe])
-        binaries[bench] = exe
-
-    # run: bench_view on its documents, bench_corpus on those and the given files
-    corpus = [os.path.join(args.data, f) for f in DEFAULT_CORPUS] + args.corpus
-    outputs = {}
-    outputs['bench_view'] = run([binaries['bench_view'], args.data, str(args.rounds)], cwd=args.build_dir,
-                                capture_output=True, text=True).stdout
-    outputs['bench_corpus'] = run([binaries['bench_corpus']] + corpus, cwd=args.build_dir,
-                                  capture_output=True, text=True).stdout
-    outputs['bench_edit'] = run([binaries['bench_edit'], args.data, str(max(1, args.rounds // 2))], cwd=args.build_dir,
-                                capture_output=True, text=True).stdout
-    for name, text in outputs.items():
-        print(text)
-
-    # results with their metadata
-    now = datetime.datetime.now()
-    host = re.sub(r'[^A-Za-z0-9-]+', '-', platform.node().split('.')[0]) or 'host'
-    stem = os.path.join(HERE, 'results', f'{now:%Y-%m-%d}-{host}')
-    os.makedirs(os.path.dirname(stem), exist_ok=True)
-    cxx_version = output(cxx + ['--version'])
-    compiler_version = cxx_version.splitlines()[0] if cxx_version else ' '.join(cxx)
-    meta = [
-        ('date', f'{now:%Y-%m-%d %H:%M}'),
-        ('commit', git_commit()),
-        ('CPU', cpu_model()),
-        ('OS', f'{platform.system()} {platform.release()} ({platform.machine()})'),
-        ('compiler', compiler_version),
-        ('flags', ' '.join(flags)),
-        ('yyjson', libs['yyjson'].version),
-        ('simdjson', libs['simdjson'].version),
-        ('Boost.JSON', libs['boost'].version if with_boost else 'skipped (not found)'),
-        ('libraries from', 'pinned downloads' if args.download else 'the system'),
-        ('rounds', str(args.rounds)),
-    ]
-    with open(stem + '.md', 'w', encoding='utf-8') as f:
-        f.write(f'# json_view comparison, {now:%Y-%m-%d}\n\n')
-        f.write('Generated by `tests/benchmarks/json_view/compare.py`; best of the interleaved rounds.\n\n')
-        f.write('| | |\n|---|---|\n')
-        for key, value in meta:
-            f.write(f'| {key} | {value} |\n')
-        for name, text in outputs.items():
-            f.write(f'\n## {name}\n\n```\n{text.rstrip()}\n```\n')
-    with open(stem + '.csv', 'w', encoding='utf-8') as out:
-        out.write(''.join(f'# {key}: {value}\n' for key, value in meta))
-        for name in ['bench_view', 'bench_corpus', 'bench_edit']:
-            path = os.path.join(args.build_dir, name + '.csv')
-            if os.path.isfile(path):
-                with open(path, encoding='utf-8') as f:
-                    out.write(f'# {name}\n' + f.read())
-    print(f'results: {stem}.md, {stem}.csv')
-
-
-if __name__ == '__main__':
-    main()

tests/benchmarks/src/benchmarks.cpp

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

tests/fuzzing.md

@@ -12,12 +12,6 @@ produces, and that a rejected input makes both parsers throw with an identical `
 are taken from the low bits of the first input byte (the byte stays part of the text). It takes plain JSON text, so it
 reuses the `corpus_json` corpus rather than a format of its own.
 
-`json_view_image_fuzzer` (`tests/src/fuzzer-json_view_image.cpp`) tests the images of `json_document` (`save()` and
-`load()`). It uses each input twice: as an image, which `load()` must either reject with `parse_error.116` or read
-safely (with `image_check::full`, the document must also serialize to the JSON it reads as), and as a JSON text, whose
-image must load and serialize to the same text. A corpus of images can be made from JSON files with a small program
-that calls `json_document::parse(text).save()`; plain JSON files work as well.
-
 ## What the fuzzers check
 
 Each fuzzer driver (`tests/src/fuzzer-parse_*.cpp`) parses its input twice: once with `allow_exceptions = false` and

tests/src/fuzzer-json_view_image.cpp

@@ -1,95 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++ (supporting code)
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-License-Identifier: MIT
-
-/*
-This file implements a test of json_document images suitable for fuzz
-testing. The input is used twice:
-
-- as an image: json_document::load() with image_check::full must either throw
-  a parse_error or yield a document that serializes to the JSON text it reads
-  as; with image_check::bounds, reading and serializing must be safe (checked
-  by the sanitizers), and serializing may only throw type_error.316
-- as a JSON text: if json_document::parse() accepts it, the image of the
-  document must load (with every check) and serialize to the same text
-
-The provided function `LLVMFuzzerTestOneInput` can be used in different fuzzer
-drivers.
-*/
-
-#include <cassert>
-#include <cstdint>
-#include <string>
-#include <vector>
-#include <nlohmann/json.hpp>
-#include <nlohmann/json_view.hpp>
-
-// the checks below are assertions; NDEBUG would compile them away
-#ifdef NDEBUG
-    #error "the fuzzer drivers must be built without NDEBUG"
-#endif
-
-using json = nlohmann::json;
-using json_document = nlohmann::json_document;
-using image_check = json_document::image_check;
-
-// see http://llvm.org/docs/LibFuzzer.html
-extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
-{
-    // the input as an image
-    for (const image_check check :
-            {
-                image_check::full, image_check::bounds
-            })
-    {
-        json_document d;
-        try
-        {
-            d = json_document::load(data, size, check);
-        }
-        catch (const json::parse_error& e)
-        {
-            assert(e.id == 116);
-            continue;
-        }
-        std::string dumped;
-        try
-        {
-            dumped = d.root().dump();
-        }
-        catch (const json::type_error& e)
-        {
-            // invalid UTF-8 can only pass the bounds check
-            assert(check == image_check::bounds && e.id == 316);
-            continue;
-        }
-        const json j = d.root().materialize();
-        if (check == image_check::full)
-        {
-            assert(json::parse(dumped) == j);
-            // an image of the loaded document is the input
-            assert(d.save() == std::vector<std::uint8_t>(data, data + size));
-        }
-    }
-
-    // the input as a JSON text
-    const std::string text(reinterpret_cast<const char*>(data), size); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-    const json_document parsed = json_document::parse(text, false);
-    if (!parsed.is_discarded())
-    {
-        const std::vector<std::uint8_t> image = parsed.save();
-        for (const image_check check :
-                {
-                    image_check::full, image_check::bounds, image_check::none
-                })
-        {
-            const json_document loaded = json_document::load(image, check);
-            assert(loaded.root().dump() == parsed.root().dump());
-        }
-    }
-    return 0;
-}

tests/src/json_view_test_helpers.hpp

@@ -15,7 +15,6 @@
 #include <nlohmann/json_view.hpp>
 
 #include <algorithm> // any_of
-#include <functional> // function
 #include <random> // mt19937
 #include <string> // string
 
@@ -87,20 +86,4 @@ inline bool has_duplicate_keys(const nlohmann::ordered_json_view& v)
         return e.is_structured() && has_duplicate_keys(e);
     });
 }
-
-#if !defined(JSON_NOEXCEPTION)
-// the exception a call throws, or "" if it throws none
-inline std::string exception_of_call(const std::function<void()>& f)
-{
-    try
-    {
-        f();
-    }
-    catch (const nlohmann::json::exception& e)
-    {
-        return e.what();
-    }
-    return "";
-}
-#endif
 } // namespace json_view_test

tests/src/unit-binary_writer_sinks.cpp

@@ -11,10 +11,8 @@
 #include <nlohmann/json.hpp>
 using nlohmann::json;
 
-#include <array>
 #include <cstdint>
 #include <limits>
-#include <sstream>
 #include <string>
 #include <vector>
 
@@ -37,17 +35,6 @@ std::vector<json> test_values()
         big_object[std::to_string(i)] = i;
     }
 
-    // large strings and binary values between small ones: a write too large
-    // for the space the vector sink has ahead takes a different path than a
-    // small one, and the small writes after it must still land behind it
-    json large_payloads = json::array();
-    for (int i = 0; i < 50; ++i)
-    {
-        large_payloads.push_back(std::string(300, static_cast<char>('a' + (i % 26))));
-        large_payloads.push_back(i);
-        large_payloads.push_back(json::binary(std::vector<std::uint8_t>(static_cast<std::size_t>(100 * i), static_cast<std::uint8_t>(i))));
-    }
-
     return
     {
         json(nullptr), json(true), json(false),
@@ -59,23 +46,10 @@ std::vector<json> test_values()
         json::array(), json::object(),
         json::array({1, 2, 3}), json({{"a", 1}, {"b", nullptr}}),
         json({{"nested", {{"deep", json::array({1, "two", 3.0, nullptr})}}}}),
-        big_array, big_object, large_payloads,
-        json::binary(std::vector<std::uint8_t>(5000, 0x42))
+        big_array, big_object
     };
 }
 
-// explicit char -> uint8_t conversion (the iterator-range constructor converts implicitly, which -fsanitize=integer flags)
-std::vector<std::uint8_t> to_bytes(const std::string& str)
-{
-    std::vector<std::uint8_t> result;
-    result.reserve(str.size());
-    for (const char c : str)
-    {
-        result.push_back(static_cast<std::uint8_t>(c));
-    }
-    return result;
-}
-
 // BON8 has no integers above the int64 range, so to_bon8() rejects them
 bool bon8_representable(const json& j)
 {
@@ -196,258 +170,6 @@ TEST_CASE("binary writer output sinks")
     }
 }
 
-namespace
-{
-
-// the CBOR head of an integer, encoded independently of binary_writer
-void reference_cbor_head(std::vector<std::uint8_t>& out, const std::uint8_t major_type, const std::uint64_t argument)
-{
-    if (argument <= 23)
-    {
-        out.push_back(static_cast<std::uint8_t>(major_type + argument));
-        return;
-    }
-
-    int length = 8;
-    std::uint8_t additional = 27;
-    if (argument <= 0xFF)
-    {
-        length = 1;
-        additional = 24;
-    }
-    else if (argument <= 0xFFFF)
-    {
-        length = 2;
-        additional = 25;
-    }
-    else if (argument <= 0xFFFFFFFF)
-    {
-        length = 4;
-        additional = 26;
-    }
-
-    out.push_back(static_cast<std::uint8_t>(major_type + additional));
-    for (int i = length - 1; i >= 0; --i)
-    {
-        out.push_back(static_cast<std::uint8_t>(argument >> (8 * i)));
-    }
-}
-
-// the CBOR encoding of an integer value
-void reference_cbor_integer(std::vector<std::uint8_t>& out, const json& j)
-{
-    if (j.is_number_unsigned())
-    {
-        reference_cbor_head(out, 0x00, j.get<std::uint64_t>());
-        return;
-    }
-
-    const auto n = j.get<std::int64_t>();
-    if (n >= 0)
-    {
-        reference_cbor_head(out, 0x00, static_cast<std::uint64_t>(n));
-    }
-    else
-    {
-        reference_cbor_head(out, 0x20, static_cast<std::uint64_t>(-1 - n));
-    }
-}
-
-// the MessagePack encoding of an integer value, encoded independently of
-// binary_writer
-void reference_msgpack_integer(std::vector<std::uint8_t>& out, const json& j)
-{
-    const auto put = [&out](const std::uint8_t marker, const std::uint64_t bits, const int length)
-    {
-        out.push_back(marker);
-        for (int i = length - 1; i >= 0; --i)
-        {
-            out.push_back(static_cast<std::uint8_t>(bits >> (8 * i)));
-        }
-    };
-
-    if (j.is_number_unsigned() || j.get<std::int64_t>() >= 0)
-    {
-        const auto u = j.get<std::uint64_t>();
-        if (u < 128)
-        {
-            out.push_back(static_cast<std::uint8_t>(u));
-        }
-        else if (u <= 0xFF)
-        {
-            put(0xCC, u, 1);
-        }
-        else if (u <= 0xFFFF)
-        {
-            put(0xCD, u, 2);
-        }
-        else if (u <= 0xFFFFFFFF)
-        {
-            put(0xCE, u, 4);
-        }
-        else
-        {
-            put(0xCF, u, 8);
-        }
-        return;
-    }
-
-    const auto n = j.get<std::int64_t>();
-    const auto bits = static_cast<std::uint64_t>(n);
-    if (n >= -32)
-    {
-        out.push_back(static_cast<std::uint8_t>(bits));
-    }
-    else if (n >= -128)
-    {
-        put(0xD0, bits, 1);
-    }
-    else if (n >= -32768)
-    {
-        put(0xD1, bits, 2);
-    }
-    else if (n >= -2147483648LL)
-    {
-        put(0xD2, bits, 4);
-    }
-    else
-    {
-        put(0xD3, bits, 8);
-    }
-}
-
-// integers at every boundary of the CBOR and MessagePack sizes, signed and
-// unsigned
-std::vector<json> boundary_integers()
-{
-    std::vector<json> result;
-    const std::array<std::uint64_t, 38> boundaries =
-    {
-        {
-            0, 1, 22, 23, 24, 25, 31, 32, 33, 126, 127, 128, 129, 254, 255, 256, 257,
-            32766, 32767, 32768, 32769, 65534, 65535, 65536, 65537,
-            2147483646ULL, 2147483647ULL, 2147483648ULL, 2147483649ULL,
-            4294967294ULL, 4294967295ULL, 4294967296ULL, 4294967297ULL,
-            9223372036854775806ULL, 9223372036854775807ULL, 9223372036854775808ULL,
-            18446744073709551614ULL, 18446744073709551615ULL
-        }
-    };
-    for (const std::uint64_t u : boundaries)
-    {
-        result.emplace_back(u);
-        if (u <= static_cast<std::uint64_t>((std::numeric_limits<std::int64_t>::max)()))
-        {
-            const auto n = static_cast<std::int64_t>(u);
-            result.emplace_back(n);
-            result.emplace_back(-n);
-            result.emplace_back(-n - 1);
-        }
-    }
-    return result;
-}
-
-} // namespace
-
-// Arrays of integers are written in runs straight into space reserved from the
-// sink, with branch-free encodings; check them against independent encoders for
-// runs shorter and longer than one reservation, broken up by other values, and
-// through each sink.
-TEST_CASE("CBOR and MessagePack integer arrays")
-{
-    const std::vector<json> integers = boundary_integers();
-
-    for (const std::size_t length :
-            {
-                std::size_t{1}, std::size_t{27}, std::size_t{28}, std::size_t{29}, std::size_t{57}, std::size_t{1000}
-            })
-    {
-        for (const std::size_t break_every :
-                {
-                    std::size_t{0}, std::size_t{1}, std::size_t{7}, std::size_t{28}
-                })
-        {
-            CAPTURE(length)
-            CAPTURE(break_every)
-
-            json array = json::array();
-            std::vector<std::uint8_t> expected_cbor;
-            std::vector<std::uint8_t> expected_msgpack;
-            for (std::size_t i = 0; i < length; ++i)
-            {
-                if (break_every != 0 && i % (break_every + 1) == break_every)
-                {
-                    array.push_back("x");
-                    expected_cbor.push_back(0x61);
-                    expected_cbor.push_back('x');
-                    expected_msgpack.push_back(0xA1);
-                    expected_msgpack.push_back('x');
-                }
-                else
-                {
-                    const json& value = integers[(i * 7) % integers.size()];
-                    array.push_back(value);
-                    reference_cbor_integer(expected_cbor, value);
-                    reference_msgpack_integer(expected_msgpack, value);
-                }
-            }
-
-            std::vector<std::uint8_t> head;
-            reference_cbor_head(head, 0x80, length);
-            expected_cbor.insert(expected_cbor.begin(), head.begin(), head.end());
-
-            head.clear();
-            if (length <= 15)
-            {
-                head.push_back(static_cast<std::uint8_t>(0x90 + length));
-            }
-            else
-            {
-                head = {0xDC, static_cast<std::uint8_t>(length >> 8), static_cast<std::uint8_t>(length)};
-            }
-            expected_msgpack.insert(expected_msgpack.begin(), head.begin(), head.end());
-
-            CHECK(json::to_cbor(array) == expected_cbor);
-            CHECK(json::to_msgpack(array) == expected_msgpack);
-
-            std::vector<std::uint8_t> through_adapter = {0xAA};
-            json::to_cbor(array, through_adapter);
-            CHECK(std::vector<std::uint8_t>(through_adapter.begin() + 1, through_adapter.end()) == expected_cbor);
-            through_adapter = {0xAA};
-            json::to_msgpack(array, through_adapter);
-            CHECK(std::vector<std::uint8_t>(through_adapter.begin() + 1, through_adapter.end()) == expected_msgpack);
-
-            std::ostringstream stream;
-            json::to_cbor(array, stream);
-            std::string streamed = stream.str();
-            CHECK(to_bytes(streamed) == expected_cbor);
-            stream.str("");
-            json::to_msgpack(array, stream);
-            streamed = stream.str();
-            CHECK(to_bytes(streamed) == expected_msgpack);
-
-            CHECK(json::from_cbor(expected_cbor) == array);
-            CHECK(json::from_msgpack(expected_msgpack) == array);
-
-            // the same array as object members
-            const json object = {{"a", array}, {"b", array}};
-            CHECK(json::from_cbor(json::to_cbor(object)) == object);
-            CHECK(json::from_msgpack(json::to_msgpack(object)) == object);
-        }
-    }
-
-    // single values, outside an array
-    for (const auto& value : integers)
-    {
-        CAPTURE(value)
-        std::vector<std::uint8_t> expected;
-        reference_cbor_integer(expected, value);
-        CHECK(json::to_cbor(value) == expected);
-        expected.clear();
-        reference_msgpack_integer(expected, value);
-        CHECK(json::to_msgpack(value) == expected);
-    }
-}
-
 // binary_reserve_hint() is documented as a *lower* bound on the serialized size,
 // so that reserving it up front can never leave the returned vector holding
 // capacity beyond what the value actually needs.
@@ -492,278 +214,3 @@ TEST_CASE("binary_reserve_hint never over-reserves")
         CHECK(nlohmann::detail::binary_reserve_hint(json({{"a", 1}, {"b", 2}})) == 5);
     }
 }
-
-namespace
-{
-
-// numbers around every boundary of the integer encodings, and floats of each
-// kind (exact in float, needing double, special values)
-std::vector<json> boundary_numbers()
-{
-    std::vector<json> numbers;
-    for (int k = 0; k < 64; ++k)
-    {
-        const std::uint64_t p = std::uint64_t{1} << k;
-        for (const std::uint64_t d :
-                {
-                    p - 1, p, p + 1
-                })
-        {
-            numbers.emplace_back(d);
-            if (d <= static_cast<std::uint64_t>((std::numeric_limits<std::int64_t>::max)()))
-            {
-                numbers.emplace_back(static_cast<std::int64_t>(d));
-                numbers.emplace_back(-static_cast<std::int64_t>(d));
-                numbers.emplace_back(-static_cast<std::int64_t>(d) - 1);
-            }
-        }
-    }
-    numbers.emplace_back((std::numeric_limits<std::int64_t>::min)());
-    numbers.emplace_back((std::numeric_limits<std::uint64_t>::max)());
-    for (const double f :
-            {
-                0.0, -0.0, 1.0, -1.0, 0.5, 0.1, 3.25, 1e300, -1e-300, 3.4028234663852886e38, 1e39,
-                std::numeric_limits<double>::infinity(), -std::numeric_limits<double>::infinity(),
-                std::numeric_limits<double>::quiet_NaN()
-            })
-    {
-        numbers.emplace_back(f);
-    }
-    return numbers;
-}
-
-// the concatenation of the encodings of the elements of @a numbers[first, first + count)
-template<typename Single>
-std::vector<std::uint8_t> concat_singles(const std::vector<json>& numbers, const std::size_t first, const std::size_t count, Single single)
-{
-    std::vector<std::uint8_t> bytes;
-    for (std::size_t i = first; i < first + count; ++i)
-    {
-        const auto one = single(numbers[i]);
-        bytes.insert(bytes.end(), one.begin(), one.end());
-    }
-    return bytes;
-}
-
-} // namespace
-
-// Runs of numbers in arrays are encoded straight into space reserved from the
-// sink, by code that is separate from the encoding of a single value. Both have
-// to agree on every number: an array is its head and the encodings of its
-// elements, one after the other.
-TEST_CASE("runs of numbers in arrays are encoded as the numbers one by one")
-{
-    const std::vector<json> numbers = boundary_numbers();
-
-    // arrays of every length that a one-byte head covers, so that runs are as
-    // long as, and longer and shorter than, what fits one reservation
-    for (const std::size_t count :
-            {
-                1u, 2u, 3u, 5u, 14u, 15u, 23u
-            })
-    {
-        for (std::size_t first = 0; first + count <= numbers.size(); first += 7)
-        {
-            const json array(std::vector<json>(numbers.begin() + static_cast<std::ptrdiff_t>(first),
-                                               numbers.begin() + static_cast<std::ptrdiff_t>(first + count)));
-            CAPTURE(array.dump(-1, ' ', false, json::error_handler_t::replace))
-
-            std::vector<std::uint8_t> expected{static_cast<std::uint8_t>(0x80 + count)};
-            auto elements = concat_singles(numbers, first, count, [](const json & j)
-            {
-                return json::to_cbor(j);
-            });
-            expected.insert(expected.end(), elements.begin(), elements.end());
-            CHECK(json::to_cbor(array) == expected);
-
-            expected.assign(1, static_cast<std::uint8_t>(count <= 15 ? 0x90 + count : 0xDC));
-            if (count > 15)
-            {
-                expected.push_back(0);
-                expected.push_back(static_cast<std::uint8_t>(count));
-            }
-            elements = concat_singles(numbers, first, count, [](const json & j)
-            {
-                return json::to_msgpack(j);
-            });
-            expected.insert(expected.end(), elements.begin(), elements.end());
-            CHECK(json::to_msgpack(array) == expected);
-
-            for (const bool bjdata :
-                    {
-                        false, true
-                    })
-            {
-                expected.assign(1, static_cast<std::uint8_t>('['));
-                elements = concat_singles(numbers, first, count, [bjdata](const json & j)
-                {
-                    return bjdata ? json::to_bjdata(j) : json::to_ubjson(j);
-                });
-                expected.insert(expected.end(), elements.begin(), elements.end());
-                expected.push_back(static_cast<std::uint8_t>(']'));
-                CHECK((bjdata ? json::to_bjdata(array) : json::to_ubjson(array)) == expected);
-            }
-
-            // BON8 has no integers above the int64 range
-            bool representable = true;
-            for (std::size_t i = first; i < first + count; ++i)
-            {
-                representable = representable && bon8_representable(numbers[i]);
-            }
-            if (representable)
-            {
-                expected.assign(1, static_cast<std::uint8_t>(count <= 4 ? 0x80 + count : 0x85));
-                elements = concat_singles(numbers, first, count, [](const json & j)
-                {
-                    return json::to_bon8(j);
-                });
-                expected.insert(expected.end(), elements.begin(), elements.end());
-                if (count > 4)
-                {
-                    expected.push_back(0xFE);
-                }
-                CHECK(json::to_bon8(array) == expected);
-            }
-            else
-            {
-                CHECK_THROWS_AS(json::to_bon8(array), json::out_of_range&);
-            }
-        }
-    }
-}
-
-// An array that is written in more than one reservation (more numbers than fit
-// one), and arrays of an index with more digits, round trip for every format.
-TEST_CASE("large arrays and many digits of indices round trip")
-{
-    json array = json::array();
-    for (int i = 0; i < 12000; ++i)
-    {
-        switch (i % 4)
-        {
-            case 0:
-                array.push_back(i);
-                break;
-            case 1:
-                array.push_back(-i);
-                break;
-            case 2:
-                array.push_back(i * 0.25);
-                break;
-            default:
-                array.push_back(i % 8 == 3);
-                break;
-        }
-    }
-    json document = json::object();
-    document["numbers"] = array;
-    document["nested"] = json::array({array, "text", array});
-
-    CHECK(json::from_cbor(json::to_cbor(document)) == document);
-    CHECK(json::from_msgpack(json::to_msgpack(document)) == document);
-    CHECK(json::from_ubjson(json::to_ubjson(document)) == document);
-    CHECK(json::from_ubjson(json::to_ubjson(document, true, true)) == document);
-    CHECK(json::from_bjdata(json::to_bjdata(document)) == document);
-    CHECK(json::from_bson(json::to_bson(document)) == document);
-    CHECK(json::from_bon8(json::to_bon8(document)) == document);
-}
-
-// Strings and keys are written with their head in one reservation up to a
-// length; around that length, and with every kind of head, they must read back.
-TEST_CASE("strings of every head length round trip")
-{
-    json document = json::object();
-    json array = json::array();
-    for (const std::size_t length :
-            {
-                0u, 1u, 2u, 3u, 4u, 7u, 8u, 15u, 16u, 17u, 23u, 24u, 25u, 31u, 32u, 33u, 63u, 127u, 128u, 129u, 200u, 245u, 246u, 247u, 248u, 249u, 250u, 251u, 252u, 253u, 254u, 255u, 256u, 257u, 300u, 1000u, 65535u, 65536u, 70000u
-            })
-    {
-        const std::string text(length, 'x');
-        array.push_back(text);
-        document[std::string(length, 'k')] = text;
-    }
-    document["array"] = array;
-
-    CHECK(json::from_cbor(json::to_cbor(document)) == document);
-    CHECK(json::from_msgpack(json::to_msgpack(document)) == document);
-    CHECK(json::from_ubjson(json::to_ubjson(document)) == document);
-    CHECK(json::from_ubjson(json::to_ubjson(document, true, true)) == document);
-    CHECK(json::from_bjdata(json::to_bjdata(document)) == document);
-    CHECK(json::from_bson(json::to_bson(document)) == document);
-    CHECK(json::from_bon8(json::to_bon8(document)) == document);
-}
-
-#if !defined(JSON_NOEXCEPTION)
-// What a write that throws leaves behind in an output adapter is what was written
-// before it, whatever the adapter and however the adapter sink buffers. (Without
-// exceptions, the writes in CHECK_THROWS_AS do not run.)
-TEST_CASE("a write that throws leaves the same bytes in every kind of output")
-{
-    json array = json::array();
-    for (int i = 0; i < 700; ++i)
-    {
-        array.push_back(i * 1000);
-        array.push_back("text " + std::to_string(i));
-    }
-    array.push_back("bad \xFF byte");
-    json document = json::object();
-    document["first"] = array;
-    document["second"] = 1;
-
-    const auto strict = json::error_handler_t::strict;
-
-    SECTION("cbor")
-    {
-        std::vector<std::uint8_t> as_vector;
-        std::string as_string;
-        std::ostringstream as_stream;
-        CHECK_THROWS_AS(json::to_cbor(document, as_vector, strict), json::type_error&);
-        CHECK_THROWS_AS(json::to_cbor(document, as_string, strict), json::type_error&);
-        CHECK_THROWS_AS(json::to_cbor(document, as_stream, strict), json::type_error&);
-        CHECK(!as_vector.empty());
-        CHECK(std::string(reinterpret_cast<const char*>(as_vector.data()), as_vector.size()) == as_string); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-        CHECK(as_stream.str() == as_string);
-    }
-
-    SECTION("msgpack")
-    {
-        std::vector<std::uint8_t> as_vector;
-        std::string as_string;
-        std::ostringstream as_stream;
-        CHECK_THROWS_AS(json::to_msgpack(document, as_vector, strict), json::type_error&);
-        CHECK_THROWS_AS(json::to_msgpack(document, as_string, strict), json::type_error&);
-        CHECK_THROWS_AS(json::to_msgpack(document, as_stream, strict), json::type_error&);
-        CHECK(!as_vector.empty());
-        CHECK(std::string(reinterpret_cast<const char*>(as_vector.data()), as_vector.size()) == as_string); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-        CHECK(as_stream.str() == as_string);
-    }
-
-    SECTION("ubjson")
-    {
-        std::vector<std::uint8_t> as_vector;
-        std::string as_string;
-        std::ostringstream as_stream;
-        CHECK_THROWS_AS(json::to_ubjson(document, as_vector, false, false, strict), json::type_error&);
-        CHECK_THROWS_AS(json::to_ubjson(document, as_string, false, false, strict), json::type_error&);
-        CHECK_THROWS_AS(json::to_ubjson(document, as_stream, false, false, strict), json::type_error&);
-        CHECK(!as_vector.empty());
-        CHECK(std::string(reinterpret_cast<const char*>(as_vector.data()), as_vector.size()) == as_string); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-        CHECK(as_stream.str() == as_string);
-    }
-
-    SECTION("bson")
-    {
-        // the size pass finds the string before anything is written
-        std::vector<std::uint8_t> as_vector;
-        std::string as_string;
-        std::ostringstream as_stream;
-        CHECK_THROWS_AS(json::to_bson(document, as_vector, strict), json::type_error&);
-        CHECK_THROWS_AS(json::to_bson(document, as_string, strict), json::type_error&);
-        CHECK_THROWS_AS(json::to_bson(document, as_stream, strict), json::type_error&);
-        CHECK(as_vector.empty());
-        CHECK(as_string.empty());
-        CHECK(as_stream.str().empty());
-    }
-}
-#endif

tests/src/unit-class_lexer.cpp

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