Merge branch 'develop' into json-view/5869-7-check-utf8

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

.github/CONTRIBUTING.md

@@ -154,11 +154,6 @@ and each page's title (H1) and declaration by
 [`docs/docset/generate_docset.py`](https://github.com/nlohmann/json/blob/develop/docs/docset/generate_docset.py);
 `make build` reports API pages that cannot be classified.
 
-A pull request that changes only the documentation, Markdown files, GitHub metadata, or license files skips the
-compiler workflows (Ubuntu, macOS, Windows); the documentation and license checks still run. See
-[`tools/check_path_filters`](https://github.com/nlohmann/json/tree/develop/tools/check_path_filters) for the list of
-skipped files and what to do when a compiler job starts reading one of them.
-
 ### Amalgamate the source code
 
 The single-header files

.github/workflows/macos.yml

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

.github/workflows/repository_checks.yml

@@ -1,78 +0,0 @@
-name: Repository checks
-
-# Checks that concern files the compiler workflows (ubuntu.yml, macos.yml,
-# windows.yml) skip with their path filter: the documentation, the license
-# information, and the path filter itself. This workflow has no path filter.
-on:
-  push:
-    branches:
-      - develop
-      - master
-      - release/*
-  pull_request:
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref || github.run_id }}
-  cancel-in-progress: true
-
-jobs:
-  check_path_filters:
-    runs-on: ubuntu-26.04
-    steps:
-      - name: Harden Runner
-        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
-        with:
-          egress-policy: audit
-
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
-        with:
-          persist-credentials: false
-      - name: Check the path filters of the compiler workflows
-        run: python3 tools/check_path_filters/check_path_filters.py
-
-  ci_reuse_compliance:
-    runs-on: ubuntu-26.04
-    steps:
-      - name: Harden Runner
-        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
-        with:
-          egress-policy: audit
-
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
-        with:
-          persist-credentials: false
-      - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@a89e43e22a96abafcd7a62db652a65ecd33052c9 # v4.4.4
-      - name: Run CMake
-        run: cmake -S . -B build -DJSON_CI=On
-      - name: Build
-        run: cmake --build build --target ci_reuse_compliance
-
-  ci_test_documentation:
-    runs-on: ubuntu-26.04
-    strategy:
-      matrix:
-        target: [ci_test_examples, ci_test_build_documentation, ci_test_documentation_mermaid]
-    steps:
-      - name: Harden Runner
-        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
-        with:
-          egress-policy: audit
-
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
-        with:
-          persist-credentials: false
-          # the git-revision-date-localized plugin needs the history; a shallow clone makes the strict build fail
-          fetch-depth: ${{ matrix.target == 'ci_test_build_documentation' && '0' || '1' }}
-      - uses: actions/setup-node@949feb2413d6458794dcd2491c4babbbce0c15c1 # v7.1.0
-        if: matrix.target == 'ci_test_documentation_mermaid'
-        with:
-          node-version: 24
-      - name: Run CMake
-        run: cmake -S . -B build -DJSON_CI=On
-      - name: Build
-        run: cmake --build build --target ${{ matrix.target }}

.github/workflows/ubuntu.yml

@@ -7,25 +7,6 @@ on:
       - master
       - release/*
   pull_request:
-    # Skip pull requests that change only files no job here reads. The list is checked by
-    # tools/check_path_filters/check_path_filters.py (repository_checks.yml); change both together.
-    paths:
-      - '**'
-      - '!docs/**'
-      - '!**.md'
-      - '!.github/*'
-      - '!.github/ISSUE_TEMPLATE/**'
-      - '!.github/external_ci/**'
-      - '!.github/workflows/**'
-      - '!.reuse/**'
-      - '!LICENSES/**'
-      - '!CITATION.cff'
-      - '!REUSE.toml'
-      # read by tools/check_build_options in the ci_meson_install job (ubuntu.yml)
-      - 'docs/mkdocs/docs/integration/package_managers.md'
-      # built by the swiftpm job (macos.yml)
-      - 'docs/mkdocs/docs/integration/swift/**'
-      - '.github/workflows/ubuntu.yml'
   workflow_dispatch:
 
 permissions:
@@ -128,7 +109,7 @@ jobs:
     runs-on: ubuntu-26.04
     strategy:
       matrix:
-        target: [ci_test_single_header, ci_cppcheck, ci_cpplint, ci_reproducible_tests, ci_non_git_tests, ci_offline_testdata, ci_test_valgrind]
+        target: [ci_test_single_header, ci_cppcheck, ci_cpplint, ci_reproducible_tests, ci_non_git_tests, ci_offline_testdata, ci_reuse_compliance, ci_test_valgrind]
     steps:
       - name: Harden Runner
         uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
@@ -468,6 +449,31 @@ jobs:
       - name: Build
         run: cmake --build build
 
+  ci_test_documentation:
+    runs-on: ubuntu-26.04
+    strategy:
+      matrix:
+        target: [ci_test_examples, ci_test_build_documentation, ci_test_documentation_mermaid]
+    steps:
+      - name: Harden Runner
+        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
+        with:
+          egress-policy: audit
+
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+          # the git-revision-date-localized plugin needs the history; a shallow clone makes the strict build fail
+          fetch-depth: ${{ matrix.target == 'ci_test_build_documentation' && '0' || '1' }}
+      - uses: actions/setup-node@949feb2413d6458794dcd2491c4babbbce0c15c1 # v7.1.0
+        if: matrix.target == 'ci_test_documentation_mermaid'
+        with:
+          node-version: 24
+      - name: Run CMake
+        run: cmake -S . -B build -DJSON_CI=On
+      - name: Build
+        run: cmake --build build --target ${{ matrix.target }}
+
   # Native Linux ARM64 runner with the latest GCC. The ubuntu-24.04-arm label is
   # only available for public repositories.
   ci_test_arm64:

.github/workflows/windows.yml

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

include/nlohmann/detail/view/edit.hpp

@@ -26,6 +26,7 @@
 #include <nlohmann/detail/view/lookup.hpp>
 #include <nlohmann/detail/view/macro_scope.hpp>
 #include <nlohmann/detail/view/node.hpp>
+#include <nlohmann/detail/view/scan.hpp>
 #include <nlohmann/detail/view/view_mode.hpp>
 
 NLOHMANN_JSON_NAMESPACE_BEGIN
@@ -46,10 +47,9 @@ struct first_true<false, Conditions...> : std::integral_constant < int, 1 + firs
 /// (type_error.316 with the same message), so that an editable document
 /// only holds valid UTF-8: the error is at the first byte that no
 /// well-formed sequence can continue with (Unicode, Table 3-7).
-inline void check_utf8(const char* s, std::size_t n)
+NLOHMANN_VIEW_ALWAYS_INLINE void check_utf8_bytewise(const unsigned char* p, std::size_t n, std::size_t i)
 {
-    const auto* const p = reinterpret_cast<const unsigned char*>(s); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-    for (std::size_t i = 0; i < n;)
+    for (; i < n;)
     {
         const unsigned char c = p[i];
         if (c < 0x80)
@@ -79,6 +79,43 @@ inline void check_utf8(const char* s, std::size_t n)
     }
 }
 
+/// The long-string path of check_utf8(): skips well-formed runs with the
+/// parser's string scan (which stops at a quote, a backslash, or a control
+/// character, all legal here, and at ill-formed UTF-8); the byte-wise check
+/// runs only from where the scan found ill-formed UTF-8, to report it.
+NLOHMANN_VIEW_NOINLINE inline void check_utf8_scan(const unsigned char* p, std::size_t n)
+{
+    const unsigned char* const e = p + n;
+    const unsigned char* q = p;
+    for (;;)
+    {
+        q = scan_string_run<true>(q, e);
+        if (q == e)
+        {
+            return;
+        }
+        if (*q >= 0x80)
+        {
+            check_utf8_bytewise(p, n, static_cast<std::size_t>(q - p));
+            return; // not reached: the scan stopped at ill-formed UTF-8
+        }
+        ++q; // a quote, backslash, or control character
+    }
+}
+
+inline void check_utf8(const char* s, std::size_t n)
+{
+    const auto* const p = reinterpret_cast<const unsigned char*>(s); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+    if (NLOHMANN_VIEW_UNLIKELY(n >= 32))
+    {
+        check_utf8_scan(p, n);
+        return;
+    }
+    // short strings: the vector scan costs more than it saves; (the loop is
+    // inlined with a constant start, so this path is the plain byte-wise check)
+    check_utf8_bytewise(p, n, 0);
+}
+
 /*!
 @brief the edits of an editable basic_json_document
 

single_include/nlohmann/json_view.hpp

@@ -3740,6 +3740,8 @@ NLOHMANN_JSON_NAMESPACE_END
 
 // #include <nlohmann/detail/view/node.hpp>
 
+// #include <nlohmann/detail/view/scan.hpp>
+
 // #include <nlohmann/detail/view/view_mode.hpp>
 //     __ _____ _____ _____
 //  __|  |   __|     |   | |  JSON for Modern C++
@@ -3813,10 +3815,9 @@ struct first_true<false, Conditions...> : std::integral_constant < int, 1 + firs
 /// (type_error.316 with the same message), so that an editable document
 /// only holds valid UTF-8: the error is at the first byte that no
 /// well-formed sequence can continue with (Unicode, Table 3-7).
-inline void check_utf8(const char* s, std::size_t n)
+NLOHMANN_VIEW_ALWAYS_INLINE void check_utf8_bytewise(const unsigned char* p, std::size_t n, std::size_t i)
 {
-    const auto* const p = reinterpret_cast<const unsigned char*>(s); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-    for (std::size_t i = 0; i < n;)
+    for (; i < n;)
     {
         const unsigned char c = p[i];
         if (c < 0x80)
@@ -3846,6 +3847,43 @@ inline void check_utf8(const char* s, std::size_t n)
     }
 }
 
+/// The long-string path of check_utf8(): skips well-formed runs with the
+/// parser's string scan (which stops at a quote, a backslash, or a control
+/// character, all legal here, and at ill-formed UTF-8); the byte-wise check
+/// runs only from where the scan found ill-formed UTF-8, to report it.
+NLOHMANN_VIEW_NOINLINE inline void check_utf8_scan(const unsigned char* p, std::size_t n)
+{
+    const unsigned char* const e = p + n;
+    const unsigned char* q = p;
+    for (;;)
+    {
+        q = scan_string_run<true>(q, e);
+        if (q == e)
+        {
+            return;
+        }
+        if (*q >= 0x80)
+        {
+            check_utf8_bytewise(p, n, static_cast<std::size_t>(q - p));
+            return; // not reached: the scan stopped at ill-formed UTF-8
+        }
+        ++q; // a quote, backslash, or control character
+    }
+}
+
+inline void check_utf8(const char* s, std::size_t n)
+{
+    const auto* const p = reinterpret_cast<const unsigned char*>(s); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+    if (NLOHMANN_VIEW_UNLIKELY(n >= 32))
+    {
+        check_utf8_scan(p, n);
+        return;
+    }
+    // short strings: the vector scan costs more than it saves; (the loop is
+    // inlined with a constant start, so this path is the plain byte-wise check)
+    check_utf8_bytewise(p, n, 0);
+}
+
 /*!
 @brief the edits of an editable basic_json_document
 

tests/src/unit-json_view_edit.cpp

@@ -941,3 +941,123 @@ TEST_CASE("json_view edits: duplicate keys")
         CHECK(d.root()["o"]["d"].get<int>() == 0);
     }
 }
+
+#if !defined(JSON_NOEXCEPTION)
+TEST_CASE("json_view edits: check_utf8 agrees with the byte-wise check")
+{
+    namespace dv = nlohmann::detail::view;
+
+    // "ok" or the exception message
+    const auto run = [](bool fast, const std::string & s) -> std::string
+    {
+        try
+        {
+            if (fast)
+            {
+                dv::check_utf8(s.data(), s.size());
+            }
+            else
+            {
+                dv::check_utf8_bytewise(reinterpret_cast<const unsigned char*>(s.data()), s.size(), 0);
+            }
+        }
+        catch (const json::type_error& e)
+        {
+            return {e.what()};
+        }
+        return {"ok"};
+    };
+    std::size_t errors = 0;
+    const auto same = [&](const std::string & s)
+    {
+        const std::string a = run(true, s);
+        const std::string b = run(false, s);
+        if (a != b)
+        {
+            INFO("fast: " << a << ", byte-wise: " << b << ", length " << s.size());
+            CHECK(a == b);
+        }
+        errors += b != "ok" ? 1u : 0u;
+    };
+
+    const std::vector<std::string> pieces =
+    {
+        "a", "Z", " ", "\"", "\\", "\n", "\x01", "\x7f", "\xc3\xa4", "\xe4\xb8\xad", "\xf0\x9f\x98\x80",
+        "\x80", "\xbf", "\xc0\x80", "\xc1\xbf", "\xc2", "\xe0\x80\x80", "\xe0\x9f\xbf", "\xed\xa0\x80", "\xed\xbf\xbf",
+        "\xf0\x80\x80\x80", "\xf0\x8f\xbf\xbf", "\xf4\x90\x80\x80", "\xf4\x8f\xbf\xbf", "\xf5", "\xf8", "\xff", "\xfe",
+        "\xe4\xb8", "\xf0\x9f\x98", "\xf0\x9f", "\xf0"
+    };
+
+    // every piece behind prefixes of every length, and followed by more bytes
+    for (std::size_t prefix = 0; prefix <= 64; ++prefix)
+    {
+        for (const auto& piece : pieces)
+        {
+            same(std::string(prefix, 'x') + piece);
+            same(std::string(prefix, 'x') + piece + "yz");
+            same(std::string(prefix, '"') + piece);
+            same(std::string(prefix, '\xc3') + piece);
+            same(std::string(prefix / 2, '\xc3').append(prefix / 2, '\xa4') + piece);
+            same(std::string(prefix, 'x') + "\xe4\xb8\xad" + piece);
+        }
+    }
+    // an invalid byte at every position of valid strings of every length
+    for (std::size_t len = 0; len <= 64; ++len)
+    {
+        const std::string ascii(len, 'a');
+        std::string mixed;
+        while (mixed.size() < len)
+        {
+            if (mixed.size() % 7 == 0)
+            {
+                mixed += "\xc3\xa4";
+            }
+            else if (mixed.size() % 11 == 0)
+            {
+                mixed += "\xf0\x9f\x98\x80";
+            }
+            else
+            {
+                mixed += "a";
+            }
+        }
+        same(ascii);
+        same(mixed);
+        for (std::size_t pos = 0; pos < len; ++pos)
+        {
+            for (const char bad :
+                    {'\x80', '\xc0', '\xc2', '\xe0', '\xf4', '\xff', '"', '\\', '\x1f'
+                    })
+            {
+                std::string s = ascii;
+                s[pos] = bad;
+                same(s);
+                s = mixed;
+                s[pos] = bad;
+                same(s);
+            }
+        }
+    }
+    // random bytes, biased to the interesting ones
+    std::mt19937 gen(5869); // NOLINT(cert-msc32-c,cert-msc51-cpp,bugprone-random-generator-seed): reproducible
+    static const std::array<unsigned char, 23> interesting = {{0x00, 0x1f, 0x22, 0x5c, 0x7f, 0x80, 0x8f, 0x90, 0x9f, 0xa0, 0xbf, 0xc0, 0xc2, 0xdf, 0xe0, 0xe1, 0xed, 0xef, 0xf0, 0xf1, 0xf4, 0xf5, 0xff}};
+    for (int i = 0; i < 100000; ++i)
+    {
+        std::string s(gen() % 80, 'a');
+        for (auto& c : s)
+        {
+            const unsigned r = gen() % 8;
+            if (r == 0)
+            {
+                c = static_cast<char>(gen() & 0xff);
+            }
+            else if (r == 1)
+            {
+                c = static_cast<char>(interesting[gen() % interesting.size()]);
+            }
+        }
+        same(s);
+    }
+    CHECK(errors > 1000);
+}
+#endif

tools/check_path_filters/README.md

@@ -1,34 +0,0 @@
-# check_path_filters
-
-The compiler workflows [`ubuntu.yml`](../../.github/workflows/ubuntu.yml),
-[`macos.yml`](../../.github/workflows/macos.yml), and [`windows.yml`](../../.github/workflows/windows.yml) skip pull
-requests that change only files no compiler job reads: the documentation, Markdown files, GitHub metadata, other
-workflows, and the license files. Pushes to `develop`, `master`, and `release/*` always run them. The documentation,
-license, and path-filter checks run in [`repository_checks.yml`](../../.github/workflows/repository_checks.yml), which
-has no path filter.
-
-The filter starts with `'**'` and excludes these files explicitly, so a new file runs the compiler workflows unless it
-is excluded on purpose. [`check_path_filters.py`](check_path_filters.py) holds the filter (`PATHS`) and checks that
-
-- each of the three workflows has exactly this filter, with its own workflow file included,
-- the CI targets that read excluded files (`UNFILTERED_TARGETS`) do not run in these workflows, and
-- no file the filter keeps (sources, tests, build files, tools, workflows) mentions an excluded file or directory
-  outside a comment line, unless the mention is listed in `KNOWN_REFERENCES` with a reason.
-
-When the check reports a mention, decide whether a compiler job reads that file:
-
-- If it does, include the file in `PATHS` after the exclusions (as `package_managers.md` and the Swift example are) and
-  copy the new filter into the three workflows.
-- If it does not, add the mention to `KNOWN_REFERENCES` with the reason.
-
-Run the check with
-
-```shell
-python3 tools/check_path_filters/check_path_filters.py
-```
-
-To see which workflows a pull request would run, pass the changed files:
-
-```shell
-python3 tools/check_path_filters/check_path_filters.py --changed $(git diff --name-only origin/develop)
-```

tools/check_path_filters/check_path_filters.py

@@ -1,269 +0,0 @@
-#!/usr/bin/env python3
-"""Check the path filters of the compiler workflows.
-
-ubuntu.yml, macos.yml and windows.yml skip pull requests that change only files
-no compiler job reads (documentation, Markdown files, GitHub metadata, license
-files). The filter starts with '**' and excludes these files explicitly, so a
-new file runs the workflows unless it is excluded on purpose.
-
-The script checks that
-
-- each of the three workflows has exactly the filter defined in PATHS below,
-  with its own workflow file included, and
-- no tracked file that the filter keeps (sources, tests, build files, tools,
-  workflows) mentions a file the filter excludes, unless the mention is listed
-  in KNOWN_REFERENCES with the reason why it does not matter.
-
-A mention found this way must either be added to PATHS as an included path
-(the file is read by a compiler job) or to KNOWN_REFERENCES (it is not).
-
-With --changed FILE..., the script prints instead which workflows a pull
-request changing these files would run.
-"""
-
-import argparse
-import os
-import re
-import subprocess  # nosec B404
-import sys
-
-REPO_ROOT = os.path.normpath(os.path.join(sys.path[0], '..', '..'))
-SELF = 'tools/check_path_filters/check_path_filters.py'
-
-WORKFLOWS = ['.github/workflows/ubuntu.yml', '.github/workflows/macos.yml', '.github/workflows/windows.yml']
-
-# The pull_request paths filter of the workflows above; '{workflow}' is replaced
-# with the workflow's own file. GitHub applies the patterns in order: a file
-# matching a later pattern is included ('pattern') or excluded ('!pattern').
-PATHS = [
-    '**',
-    '!docs/**',
-    '!**.md',
-    '!.github/*',
-    '!.github/ISSUE_TEMPLATE/**',
-    '!.github/external_ci/**',
-    '!.github/workflows/**',
-    '!.reuse/**',
-    '!LICENSES/**',
-    '!CITATION.cff',
-    '!REUSE.toml',
-    # read by tools/check_build_options in the ci_meson_install job (ubuntu.yml)
-    'docs/mkdocs/docs/integration/package_managers.md',
-    # built by the swiftpm job (macos.yml)
-    'docs/mkdocs/docs/integration/swift/**',
-    '{workflow}',
-]
-
-# Mentions of excluded files that no job of the three workflows depends on:
-# (file that mentions it, the mention, reason)
-KNOWN_REFERENCES = [
-    ('cmake/ci.cmake', 'docs/', 'ci_test_examples; runs in repository_checks.yml, which has no path filter'),
-    ('cmake/ci.cmake', 'docs/mkdocs/', 'ci_test_build_documentation and ci_test_documentation_mermaid; they run in '
-                                       'repository_checks.yml, which has no path filter'),
-    ('cmake/ci.cmake', 'docs/mkdocs/docs/examples/', 'indentation check of ci_test_amalgamation; the same check runs in '
-                                                     'check_amalgamation.yml, which has no path filter'),
-    ('Makefile', 'docs/mkdocs/docs/examples/', 'make pretty; runs in check_amalgamation.yml, which has no path filter'),
-    ('Makefile', 'ChangeLog.md', 'make ChangeLog.md writes the file; no CI job runs it'),
-    ('Makefile', 'tests/fuzzing.md', 'help text'),
-    ('Makefile', 'tools/generate_natvis/README.md', 'help text'),
-    ('tests/src/make_test_data_available.hpp', 'README.md', 'a file of the external test data repository'),
-    ('tools/check_build_options/check_build_options.py', 'docs/', 'builds the path of package_managers.md, which '
-                                                                  'PATHS includes'),
-]
-
-
-# CI targets that read excluded files; they must run in a workflow without a path filter
-UNFILTERED_TARGETS = ['ci_test_examples', 'ci_test_build_documentation', 'ci_test_documentation_mermaid',
-                      'ci_test_amalgamation', 'ci_reuse_compliance']
-
-
-def git_files(root):
-    # fixed command, no user input; includes new files not yet added, so a local run
-    # sees what CI sees after the commit
-    out = subprocess.check_output(['git', 'ls-files', '-z', '--cached', '--others', '--exclude-standard'], cwd=root)  # nosec B603, B607
-    return [f for f in out.decode('utf-8').split('\0') if f]
-
-
-def glob_to_regex(pattern):
-    """Translate a GitHub Actions path pattern to a regular expression."""
-    regex = ''
-    i = 0
-    while i < len(pattern):
-        if pattern.startswith('**', i):
-            regex += '.*'
-            i += 2
-        elif pattern[i] == '*':
-            regex += '[^/]*'
-            i += 1
-        elif pattern[i] == '?':
-            regex += '[^/]'
-            i += 1
-        else:
-            regex += re.escape(pattern[i])
-            i += 1
-    return re.compile(regex + r'\Z')
-
-
-def compile_filter(paths, workflow):
-    return [(p.startswith('!'), glob_to_regex(p.lstrip('!').replace('{workflow}', workflow))) for p in paths]
-
-
-def included(compiled, path):
-    result = False
-    for negated, regex in compiled:
-        if regex.match(path):
-            result = not negated
-    return result
-
-
-def read_filter(root, workflow):
-    """Return the pull_request paths list of a workflow file."""
-    with open(os.path.join(root, workflow), encoding='utf-8') as f:
-        lines = f.read().splitlines()
-    paths = None
-    in_pull_request = False
-    for line in lines:
-        if re.match(r'^  pull_request:', line):
-            in_pull_request = True
-            continue
-        if in_pull_request:
-            if re.match(r'^  \S', line) or re.match(r'^\S', line):
-                break
-            if re.match(r'^    paths:\s*$', line):
-                paths = []
-                continue
-            m = re.match(r"^      - '(.*)'\s*(#.*)?$", line)
-            if paths is not None and m:
-                paths.append(m.group(1))
-            elif paths is not None and line.strip() and not line.strip().startswith('#'):
-                break
-    return paths
-
-
-TOKEN = re.compile(r'(["\'/]?)([\w.-]+(?:/[\w.-]+)*)')
-
-
-COMMENT_LINE = re.compile(r'^[ \t]*(//|#|/?\*|--).*$', re.MULTILINE)
-
-
-class Mentions:
-    """Finds the words and paths in a text that name an excluded file or directory."""
-
-    def __init__(self, files, excluded, is_excluded):
-        self.files = set(files)
-        self.excluded = excluded
-        self.dirs = {'/'.join(f.split('/')[:n]) for f in files for n in range(1, f.count('/') + 1)}
-        # an excluded directory: a new file in it would be excluded
-        self.excluded_dirs = {d for d in self.dirs if is_excluded(d + '/new_file')}
-        # base names that only excluded files have, e.g. 'ChangeLog.md' but not 'CMakeLists.txt'
-        self.names = {os.path.basename(f) for f in excluded} - {os.path.basename(f) for f in files if f not in excluded}
-
-    def find(self, text):
-        """Yield (offset, mention) for every word or path in text that names an excluded file or directory."""
-        for m in TOKEN.finditer(text):
-            parts = m.group(2).rstrip('/').split('/')
-            # a single word names a directory only in a path context, e.g. 'docs' in os.path.join('docs', ...)
-            path_context = len(parts) > 1 or m.group(1)
-            for i in range(len(parts)):
-                path = '/'.join(parts[i:])
-                if path in self.files:
-                    if path in self.excluded:
-                        yield m.start(2), path
-                    break
-                if path in self.dirs and path_context:
-                    if path in self.excluded_dirs:
-                        yield m.start(2), path + '/'
-                    break
-            else:
-                if parts[-1] in self.names and '.' in parts[-1]:
-                    yield m.start(2), parts[-1]
-
-
-def known(path, mention):
-    return any(path == file and mention == known_mention for file, known_mention, _ in KNOWN_REFERENCES)
-
-
-def check_workflows(root):
-    """Return the errors in the filters of the workflows and in the targets they run."""
-    errors = []
-    for workflow in WORKFLOWS:
-        expected = [p.replace('{workflow}', workflow) for p in PATHS]
-        actual = read_filter(root, workflow)
-        if actual != expected:
-            errors.append('{}: the pull_request paths filter differs from tools/check_path_filters/check_path_filters.py\n'
-                          '  expected: {}\n  actual:   {}'.format(workflow, expected, actual))
-        with open(os.path.join(root, workflow), encoding='utf-8') as f:
-            text = f.read()
-        errors += ['{}: runs {}, which reads excluded files; run it in repository_checks.yml'.format(workflow, target)
-                   for target in UNFILTERED_TARGETS if re.search(r'\b' + target + r'\b', text)]
-    return errors
-
-
-def scanned_text(root, path):
-    """Return the text of a kept file without comment lines and without the filter itself, or None to skip it."""
-    # third-party code and Markdown files read nothing; this script lists the excluded files
-    if path.startswith('tests/thirdparty/') or path.endswith('.md') or path == SELF:
-        return None
-    try:
-        with open(os.path.join(root, path), encoding='utf-8') as f:
-            # a mention in a comment line reads nothing; keep the line numbers
-            text = COMMENT_LINE.sub('', f.read())
-    except (UnicodeDecodeError, OSError):
-        return None
-    if path in WORKFLOWS:
-        # the filter itself lists the excluded files
-        for p in PATHS:
-            text = text.replace("      - '{}'".format(p.replace('{workflow}', path)), '')
-    return text
-
-
-def check_mentions(root, files, excluded, finder):
-    """Return an error for every mention of an excluded file in a kept file that KNOWN_REFERENCES does not list."""
-    errors = []
-    for path in sorted(set(files) - excluded):
-        text = scanned_text(root, path)
-        reported = set()
-        for offset, mention in finder.find(text or ''):
-            if mention not in reported and not known(path, mention):
-                reported.add(mention)
-                line = text.count('\n', 0, offset) + 1
-                errors.append('{}:{}: mentions excluded {}; include it in PATHS if a compiler job reads it, '
-                              'or add it to KNOWN_REFERENCES'.format(path, line, mention))
-    return errors
-
-
-def check(root):
-    files = git_files(root)
-    union = [compile_filter(PATHS, w) for w in WORKFLOWS]
-
-    def is_excluded(path):
-        return not any(included(c, path) for c in union)
-
-    excluded = {f for f in files if is_excluded(f)}
-    errors = check_workflows(root) + check_mentions(root, files, excluded, Mentions(files, excluded, is_excluded))
-    for e in errors:
-        print(e)
-    if not errors:
-        print('path filters OK: {} of {} tracked files skip the compiler workflows'.format(len(excluded), len(files)))
-    return 1 if errors else 0
-
-
-def explain(changed):
-    for workflow in WORKFLOWS:
-        compiled = compile_filter(PATHS, workflow)
-        hits = [f for f in changed if included(compiled, f)]
-        print('{}: {}'.format(workflow, 'runs ({})'.format(', '.join(hits[:3]) + (' ...' if len(hits) > 3 else ''))
-                                       if hits else 'skipped'))
-    return 0
-
-
-def main():
-    parser = argparse.ArgumentParser(description=__doc__.splitlines()[0])
-    parser.add_argument('--root', default=REPO_ROOT, help='repository root')
-    parser.add_argument('--changed', nargs='+', metavar='FILE', help='show which workflows these changed files run')
-    args = parser.parse_args()
-    return explain(args.changed) if args.changed else check(args.root)
-
-
-if __name__ == '__main__':
-    sys.exit(main())