Fix UBSan implicit-conversion in BSON stream tests

std::string(first, last) over std::uint8_t iterators converts each byte
to char implicitly, which -fsanitize=implicit-conversion reports as soon
as a byte is >= 0x80 (the document size byte of the enlarged test input,
and 0xFF in the new array element name test). Build the string from a
const char* and a size instead.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N5NasCxh8jKXBaa6HBx9Xk
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@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
-        with:
-          egress-policy: audit
-
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
-        with:
-          persist-credentials: false
-      - name: Check the path filters of the compiler workflows
-        run: python3 tools/check_path_filters/check_path_filters.py
-
-  ci_reuse_compliance:
-    runs-on: ubuntu-26.04
-    steps:
-      - name: Harden Runner
-        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
-        with:
-          egress-policy: audit
-
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
-        with:
-          persist-credentials: false
-      - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@a89e43e22a96abafcd7a62db652a65ecd33052c9 # v4.4.4
-      - name: Run CMake
-        run: cmake -S . -B build -DJSON_CI=On
-      - name: Build
-        run: cmake --build build --target ci_reuse_compliance
-
-  ci_test_documentation:
-    runs-on: ubuntu-26.04
-    strategy:
-      matrix:
-        target: [ci_test_examples, ci_test_build_documentation, ci_test_documentation_mermaid]
-    steps:
-      - name: Harden Runner
-        uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
-        with:
-          egress-policy: audit
-
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
-        with:
-          persist-credentials: false
-          # the git-revision-date-localized plugin needs the history; a shallow clone makes the strict build fail
-          fetch-depth: ${{ matrix.target == 'ci_test_build_documentation' && '0' || '1' }}
-      - uses: actions/setup-node@949feb2413d6458794dcd2491c4babbbce0c15c1 # v7.1.0
-        if: matrix.target == 'ci_test_documentation_mermaid'
-        with:
-          node-version: 24
-      - name: Run CMake
-        run: cmake -S . -B build -DJSON_CI=On
-      - name: Build
-        run: cmake --build build --target ${{ matrix.target }}

.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@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
@@ -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@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2
+        with:
+          egress-policy: audit
+
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+          # the git-revision-date-localized plugin needs the history; a shallow clone makes the strict build fail
+          fetch-depth: ${{ matrix.target == 'ci_test_build_documentation' && '0' || '1' }}
+      - uses: actions/setup-node@949feb2413d6458794dcd2491c4babbbce0c15c1 # v7.1.0
+        if: matrix.target == 'ci_test_documentation_mermaid'
+        with:
+          node-version: 24
+      - name: Run CMake
+        run: cmake -S . -B build -DJSON_CI=On
+      - name: Build
+        run: cmake --build build --target ${{ matrix.target }}
+
   # 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/input/binary_reader.hpp

@@ -465,15 +465,17 @@ class binary_reader
             }
 
             const std::size_t element_type_parse_position = chars_read;
+            // an array's elements are named "0", "1", ... in the wire format,
+            // and those names are not passed on: they are skipped unless
+            // error_handler_t::strict must reject ill-formed UTF-8 in them
+            const bool is_object = container_stack.back().is_object;
             key.clear();
-            if (JSON_HEDLEY_UNLIKELY(!get_bson_cstr(key)))
+            if (JSON_HEDLEY_UNLIKELY(!get_bson_cstr(key, is_object || error_handler == error_handler_t::strict)))
             {
                 return false;
             }
 
-            // an array's elements are named "0", "1", ... in the wire format,
-            // and those names are not passed on
-            if (container_stack.back().is_object && !sax->key(key))
+            if (is_object && !sax->key(key))
             {
                 return false;
             }
@@ -489,14 +491,18 @@ class binary_reader
     @brief Parses a C-style string from the BSON input.
     @param[in,out] result  A reference to the string variable where the read
                             string is to be stored.
+    @param[in] store  whether the characters are needed; if not (the names of
+                      an array's elements), they are skipped and @a result may
+                      be left unchanged, and they are not checked against
+                      @ref error_handler
     @return `true` if the \\x00-byte indicating the end of the string was
              encountered before the EOF; false` indicates an unexpected EOF.
     */
-    bool get_bson_cstr(string_t& result)
+    bool get_bson_cstr(string_t& result, const bool store = true)
     {
-        if (get_bson_cstr_bulk(result, std::integral_constant<bool, bulk_scan> {}))
+        if (get_bson_cstr_bulk(result, store, std::integral_constant<bool, bulk_scan> {}))
         {
-            return check_string_utf8(result, "key");
+            return !store || check_string_utf8(result, "key");
         }
 
         auto out = std::back_inserter(result);
@@ -509,7 +515,7 @@ class binary_reader
             }
             if (current == 0x00)
             {
-                return check_string_utf8(result, "key");
+                return !store || check_string_utf8(result, "key");
             }
             *out++ = static_cast<typename string_t::value_type>(current);
         }
@@ -519,10 +525,11 @@ class binary_reader
     @brief read a C-style string from contiguous input in one step
 
     @param[in,out] result  the string to append to
+    @param[in] store  whether to append the characters to @a result
     @return whether the string was read; if the input has no \\x00-byte, nothing
             is read, and @ref get_bson_cstr reports the end of the input
     */
-    bool get_bson_cstr_bulk(string_t& result, std::true_type /*bulk*/)
+    bool get_bson_cstr_bulk(string_t& result, const bool store, std::true_type /*bulk*/)
     {
         const std::size_t remaining = ia.bulk_remaining();
         if (remaining == 0)
@@ -530,18 +537,15 @@ class binary_reader
             return false;
         }
         const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
-        // a plain loop rather than std::memchr: most keys are short (array
-        // indices are keys, too), and the call would cost more than it saves
-        std::size_t length = 0;
-        while (length < remaining && data[length] != 0x00)
-        {
-            ++length;
-        }
+        const std::size_t length = find_zero_byte(data, remaining);
         if (length == remaining)
         {
             return false;
         }
-        result.append(reinterpret_cast<const typename string_t::value_type*>(data), length);
+        if (store)
+        {
+            result.append(reinterpret_cast<const typename string_t::value_type*>(data), length);
+        }
         // consume the string and its \x00-byte, as the byte-wise path does
         ia.bulk_skip(length + 1);
         chars_read += length + 1;
@@ -550,7 +554,7 @@ class binary_reader
     }
 
     /// input that is not contiguous: C-style strings are read byte by byte
-    bool get_bson_cstr_bulk(string_t& /*result*/, std::false_type /*bulk*/) const noexcept
+    bool get_bson_cstr_bulk(string_t& /*result*/, const bool /*store*/, std::false_type /*bulk*/) const noexcept
     {
         return false;
     }

include/nlohmann/detail/input/string_scan.hpp

@@ -90,6 +90,34 @@ JSON_HEDLEY_ALWAYS_INLINE std::size_t find_string_special(const unsigned char* d
     return n;
 }
 
+// return the index of the first 0x00 byte in [data, data+n), or n if there is
+// none; scans 8 bytes at a time (BSON's C-style strings)
+JSON_HEDLEY_ALWAYS_INLINE std::size_t find_zero_byte(const unsigned char* data, 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(data + i);
+        const std::uint64_t zero = (v - ones) & ~v & high;
+        if (zero != 0)
+        {
+            // the lowest flagged byte is the first zero byte (see
+            // find_string_special())
+            return i + (static_cast<std::size_t>(count_trailing_zeros(zero)) / 8);
+        }
+    }
+    for (; i < n; ++i)
+    {
+        if (data[i] == 0x00)
+        {
+            return i;
+        }
+    }
+    return n;
+}
+
 // classify a byte as one the serializer must NOT copy verbatim when
 // ensure_ascii is requested: the closing quote, an escape, a control character
 // (< 0x20), DEL (0x7F), or any non-ASCII byte (>= 0x80). Everything else -

include/nlohmann/json_view.hpp

@@ -766,9 +766,6 @@ class basic_json_view
     template<typename, typename> friend class detail::view::view_side;
     friend iterator;
 
-    /// whether the view is one of an editable document
-    static constexpr bool is_editable = Editable;
-
     basic_json_view(const document_data* d, const node* n) noexcept
         : m_doc(d), m_node(n)
     {}

single_include/nlohmann/json.hpp

@@ -12458,6 +12458,34 @@ JSON_HEDLEY_ALWAYS_INLINE std::size_t find_string_special(const unsigned char* d
     return n;
 }
 
+// return the index of the first 0x00 byte in [data, data+n), or n if there is
+// none; scans 8 bytes at a time (BSON's C-style strings)
+JSON_HEDLEY_ALWAYS_INLINE std::size_t find_zero_byte(const unsigned char* data, 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(data + i);
+        const std::uint64_t zero = (v - ones) & ~v & high;
+        if (zero != 0)
+        {
+            // the lowest flagged byte is the first zero byte (see
+            // find_string_special())
+            return i + (static_cast<std::size_t>(count_trailing_zeros(zero)) / 8);
+        }
+    }
+    for (; i < n; ++i)
+    {
+        if (data[i] == 0x00)
+        {
+            return i;
+        }
+    }
+    return n;
+}
+
 // classify a byte as one the serializer must NOT copy verbatim when
 // ensure_ascii is requested: the closing quote, an escape, a control character
 // (< 0x20), DEL (0x7F), or any non-ASCII byte (>= 0x80). Everything else -
@@ -18241,15 +18269,17 @@ class binary_reader
             }
 
             const std::size_t element_type_parse_position = chars_read;
+            // an array's elements are named "0", "1", ... in the wire format,
+            // and those names are not passed on: they are skipped unless
+            // error_handler_t::strict must reject ill-formed UTF-8 in them
+            const bool is_object = container_stack.back().is_object;
             key.clear();
-            if (JSON_HEDLEY_UNLIKELY(!get_bson_cstr(key)))
+            if (JSON_HEDLEY_UNLIKELY(!get_bson_cstr(key, is_object || error_handler == error_handler_t::strict)))
             {
                 return false;
             }
 
-            // an array's elements are named "0", "1", ... in the wire format,
-            // and those names are not passed on
-            if (container_stack.back().is_object && !sax->key(key))
+            if (is_object && !sax->key(key))
             {
                 return false;
             }
@@ -18265,14 +18295,18 @@ class binary_reader
     @brief Parses a C-style string from the BSON input.
     @param[in,out] result  A reference to the string variable where the read
                             string is to be stored.
+    @param[in] store  whether the characters are needed; if not (the names of
+                      an array's elements), they are skipped and @a result may
+                      be left unchanged, and they are not checked against
+                      @ref error_handler
     @return `true` if the \\x00-byte indicating the end of the string was
              encountered before the EOF; false` indicates an unexpected EOF.
     */
-    bool get_bson_cstr(string_t& result)
+    bool get_bson_cstr(string_t& result, const bool store = true)
     {
-        if (get_bson_cstr_bulk(result, std::integral_constant<bool, bulk_scan> {}))
+        if (get_bson_cstr_bulk(result, store, std::integral_constant<bool, bulk_scan> {}))
         {
-            return check_string_utf8(result, "key");
+            return !store || check_string_utf8(result, "key");
         }
 
         auto out = std::back_inserter(result);
@@ -18285,7 +18319,7 @@ class binary_reader
             }
             if (current == 0x00)
             {
-                return check_string_utf8(result, "key");
+                return !store || check_string_utf8(result, "key");
             }
             *out++ = static_cast<typename string_t::value_type>(current);
         }
@@ -18295,10 +18329,11 @@ class binary_reader
     @brief read a C-style string from contiguous input in one step
 
     @param[in,out] result  the string to append to
+    @param[in] store  whether to append the characters to @a result
     @return whether the string was read; if the input has no \\x00-byte, nothing
             is read, and @ref get_bson_cstr reports the end of the input
     */
-    bool get_bson_cstr_bulk(string_t& result, std::true_type /*bulk*/)
+    bool get_bson_cstr_bulk(string_t& result, const bool store, std::true_type /*bulk*/)
     {
         const std::size_t remaining = ia.bulk_remaining();
         if (remaining == 0)
@@ -18306,18 +18341,15 @@ class binary_reader
             return false;
         }
         const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
-        // a plain loop rather than std::memchr: most keys are short (array
-        // indices are keys, too), and the call would cost more than it saves
-        std::size_t length = 0;
-        while (length < remaining && data[length] != 0x00)
-        {
-            ++length;
-        }
+        const std::size_t length = find_zero_byte(data, remaining);
         if (length == remaining)
         {
             return false;
         }
-        result.append(reinterpret_cast<const typename string_t::value_type*>(data), length);
+        if (store)
+        {
+            result.append(reinterpret_cast<const typename string_t::value_type*>(data), length);
+        }
         // consume the string and its \x00-byte, as the byte-wise path does
         ia.bulk_skip(length + 1);
         chars_read += length + 1;
@@ -18326,7 +18358,7 @@ class binary_reader
     }
 
     /// input that is not contiguous: C-style strings are read byte by byte
-    bool get_bson_cstr_bulk(string_t& /*result*/, std::false_type /*bulk*/) const noexcept
+    bool get_bson_cstr_bulk(string_t& /*result*/, const bool /*store*/, std::false_type /*bulk*/) const noexcept
     {
         return false;
     }

single_include/nlohmann/json_view.hpp

@@ -9807,9 +9807,6 @@ class basic_json_view
     template<typename, typename> friend class detail::view::view_side;
     friend iterator;
 
-    /// whether the view is one of an editable document
-    static constexpr bool is_editable = Editable;
-
     basic_json_view(const document_data* d, const node* n) noexcept
         : m_doc(d), m_node(n)
     {}

tests/src/unit-bson.cpp

@@ -1164,7 +1164,13 @@ TEST_CASE("BSON keys from contiguous and stream input")
     // contiguous input reads a key up to its \x00-byte in one step, a stream
     // reads it byte by byte; both must give the same value or error for the
     // complete document and for every truncation of it
-    const json j = {{"", true}, {"k", {1, 2, 3}}, {std::string(40, 'x'), {{"nested key", "value"}}}};
+    json j = {{"", true}, {"k", {1, 2, 3}}, {std::string(40, 'x'), {{"nested key", "value"}}}};
+    // keys and array element names ("0" to "11") that end at every position of
+    // an 8-byte word, which contiguous input scans at a time
+    for (std::size_t length = 1; length <= 17; ++length)
+    {
+        j[std::string(length, static_cast<char>('a' + length))] = json::array({0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, {11}});
+    }
     const std::vector<std::uint8_t> bson = json::to_bson(j);
     CHECK(json::from_bson(bson) == j);
 
@@ -1184,7 +1190,7 @@ TEST_CASE("BSON keys from contiguous and stream input")
         }
         try
         {
-            std::istringstream stream(std::string(input.begin(), input.end()));
+            std::istringstream stream(std::string(reinterpret_cast<const char*>(input.data()), input.size()));
             from_stream = json::from_bson(stream).dump();
         }
         catch (const json::parse_error& e)
@@ -1194,6 +1200,33 @@ TEST_CASE("BSON keys from contiguous and stream input")
         CHECK(from_vector == from_stream);
     }
 }
+
+TEST_CASE("BSON array element names")
+{
+    // an array's element names are not part of the value, so they are not
+    // passed on; error_handler_t::strict still rejects ill-formed UTF-8 in them
+    const std::vector<std::uint8_t> bson =
+    {
+        0x1D, 0x00, 0x00, 0x00, // size (little endian)
+        0x04, 'a', 0x00,        // entry: array "a"
+        0x15, 0x00, 0x00, 0x00, // size (little endian)
+        0x08, 0xFF, 0x00, 0x01, // entry: boolean named "\xFF", true
+        0x08, '1', '2', '3', '4', '5', '6', '7', '8', '9', 0x00, 0x00, // entry: boolean named "123456789", false
+        0x00,                   // end of the array
+        0x00                    // end of the document
+    };
+    const json expected = {{"a", {true, false}}};
+
+    CHECK(json::from_bson(bson) == expected);
+    CHECK(json::from_bson(bson, true, true, json::error_handler_t::replace) == expected);
+    CHECK(json::from_bson(bson, true, true, json::error_handler_t::ignore) == expected);
+
+    json _;
+    CHECK_THROWS_WITH_AS(_ = json::from_bson(bson, true, true, json::error_handler_t::strict), "[json.exception.parse_error.113] parse error at byte 14: syntax error while parsing BSON key: invalid string: ill-formed UTF-8 byte", json::parse_error&);
+
+    std::istringstream stream(std::string(reinterpret_cast<const char*>(bson.data()), bson.size()));
+    CHECK(json::from_bson(stream) == expected);
+}
 #endif
 
 TEST_CASE("Negative size of binary value")

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())