json_view: keep accept()'s string check out of run()

Clang 23 made run() slower on files without escapes (mesh.pretty +15 %) when
the check-only string path was a separate call target. Dispatch inside
slow_string() instead, so the call in run() is the same as before, and skip
the SIMD run scan between escapes that follow each other (twitterescaped
1.11 -> 0.82 against the previous commit).

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:

docs/mkdocs/docs/api/basic_json_document/accept.md

@@ -13,9 +13,15 @@ function never throws an exception for invalid input, and the returned `#!cpp bo
 is returned.
 
 The result is the same as that of `BasicJsonType::accept()` by design; the difference is how the check is made. This
-function runs the document's index builder (and discards the index), while `BasicJsonType::accept()` runs the SAX
-parser with a handler that ignores every event. Use this one if you go on to parse the same input with
-[`parse()`](parse.md) anyway, so that both use the same code; either is fine for a plain yes/no answer.
+function runs the document's builder, which checks the text as [`parse()`](parse.md) does, while
+`BasicJsonType::accept()` runs the SAX parser with a handler that ignores every event. Use this one if you go on to
+parse the same input with [`parse()`](parse.md) anyway, so that both use the same code; either is fine for a plain
+yes/no answer.
+
+When both `ignore_comments` and `ignore_trailing_commas` are `#!cpp false` (the default), the builder writes no index.
+With either option set, it builds the index as [`parse()`](parse.md) does and discards it: the result is the same, only
+the time differs. (Neither option needs the index; the variant that skips it exists only for the default options to
+keep the code size down.)
 
 ## Template parameters
 

include/nlohmann/detail/view/builder.hpp

@@ -69,7 +69,8 @@ struct parse_failure
 };
 
 /// FloatType: the number_float_t of the document, whose overflow parse() rejects
-template<typename FloatType, bool Comments, bool TrailingCommas, bool NulIsEnd, bool Sentinel>
+/// Store: false for accept(): the grammar, number, string and UTF-8 checks run as for parse(), but no node is written
+template<typename FloatType, bool Comments, bool TrailingCommas, bool NulIsEnd, bool Sentinel, bool Store>
 class builder
 {
   public:
@@ -245,11 +246,87 @@ class builder
         return p;
     }
 
+    /// the string from p, the first backslash, control character, ill-formed UTF-8 byte, or the end, checked and not
+    /// decoded (accept() stores nothing, so the arena is not written): the checks, errors and error positions of
+    /// slow_string(), for everything up to the closing quote
+    NLOHMANN_VIEW_NOINLINE decoded check_string(const unsigned char* p)
+    {
+        const unsigned char* const end = m_end;
+        for (;;)
+        {
+            if (p == end)
+            {
+                return failed(error_code::string_missing_quote, p);
+            }
+            const unsigned char c = *p;
+            if (c == '"')
+            {
+                ++p;
+                return decoded{p, 0, 0};
+            }
+            if (c != '\\')
+            {
+                return failed(c < 0x20 ? error_code::string_control_character : error_code::string_utf8, p);
+            }
+            ++p;
+            if (p == end)
+            {
+                return failed(error_code::string_missing_quote, p);
+            }
+            const unsigned char d = *p++;
+            if (d == 'u')
+            {
+                const int cp = hex4(p); // (moves p past the four digits)
+                if (NLOHMANN_VIEW_UNLIKELY(cp < 0))
+                {
+                    return failed(error_code::string_unicode_hex, p);
+                }
+                if (NLOHMANN_VIEW_UNLIKELY((cp & 0xF800) == 0xD800)) // a surrogate
+                {
+                    if (cp >= 0xDC00)
+                    {
+                        return failed(error_code::string_surrogate_low, p);
+                    }
+                    if (end - p < 2 || p[0] != '\\' || p[1] != 'u')
+                    {
+                        return failed(error_code::string_surrogate_high, p);
+                    }
+                    p += 2;
+                    const int lo = hex4(p); // (moves p past the four digits)
+                    if (lo < 0)
+                    {
+                        return failed(error_code::string_unicode_hex, p);
+                    }
+                    if (lo < 0xDC00 || lo > 0xDFFF)
+                    {
+                        return failed(error_code::string_surrogate_high, p);
+                    }
+                }
+            }
+            else if (!(d == '"' || d == '\\' || d == '/' || d == 'b' || d == 'f' || d == 'n' || d == 'r' || d == 't'))
+            {
+                --p;
+                return failed(error_code::string_escape, p);
+            }
+            if (p != end && *p == '\\')
+            {
+                continue; // (escapes in a row: no run of text between them)
+            }
+            p = scan_string_run(p, end); // the text up to the next backslash, quote, control character, or ill-formed UTF-8
+        }
+    }
+
     /// s points to the start of the string, p to a backslash, a control
     /// character, an ill-formed UTF-8 byte, or the end: decode the string into
     /// the arena
     NLOHMANN_VIEW_NOINLINE decoded slow_string(const unsigned char* s, const unsigned char* p)
     {
+        if (!enabled(Store))
+        {
+            // (accept(): the string is checked, not decoded)
+            static_cast<void>(s);
+            return check_string(p);
+        }
         // single-character escapes; 0: invalid (and 'u', handled separately)
         static const std::array<char, 128> simple_escape =
         {
@@ -610,10 +687,13 @@ run_found:
 
         NLOHMANN_VIEW_ALWAYS_INLINE bool run()
         {
-            cold.m_doc.reserve(estimate_nodes(reinterpret_cast<const char*>(b), static_cast<std::size_t>(e - b)));
-            base = cold.m_doc.nodes;
-            out = base;
-            cap = base + cold.m_doc.node_capacity;
+            if (enabled(Store))
+            {
+                cold.m_doc.reserve(estimate_nodes(reinterpret_cast<const char*>(b), static_cast<std::size_t>(e - b)));
+                base = cold.m_doc.nodes;
+                out = base;
+                cap = base + cold.m_doc.node_capacity;
+            }
 
             if (e - p >= 3 && p[0] == 0xEF && p[1] == 0xBB && p[2] == 0xBF)
             {
@@ -797,7 +877,10 @@ close_object:
             // an array pays nothing for this)
             if (NLOHMANN_VIEW_UNLIKELY(cur_count >= document_data::index_min_members))
             {
-                cold.note_large_object(cur_idx);
+                if (enabled(Store))
+                {
+                    cold.note_large_object(cur_idx);
+                }
             }
 
 close_container:
@@ -957,6 +1040,12 @@ indent_done:
         /// an integer's value); two stores on little-endian targets
         NLOHMANN_VIEW_ALWAYS_INLINE node* push_node(node_kind k, std::uint8_t flags, std::uint16_t extra, std::size_t off, std::uint64_t second)
         {
+            if (!enabled(Store))
+            {
+                // accept(): nothing is stored, so what computes the arguments is not run either. base and out stay
+                // null: their difference, which open() takes, is 0.
+                return out;
+            }
             if (NLOHMANN_VIEW_UNLIKELY(out == cap))
             {
                 const auto n = static_cast<std::size_t>(out - base);
@@ -1015,9 +1104,12 @@ indent_done:
 
         NLOHMANN_VIEW_ALWAYS_INLINE void close()
         {
-            node& n = base[cur_idx];
-            n.len = cur_count;
-            n.next = static_cast<std::uint32_t>(out - base) - cur_idx;
+            if (enabled(Store))
+            {
+                node& n = base[cur_idx];
+                n.len = cur_count;
+                n.next = static_cast<std::uint32_t>(out - base) - cur_idx;
+            }
             if (--depth != 0)
             {
                 if (NLOHMANN_VIEW_LIKELY(depth <= 64))
@@ -1192,34 +1284,44 @@ indent_done:
 };
 
 /// run the builder with compile-time options
-template<typename FloatType, bool Comments, bool TrailingCommas, bool NulIsEnd>
+template<typename FloatType, bool Comments, bool TrailingCommas, bool NulIsEnd, bool Store>
 inline bool build_with(document_data& d, const char* src, std::size_t size, bool sentinel, parse_failure& failure)
 {
     if (sentinel)
     {
-        builder<FloatType, Comments, TrailingCommas, NulIsEnd, true> bld(d, src, size);
+        builder<FloatType, Comments, TrailingCommas, NulIsEnd, true, Store> bld(d, src, size);
         const bool ok = bld.run();
         failure = bld.failure();
         return ok;
     }
-    builder<FloatType, Comments, TrailingCommas, NulIsEnd, false> bld(d, src, size);
+    builder<FloatType, Comments, TrailingCommas, NulIsEnd, false, Store> bld(d, src, size);
     const bool ok = bld.run();
     failure = bld.failure();
     return ok;
 }
 
 /// sentinel: src[size] is readable and 0 (e.g. std::string); FloatType: the
-/// number_float_t of the document
+/// number_float_t of the document; validate_only: accept(), only the result is
+/// used
 template<typename FloatType, bool NulIsEnd>
-inline bool build(document_data& d, const char* src, std::size_t size, bool comments, bool trailing_commas, bool sentinel, parse_failure& failure)
+inline bool build(document_data& d, const char* src, std::size_t size, bool comments, bool trailing_commas, bool sentinel, bool validate_only,
+                  parse_failure& failure)
 {
+    if (validate_only && !comments && !trailing_commas)
+    {
+        // accept() of plain JSON: nothing is stored. The other option sets
+        // could skip the stores just as well; they keep the builder that
+        // stores only so that there are two more instantiations of the parse
+        // loop, not eight.
+        return build_with<FloatType, false, false, NulIsEnd, false>(d, src, size, sentinel, failure);
+    }
     if (comments)
     {
-        return trailing_commas ? build_with<FloatType, true, true, NulIsEnd>(d, src, size, sentinel, failure)
-               : build_with<FloatType, true, false, NulIsEnd>(d, src, size, sentinel, failure);
+        return trailing_commas ? build_with<FloatType, true, true, NulIsEnd, true>(d, src, size, sentinel, failure)
+               : build_with<FloatType, true, false, NulIsEnd, true>(d, src, size, sentinel, failure);
     }
-    return trailing_commas ? build_with<FloatType, false, true, NulIsEnd>(d, src, size, sentinel, failure)
-           : build_with<FloatType, false, false, NulIsEnd>(d, src, size, sentinel, failure);
+    return trailing_commas ? build_with<FloatType, false, true, NulIsEnd, true>(d, src, size, sentinel, failure)
+           : build_with<FloatType, false, false, NulIsEnd, true>(d, src, size, sentinel, failure);
 }
 
 }  // namespace view

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)
     {}
@@ -1063,7 +1060,7 @@ class basic_json_document
                                      const bool ignore_trailing_commas = false)
     {
         basic_json_document d;
-        d.read_range(first, last, allow_exceptions, ignore_comments, ignore_trailing_commas);
+        d.read_range(first, last, error_mode(allow_exceptions), ignore_comments, ignore_trailing_commas);
         return d;
     }
 
@@ -1078,7 +1075,7 @@ class basic_json_document
         basic_json_document d;
         std::string buf;
         append_input(buf, std::forward<InputType>(input));
-        d.build_owned(std::move(buf), allow_exceptions, ignore_comments, ignore_trailing_commas);
+        d.build_owned(std::move(buf), error_mode(allow_exceptions), ignore_comments, ignore_trailing_commas);
         return d;
     }
 
@@ -1091,7 +1088,8 @@ class basic_json_document
     static bool accept(InputType&& input, const bool ignore_comments = false, const bool ignore_trailing_commas = false)
     {
         basic_json_document d;
-        d.read(std::forward<InputType>(input), false, ignore_comments, ignore_trailing_commas);
+        d.read_kind(std::forward<InputType>(input), on_error::validate, ignore_comments, ignore_trailing_commas,
+                    std::integral_constant<detail::view::input_kind, detail::view::classify_input<InputType>::value> {});
         return !d.is_discarded();
     }
 
@@ -1107,7 +1105,7 @@ class basic_json_document
               const bool ignore_comments = false,
               const bool ignore_trailing_commas = false)
     {
-        read_kind(std::forward<InputType>(input), allow_exceptions, ignore_comments, ignore_trailing_commas,
+        read_kind(std::forward<InputType>(input), error_mode(allow_exceptions), ignore_comments, ignore_trailing_commas,
                   std::integral_constant<detail::view::input_kind, detail::view::classify_input<InputType>::value> {});
     }
 
@@ -1466,6 +1464,22 @@ class basic_json_document
         return idx;
     }
 
+    /// what a failed parse does
+    enum class on_error : std::uint8_t
+    {
+        discard, ///< the document is discarded
+        raise,   ///< parse_error is thrown
+        validate ///< accept(): the document is discarded, and no node is stored while parsing
+    };
+
+    static on_error error_mode(bool allow_exceptions) noexcept
+    {
+        return allow_exceptions ? on_error::raise : on_error::discard;
+    }
+
+    /// NulIsEnd of the builder: a null byte ends the input unless strict_nul_handling
+    static constexpr bool nul_is_end = !detail::abi_config::strict_nul_handling;
+
     /// create the storage (sized for the input) on first use
     void ensure_data(const char* src, std::size_t size)
     {
@@ -1477,7 +1491,7 @@ class basic_json_document
 
     /// parse a buffer the document takes ownership of (it replaces the
     /// previous owned copy)
-    void build_owned(std::string&& buf, bool allow_exceptions, bool comments, bool trailing_commas)
+    void build_owned(std::string&& buf, on_error allow_exceptions, bool comments, bool trailing_commas)
     {
         ensure_data(buf.data(), buf.size());
         m_data->owned = std::move(buf);
@@ -1487,7 +1501,7 @@ class basic_json_document
     /// parse a copy of the input; the copy is appended to the cleared owned
     /// buffer, so that its capacity is reused
     template<typename T>
-    void build_copy(T&& input, bool allow_exceptions, bool comments, bool trailing_commas)
+    void build_copy(T&& input, on_error allow_exceptions, bool comments, bool trailing_commas)
     {
         if (!m_data)
         {
@@ -1508,7 +1522,7 @@ class basic_json_document
     }
 
     /// sentinel: src[size] is readable and 0 (std::string, C strings)
-    void build(const char* src, std::size_t size, bool allow_exceptions, bool comments, bool trailing_commas, bool owned, bool sentinel)
+    void build(const char* src, std::size_t size, on_error allow_exceptions, bool comments, bool trailing_commas, bool owned, bool sentinel)
     {
         ensure_data(src, size);
         document_data& d = *m_data;
@@ -1535,7 +1549,8 @@ class basic_json_document
         }
         else
         {
-            ok = detail::view::build < typename BasicJsonType::number_float_t, !detail::abi_config::strict_nul_handling > (d, src, size, comments, trailing_commas, sentinel, failure);
+            ok = detail::view::build<typename BasicJsonType::number_float_t, nul_is_end>(d, src, size, comments, trailing_commas, sentinel,
+                 allow_exceptions == on_error::validate, failure);
         }
         if (NLOHMANN_VIEW_LIKELY(ok))
         {
@@ -1548,7 +1563,7 @@ class basic_json_document
             return;
         }
         std::vector<std::uint32_t>().swap(d.large_objects);
-        if (allow_exceptions)
+        if (allow_exceptions == on_error::raise)
         {
             detail::view::throw_parse_failure<BasicJsonType>(failure, src, size, comments, trailing_commas);
         }
@@ -1556,13 +1571,13 @@ class basic_json_document
 
     // --- input dispatch (see detail::view::input_kind) ---
 
-    void read_kind(std::string&& s, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::move_string> /*unused*/)
+    void read_kind(std::string&& s, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::move_string> /*unused*/)
     {
         build_owned(std::move(s), ae, c, tc);
     }
 
     template<typename CharT>
-    void read_kind(CharT* s, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::c_string> /*unused*/)
+    void read_kind(CharT* s, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::c_string> /*unused*/)
     {
         if (s == nullptr)
         {
@@ -1576,7 +1591,7 @@ class basic_json_document
     }
 
     template<typename Array>
-    void read_kind(Array& a, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::char_array> /*unused*/)
+    void read_kind(Array& a, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::char_array> /*unused*/)
     {
         using CharT = typename std::remove_cv<typename std::remove_extent<Array>::type>::type;
         const std::size_t n = std::extent<Array>::value;
@@ -1587,7 +1602,7 @@ class basic_json_document
     }
 
     template<typename T>
-    void read_kind(const T& s, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::borrow_range> /*unused*/)
+    void read_kind(const T& s, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::borrow_range> /*unused*/)
     {
         // std::basic_string guarantees data()[size()] == 0: use it as sentinel
         const auto size = static_cast<std::size_t>(s.size());
@@ -1596,13 +1611,13 @@ class basic_json_document
     }
 
     template<typename T>
-    void read_kind(const T& s, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::copy_range> /*unused*/)
+    void read_kind(const T& s, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::copy_range> /*unused*/)
     {
         build_copy(s, ae, c, tc);
     }
 
     template<typename CharT>
-    void read_kind(CharT* s, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::wide_c_string> /*unused*/)
+    void read_kind(CharT* s, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::wide_c_string> /*unused*/)
     {
         if (s == nullptr)
         {
@@ -1614,13 +1629,13 @@ class basic_json_document
     }
 
     template<typename T>
-    void read_kind(T&& input, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::adapter> /*unused*/)
+    void read_kind(T&& input, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::adapter> /*unused*/)
     {
         build_copy(std::forward<T>(input), ae, c, tc);
     }
 
     template<typename IteratorType>
-    void read_range(IteratorType first, IteratorType last, bool ae, bool c, bool tc)
+    void read_range(IteratorType first, IteratorType last, on_error ae, bool c, bool tc)
     {
         using value_type = typename std::remove_cv<typename std::iterator_traits<IteratorType>::value_type>::type;
         // borrow the range where the library's input adapter scans it as one
@@ -1631,14 +1646,14 @@ class basic_json_document
     }
 
     template<typename IteratorType>
-    void read_range_impl(IteratorType first, IteratorType last, bool ae, bool c, bool tc, std::true_type /*contiguous bytes*/)
+    void read_range_impl(IteratorType first, IteratorType last, on_error ae, bool c, bool tc, std::true_type /*contiguous bytes*/)
     {
         const auto size = static_cast<std::size_t>(std::distance(first, last));
         build(size == 0 ? "" : reinterpret_cast<const char*>(&*first), size, ae, c, tc, false, size == 0); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
     }
 
     template<typename IteratorType>
-    void read_range_impl(IteratorType first, IteratorType last, bool ae, bool c, bool tc, std::false_type /*other*/)
+    void read_range_impl(IteratorType first, IteratorType last, on_error ae, bool c, bool tc, std::false_type /*other*/)
     {
         build_copy(detail::view::make_adapter_input(detail::input_adapter(first, last)), ae, c, tc);
     }

single_include/nlohmann/json_view.hpp

@@ -1311,7 +1311,8 @@ struct parse_failure
 };
 
 /// FloatType: the number_float_t of the document, whose overflow parse() rejects
-template<typename FloatType, bool Comments, bool TrailingCommas, bool NulIsEnd, bool Sentinel>
+/// Store: false for accept(): the grammar, number, string and UTF-8 checks run as for parse(), but no node is written
+template<typename FloatType, bool Comments, bool TrailingCommas, bool NulIsEnd, bool Sentinel, bool Store>
 class builder
 {
   public:
@@ -1487,11 +1488,87 @@ class builder
         return p;
     }
 
+    /// the string from p, the first backslash, control character, ill-formed UTF-8 byte, or the end, checked and not
+    /// decoded (accept() stores nothing, so the arena is not written): the checks, errors and error positions of
+    /// slow_string(), for everything up to the closing quote
+    NLOHMANN_VIEW_NOINLINE decoded check_string(const unsigned char* p)
+    {
+        const unsigned char* const end = m_end;
+        for (;;)
+        {
+            if (p == end)
+            {
+                return failed(error_code::string_missing_quote, p);
+            }
+            const unsigned char c = *p;
+            if (c == '"')
+            {
+                ++p;
+                return decoded{p, 0, 0};
+            }
+            if (c != '\\')
+            {
+                return failed(c < 0x20 ? error_code::string_control_character : error_code::string_utf8, p);
+            }
+            ++p;
+            if (p == end)
+            {
+                return failed(error_code::string_missing_quote, p);
+            }
+            const unsigned char d = *p++;
+            if (d == 'u')
+            {
+                const int cp = hex4(p); // (moves p past the four digits)
+                if (NLOHMANN_VIEW_UNLIKELY(cp < 0))
+                {
+                    return failed(error_code::string_unicode_hex, p);
+                }
+                if (NLOHMANN_VIEW_UNLIKELY((cp & 0xF800) == 0xD800)) // a surrogate
+                {
+                    if (cp >= 0xDC00)
+                    {
+                        return failed(error_code::string_surrogate_low, p);
+                    }
+                    if (end - p < 2 || p[0] != '\\' || p[1] != 'u')
+                    {
+                        return failed(error_code::string_surrogate_high, p);
+                    }
+                    p += 2;
+                    const int lo = hex4(p); // (moves p past the four digits)
+                    if (lo < 0)
+                    {
+                        return failed(error_code::string_unicode_hex, p);
+                    }
+                    if (lo < 0xDC00 || lo > 0xDFFF)
+                    {
+                        return failed(error_code::string_surrogate_high, p);
+                    }
+                }
+            }
+            else if (!(d == '"' || d == '\\' || d == '/' || d == 'b' || d == 'f' || d == 'n' || d == 'r' || d == 't'))
+            {
+                --p;
+                return failed(error_code::string_escape, p);
+            }
+            if (p != end && *p == '\\')
+            {
+                continue; // (escapes in a row: no run of text between them)
+            }
+            p = scan_string_run(p, end); // the text up to the next backslash, quote, control character, or ill-formed UTF-8
+        }
+    }
+
     /// s points to the start of the string, p to a backslash, a control
     /// character, an ill-formed UTF-8 byte, or the end: decode the string into
     /// the arena
     NLOHMANN_VIEW_NOINLINE decoded slow_string(const unsigned char* s, const unsigned char* p)
     {
+        if (!enabled(Store))
+        {
+            // (accept(): the string is checked, not decoded)
+            static_cast<void>(s);
+            return check_string(p);
+        }
         // single-character escapes; 0: invalid (and 'u', handled separately)
         static const std::array<char, 128> simple_escape =
         {
@@ -1852,10 +1929,13 @@ run_found:
 
         NLOHMANN_VIEW_ALWAYS_INLINE bool run()
         {
-            cold.m_doc.reserve(estimate_nodes(reinterpret_cast<const char*>(b), static_cast<std::size_t>(e - b)));
-            base = cold.m_doc.nodes;
-            out = base;
-            cap = base + cold.m_doc.node_capacity;
+            if (enabled(Store))
+            {
+                cold.m_doc.reserve(estimate_nodes(reinterpret_cast<const char*>(b), static_cast<std::size_t>(e - b)));
+                base = cold.m_doc.nodes;
+                out = base;
+                cap = base + cold.m_doc.node_capacity;
+            }
 
             if (e - p >= 3 && p[0] == 0xEF && p[1] == 0xBB && p[2] == 0xBF)
             {
@@ -2039,7 +2119,10 @@ close_object:
             // an array pays nothing for this)
             if (NLOHMANN_VIEW_UNLIKELY(cur_count >= document_data::index_min_members))
             {
-                cold.note_large_object(cur_idx);
+                if (enabled(Store))
+                {
+                    cold.note_large_object(cur_idx);
+                }
             }
 
 close_container:
@@ -2199,6 +2282,12 @@ indent_done:
         /// an integer's value); two stores on little-endian targets
         NLOHMANN_VIEW_ALWAYS_INLINE node* push_node(node_kind k, std::uint8_t flags, std::uint16_t extra, std::size_t off, std::uint64_t second)
         {
+            if (!enabled(Store))
+            {
+                // accept(): nothing is stored, so what computes the arguments is not run either. base and out stay
+                // null: their difference, which open() takes, is 0.
+                return out;
+            }
             if (NLOHMANN_VIEW_UNLIKELY(out == cap))
             {
                 const auto n = static_cast<std::size_t>(out - base);
@@ -2257,9 +2346,12 @@ indent_done:
 
         NLOHMANN_VIEW_ALWAYS_INLINE void close()
         {
-            node& n = base[cur_idx];
-            n.len = cur_count;
-            n.next = static_cast<std::uint32_t>(out - base) - cur_idx;
+            if (enabled(Store))
+            {
+                node& n = base[cur_idx];
+                n.len = cur_count;
+                n.next = static_cast<std::uint32_t>(out - base) - cur_idx;
+            }
             if (--depth != 0)
             {
                 if (NLOHMANN_VIEW_LIKELY(depth <= 64))
@@ -2434,34 +2526,44 @@ indent_done:
 };
 
 /// run the builder with compile-time options
-template<typename FloatType, bool Comments, bool TrailingCommas, bool NulIsEnd>
+template<typename FloatType, bool Comments, bool TrailingCommas, bool NulIsEnd, bool Store>
 inline bool build_with(document_data& d, const char* src, std::size_t size, bool sentinel, parse_failure& failure)
 {
     if (sentinel)
     {
-        builder<FloatType, Comments, TrailingCommas, NulIsEnd, true> bld(d, src, size);
+        builder<FloatType, Comments, TrailingCommas, NulIsEnd, true, Store> bld(d, src, size);
         const bool ok = bld.run();
         failure = bld.failure();
         return ok;
     }
-    builder<FloatType, Comments, TrailingCommas, NulIsEnd, false> bld(d, src, size);
+    builder<FloatType, Comments, TrailingCommas, NulIsEnd, false, Store> bld(d, src, size);
     const bool ok = bld.run();
     failure = bld.failure();
     return ok;
 }
 
 /// sentinel: src[size] is readable and 0 (e.g. std::string); FloatType: the
-/// number_float_t of the document
+/// number_float_t of the document; validate_only: accept(), only the result is
+/// used
 template<typename FloatType, bool NulIsEnd>
-inline bool build(document_data& d, const char* src, std::size_t size, bool comments, bool trailing_commas, bool sentinel, parse_failure& failure)
+inline bool build(document_data& d, const char* src, std::size_t size, bool comments, bool trailing_commas, bool sentinel, bool validate_only,
+                  parse_failure& failure)
 {
+    if (validate_only && !comments && !trailing_commas)
+    {
+        // accept() of plain JSON: nothing is stored. The other option sets
+        // could skip the stores just as well; they keep the builder that
+        // stores only so that there are two more instantiations of the parse
+        // loop, not eight.
+        return build_with<FloatType, false, false, NulIsEnd, false>(d, src, size, sentinel, failure);
+    }
     if (comments)
     {
-        return trailing_commas ? build_with<FloatType, true, true, NulIsEnd>(d, src, size, sentinel, failure)
-               : build_with<FloatType, true, false, NulIsEnd>(d, src, size, sentinel, failure);
+        return trailing_commas ? build_with<FloatType, true, true, NulIsEnd, true>(d, src, size, sentinel, failure)
+               : build_with<FloatType, true, false, NulIsEnd, true>(d, src, size, sentinel, failure);
     }
-    return trailing_commas ? build_with<FloatType, false, true, NulIsEnd>(d, src, size, sentinel, failure)
-           : build_with<FloatType, false, false, NulIsEnd>(d, src, size, sentinel, failure);
+    return trailing_commas ? build_with<FloatType, false, true, NulIsEnd, true>(d, src, size, sentinel, failure)
+           : build_with<FloatType, false, false, NulIsEnd, true>(d, src, size, sentinel, failure);
 }
 
 }  // namespace view
@@ -9807,9 +9909,6 @@ 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)
     {}
@@ -10104,7 +10203,7 @@ class basic_json_document
                                      const bool ignore_trailing_commas = false)
     {
         basic_json_document d;
-        d.read_range(first, last, allow_exceptions, ignore_comments, ignore_trailing_commas);
+        d.read_range(first, last, error_mode(allow_exceptions), ignore_comments, ignore_trailing_commas);
         return d;
     }
 
@@ -10119,7 +10218,7 @@ class basic_json_document
         basic_json_document d;
         std::string buf;
         append_input(buf, std::forward<InputType>(input));
-        d.build_owned(std::move(buf), allow_exceptions, ignore_comments, ignore_trailing_commas);
+        d.build_owned(std::move(buf), error_mode(allow_exceptions), ignore_comments, ignore_trailing_commas);
         return d;
     }
 
@@ -10132,7 +10231,8 @@ class basic_json_document
     static bool accept(InputType&& input, const bool ignore_comments = false, const bool ignore_trailing_commas = false)
     {
         basic_json_document d;
-        d.read(std::forward<InputType>(input), false, ignore_comments, ignore_trailing_commas);
+        d.read_kind(std::forward<InputType>(input), on_error::validate, ignore_comments, ignore_trailing_commas,
+                    std::integral_constant<detail::view::input_kind, detail::view::classify_input<InputType>::value> {});
         return !d.is_discarded();
     }
 
@@ -10148,7 +10248,7 @@ class basic_json_document
               const bool ignore_comments = false,
               const bool ignore_trailing_commas = false)
     {
-        read_kind(std::forward<InputType>(input), allow_exceptions, ignore_comments, ignore_trailing_commas,
+        read_kind(std::forward<InputType>(input), error_mode(allow_exceptions), ignore_comments, ignore_trailing_commas,
                   std::integral_constant<detail::view::input_kind, detail::view::classify_input<InputType>::value> {});
     }
 
@@ -10507,6 +10607,22 @@ class basic_json_document
         return idx;
     }
 
+    /// what a failed parse does
+    enum class on_error : std::uint8_t
+    {
+        discard, ///< the document is discarded
+        raise,   ///< parse_error is thrown
+        validate ///< accept(): the document is discarded, and no node is stored while parsing
+    };
+
+    static on_error error_mode(bool allow_exceptions) noexcept
+    {
+        return allow_exceptions ? on_error::raise : on_error::discard;
+    }
+
+    /// NulIsEnd of the builder: a null byte ends the input unless strict_nul_handling
+    static constexpr bool nul_is_end = !detail::abi_config::strict_nul_handling;
+
     /// create the storage (sized for the input) on first use
     void ensure_data(const char* src, std::size_t size)
     {
@@ -10518,7 +10634,7 @@ class basic_json_document
 
     /// parse a buffer the document takes ownership of (it replaces the
     /// previous owned copy)
-    void build_owned(std::string&& buf, bool allow_exceptions, bool comments, bool trailing_commas)
+    void build_owned(std::string&& buf, on_error allow_exceptions, bool comments, bool trailing_commas)
     {
         ensure_data(buf.data(), buf.size());
         m_data->owned = std::move(buf);
@@ -10528,7 +10644,7 @@ class basic_json_document
     /// parse a copy of the input; the copy is appended to the cleared owned
     /// buffer, so that its capacity is reused
     template<typename T>
-    void build_copy(T&& input, bool allow_exceptions, bool comments, bool trailing_commas)
+    void build_copy(T&& input, on_error allow_exceptions, bool comments, bool trailing_commas)
     {
         if (!m_data)
         {
@@ -10549,7 +10665,7 @@ class basic_json_document
     }
 
     /// sentinel: src[size] is readable and 0 (std::string, C strings)
-    void build(const char* src, std::size_t size, bool allow_exceptions, bool comments, bool trailing_commas, bool owned, bool sentinel)
+    void build(const char* src, std::size_t size, on_error allow_exceptions, bool comments, bool trailing_commas, bool owned, bool sentinel)
     {
         ensure_data(src, size);
         document_data& d = *m_data;
@@ -10576,7 +10692,8 @@ class basic_json_document
         }
         else
         {
-            ok = detail::view::build < typename BasicJsonType::number_float_t, !detail::abi_config::strict_nul_handling > (d, src, size, comments, trailing_commas, sentinel, failure);
+            ok = detail::view::build<typename BasicJsonType::number_float_t, nul_is_end>(d, src, size, comments, trailing_commas, sentinel,
+                 allow_exceptions == on_error::validate, failure);
         }
         if (NLOHMANN_VIEW_LIKELY(ok))
         {
@@ -10589,7 +10706,7 @@ class basic_json_document
             return;
         }
         std::vector<std::uint32_t>().swap(d.large_objects);
-        if (allow_exceptions)
+        if (allow_exceptions == on_error::raise)
         {
             detail::view::throw_parse_failure<BasicJsonType>(failure, src, size, comments, trailing_commas);
         }
@@ -10597,13 +10714,13 @@ class basic_json_document
 
     // --- input dispatch (see detail::view::input_kind) ---
 
-    void read_kind(std::string&& s, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::move_string> /*unused*/)
+    void read_kind(std::string&& s, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::move_string> /*unused*/)
     {
         build_owned(std::move(s), ae, c, tc);
     }
 
     template<typename CharT>
-    void read_kind(CharT* s, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::c_string> /*unused*/)
+    void read_kind(CharT* s, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::c_string> /*unused*/)
     {
         if (s == nullptr)
         {
@@ -10617,7 +10734,7 @@ class basic_json_document
     }
 
     template<typename Array>
-    void read_kind(Array& a, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::char_array> /*unused*/)
+    void read_kind(Array& a, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::char_array> /*unused*/)
     {
         using CharT = typename std::remove_cv<typename std::remove_extent<Array>::type>::type;
         const std::size_t n = std::extent<Array>::value;
@@ -10628,7 +10745,7 @@ class basic_json_document
     }
 
     template<typename T>
-    void read_kind(const T& s, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::borrow_range> /*unused*/)
+    void read_kind(const T& s, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::borrow_range> /*unused*/)
     {
         // std::basic_string guarantees data()[size()] == 0: use it as sentinel
         const auto size = static_cast<std::size_t>(s.size());
@@ -10637,13 +10754,13 @@ class basic_json_document
     }
 
     template<typename T>
-    void read_kind(const T& s, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::copy_range> /*unused*/)
+    void read_kind(const T& s, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::copy_range> /*unused*/)
     {
         build_copy(s, ae, c, tc);
     }
 
     template<typename CharT>
-    void read_kind(CharT* s, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::wide_c_string> /*unused*/)
+    void read_kind(CharT* s, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::wide_c_string> /*unused*/)
     {
         if (s == nullptr)
         {
@@ -10655,13 +10772,13 @@ class basic_json_document
     }
 
     template<typename T>
-    void read_kind(T&& input, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::adapter> /*unused*/)
+    void read_kind(T&& input, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::adapter> /*unused*/)
     {
         build_copy(std::forward<T>(input), ae, c, tc);
     }
 
     template<typename IteratorType>
-    void read_range(IteratorType first, IteratorType last, bool ae, bool c, bool tc)
+    void read_range(IteratorType first, IteratorType last, on_error ae, bool c, bool tc)
     {
         using value_type = typename std::remove_cv<typename std::iterator_traits<IteratorType>::value_type>::type;
         // borrow the range where the library's input adapter scans it as one
@@ -10672,14 +10789,14 @@ class basic_json_document
     }
 
     template<typename IteratorType>
-    void read_range_impl(IteratorType first, IteratorType last, bool ae, bool c, bool tc, std::true_type /*contiguous bytes*/)
+    void read_range_impl(IteratorType first, IteratorType last, on_error ae, bool c, bool tc, std::true_type /*contiguous bytes*/)
     {
         const auto size = static_cast<std::size_t>(std::distance(first, last));
         build(size == 0 ? "" : reinterpret_cast<const char*>(&*first), size, ae, c, tc, false, size == 0); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
     }
 
     template<typename IteratorType>
-    void read_range_impl(IteratorType first, IteratorType last, bool ae, bool c, bool tc, std::false_type /*other*/)
+    void read_range_impl(IteratorType first, IteratorType last, on_error ae, bool c, bool tc, std::false_type /*other*/)
     {
         build_copy(detail::view::make_adapter_input(detail::input_adapter(first, last)), ae, c, tc);
     }

tests/src/unit-json_view_builder.cpp

@@ -59,7 +59,8 @@ built build(const std::string& text, bool comments, bool trailing_commas, bool s
         r.copy.assign(text.begin(), text.end());
         src = r.copy.data();
     }
-    r.ok = nlohmann::detail::view::build < FloatType, !nlohmann::detail::abi_config::strict_nul_handling > (*r.data, src, text.size(), comments, trailing_commas, sentinel, r.failure);
+    constexpr bool nul_is_end = !nlohmann::detail::abi_config::strict_nul_handling;
+    r.ok = nlohmann::detail::view::build<FloatType, nul_is_end>(*r.data, src, text.size(), comments, trailing_commas, sentinel, false, r.failure);
     r.data->src = src;
     r.data->base[0] = src;
     r.data->base[1] = r.data->arena.data();
@@ -172,6 +173,22 @@ void check_string(const std::string& content)
     }
 }
 
+// accept() stores no nodes: it must accept and reject what json::accept does, for all options and for inputs with
+// and without a terminating NUL
+void check_accept(const std::string& text)
+{
+    CAPTURE(text)
+    const std::vector<char> bytes(text.begin(), text.end());
+    for (int options = 0; options < 4; ++options)
+    {
+        const bool comments = (options & 1) != 0;
+        const bool trailing_commas = (options & 2) != 0;
+        const bool accepted = json::accept(text, comments, trailing_commas);
+        CHECK(nlohmann::json_document::accept(text, comments, trailing_commas) == accepted);
+        CHECK(nlohmann::json_document::accept(bytes, comments, trailing_commas) == accepted);
+    }
+}
+
 // a small deterministic generator of documents
 struct generator
 {
@@ -423,6 +440,133 @@ TEST_CASE("json_view builder")
         }
     }
 
+    SECTION("accept() without an index")
+    {
+        for (const char* text :
+                {
+                    "", " ", "\n", "null", "nul", "true", "[", "]", "[]", "{}", "[1,2,3]", "[1,2,3", "[1,2,3,]", "{\"a\":1,}", "{\"a\"}", "{\"a\":}",
+                    "[1] x", "[1][2]", "\xEF\xBB\xBF[1]", "[\"a\\", "[\"\\u12\"]", "[\"\\ud800\"]", "[\"\x01\"]", "[\"\xff\"]", "[01]", "[1.]",
+                    "[.5]", "[-]", "[1e]", "// c\n[1]", "/* c */ {\"a\" /* x */ : 1}", "/* c", "[1] // c", "1e400", "-1e400", "123456789012345678901234567890",
+                    "{\"a\":1,\"a\":2}", "[[[]]]", "\"\\u00e4\\n\\ud83d\\ude00\""
+                })
+        {
+            check_accept(text);
+        }
+        // a null byte inside the text, and after it
+        check_accept(std::string("[1,\0]", 5));
+        check_accept(std::string("[1]\0", 4));
+        check_accept(std::string("\0", 1));
+
+        // generated documents and damaged copies, as for the builder above
+        generator g;
+        for (int i = 0; i < 2000; ++i)
+        {
+            std::string text;
+            g.value(text, 0);
+            check_accept(text);
+            std::string damaged = text;
+            const auto at = static_cast<std::size_t>(g.r(static_cast<int>(damaged.size())));
+            static const char replacements[] = {'x', '"', '\\', ',', ':', ']', '}', '[', '{', '1', '-', '.', 'e', '\0', '\n', '/'}; // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+            damaged[at] = replacements[g.r(16)];
+            check_accept(damaged);
+            check_accept(text.substr(0, at));
+        }
+
+        // nesting beyond the 64 levels that are kept on the builder's own stack, closed and not closed
+        for (const std::size_t depth :
+                {
+                    63, 64, 65, 66, 200, 1000
+                })
+        {
+            check_accept(std::string(depth, '[') + std::string(depth, ']'));
+            check_accept(std::string(depth, '[') + std::string(depth - 1, ']'));
+            std::string objects;
+            for (std::size_t i = 0; i < depth; ++i)
+            {
+                objects += "{\"k\":";
+            }
+            objects += "1" + std::string(depth, '}');
+            check_accept(objects);
+            check_accept(objects.substr(0, objects.size() - 1));
+        }
+
+        // objects with enough members to get a hash index when they are indexed (and duplicate keys)
+        std::string large = "{";
+        for (int i = 0; i < 300; ++i)
+        {
+            large += (i == 0 ? "\"k" : ",\"k") + std::to_string(i % 200) + "\":" + std::to_string(i);
+        }
+        check_accept(large + "}");
+        check_accept(large);
+        check_accept("[" + large + "},{" + large.substr(1) + "}]");
+
+        // the overflow check uses the floating-point type of the document
+        using float_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t, float>;
+        for (const char* text :
+                {
+                    "1e39", "-1e39", "3.4028235e38", "3.4028236e38", "[1.5e38, 3.5e38]", "{\"a\": 1e-50, \"b\": 1e39}", "340282356779733661637539395458142568448"
+                })
+        {
+            CAPTURE(text)
+            CHECK(nlohmann::basic_json_document<float_json>::accept(text) == float_json::accept(text));
+        }
+
+        // strings are checked and not decoded: runs of text of every length from 0 to 40 between valid and invalid
+        // escapes, UTF-8 sequences and control characters, in values and in keys, cut near the end of the text
+        const std::array<const char*, 9> valid = {{"\\n", "\\\"", "\\\\", "\\/", "\\t", "\\u00e4", "\\u20ac", "\\ud83d\\ude00", "\\u0000"}};
+        const std::array<const char*, 12> invalid = {{"\\x", "\\ud800", "\\udc00", "\\u12G4", "\\u12", "\\ud83dx", "\\ud83d\\u0041", "\\ud83d\\ud83d", "\\", "\x01", "\x1f", "\x7f"}};
+        const std::array<const char*, 6> utf8 = {{"\xc3\xa4", "\xe2\x82\xac", "\xf0\x9f\x98\x80", "\xc3", "\xff", "\x80"}};
+        std::mt19937 rng(2029); // NOLINT(cert-msc32-c,cert-msc51-cpp,bugprone-random-generator-seed): reproducible
+        for (std::size_t run = 0; run <= 40; ++run)
+        {
+            for (int i = 0; i < 30; ++i)
+            {
+                std::string content = std::string(rng() % 20, 'a');
+                const auto pieces = 1 + (rng() % 6);
+                for (unsigned k = 0; k < pieces; ++k)
+                {
+                    content += valid[rng() % valid.size()];
+                    content += std::string(k == 0 ? run : rng() % 41, static_cast<char>('b' + (rng() % 20)));
+                    switch (rng() % 8)
+                    {
+                        case 0:
+                            content += utf8[rng() % 3];
+                            break;
+                        case 1:
+                            content += utf8[rng() % utf8.size()];
+                            break;
+                        case 2:
+                            content += invalid[rng() % invalid.size()];
+                            break;
+                        default:
+                            break;
+                    }
+                }
+                for (const std::string& text :
+                        {
+                            "[\"" + content + "\"]", "{\"" + content + "\":1}", "[\"" + content, "[\"" + content.substr(0, content.size() - (rng() % 4)) + "\"]"
+                        })
+                {
+                    check_accept(text);
+                }
+            }
+        }
+    }
+
+    SECTION("escapes in a row")
+    {
+        for (const char* content :
+                {
+                    "\\n", "\\n\\t\\\\", "\\u00e9\\u00e9\\u4e2d", "\\u00e9\\u00e", "\\u00e9\\", "\\n\\q", "\\n\\ud83d\\ude00\\n",
+                    "\\ud83d\\ude00\\ud83d", "\\n\\n\\n abc \\n\\n", "\\n\x01", "\\n\xC3\x28", "\\n\\"
+                })
+        {
+            check_accept(std::string("[\"") + content + "\"]");
+            check_accept(std::string("[\"") + content);
+            check_accept(std::string("{\"") + content + "\":1}");
+        }
+    }
+
     SECTION("test files")
     {
         for (const char* name :

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())