Merge branch 'develop' into claude/copy-without-assignable-base-5674

Conflicts:
- include/nlohmann/json.hpp: copy_array_level() keeps develop's #5721
  "set the array type only once the container exists" and then builds the
  elements with the PR's copy_construct_tag emplace_back loop
- single_include/nlohmann/json.hpp: regenerated with make amalgamate

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

include/nlohmann/detail/json_pointer.hpp

@@ -679,29 +679,19 @@ class json_pointer
                         return nullptr;
                     }
 
-                    // tokens that array_index() rejects with parse_error.106/109
-                    // are passed on to it; all other tokens that it would reject
-                    // with out_of_range.404/410 are detected here, so that this
-                    // also works without exceptions
-                    if (JSON_HEDLEY_UNLIKELY(reference_token.size() > 1 && !(reference_token[0] >= '1' && reference_token[0] <= '9')))
+                    // may throw parse_error.106/109 for a malformed index; an
+                    // index that is syntactically valid but cannot be
+                    // represented (out_of_range.404/410) is treated like an
+                    // out-of-range index below
+                    typename BasicJsonType::size_type idx{};
+                    JSON_TRY
                     {
-                        static_cast<void>(array_index<BasicJsonType>(reference_token)); // throws parse_error.106/109
+                        idx = array_index<BasicJsonType>(reference_token);
                     }
-                    if (JSON_HEDLEY_UNLIKELY(reference_token.empty() || !std::all_of(reference_token.begin(), reference_token.end(), [](const char c)
-                {
-                    return c >= '0' && c <= '9';
-                })))
+                    JSON_INTERNAL_CATCH (detail::out_of_range&)
                     {
                         return nullptr;
                     }
-                    errno = 0; // strtoull() does not reset errno on success
-                    char* p_end = nullptr; // NOLINT(misc-const-correctness)
-                    const unsigned long long magnitude = std::strtoull(reference_token.data(), &p_end, 10); // NOLINT(runtime/int)
-                    if (JSON_HEDLEY_UNLIKELY(errno == ERANGE || magnitude >= static_cast<unsigned long long>((std::numeric_limits<typename BasicJsonType::size_type>::max)()))) // NOLINT(runtime/int)
-                    {
-                        return nullptr;
-                    }
-                    const auto idx = static_cast<typename BasicJsonType::size_type>(magnitude);
 
                     if (JSON_HEDLEY_UNLIKELY(idx >= ptr->m_data.m_value.array->size()))
                     {

include/nlohmann/json.hpp

@@ -1004,19 +1004,39 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     using copy_scratch_value_t = std::pair<typename object_t::key_type, basic_json>;
     using copy_scratch_t = std::vector<copy_scratch_value_t, AllocatorType<copy_scratch_value_t>>;
 
-    /// @brief copy everything of @a src into @a dst but its type and value
-    static void copy_metadata(const basic_json& src, basic_json& dst)
-    {
-        // a custom base class is only required to be copy-constructible and
-        // move-assignable, so the copy has to go through a temporary
-        static_cast<json_base_class_t&>(dst) = json_base_class_t(static_cast<const json_base_class_t&>(src));
+    /// @brief tag selecting the constructor below; used only to build the
+    /// elements of a deep copy (@ref copy_array_level, @ref copy_object_level)
+    struct copy_construct_tag {};
 
+  public:
+    /*!
+    @brief construct a null value whose base class - and, with @ref
+           JSON_DIAGNOSTIC_POSITIONS, positions - are copied from @a src
+
+    Copy-constructing @ref json_base_class_t here, rather than default-
+    constructing the element and assigning its base class afterwards, means
+    that copying a @ref basic_json only ever requires a copy-constructible
+    base class, and never a move-assignable one as well.
+
+    @note this constructor has to be public: @ref copy_array_level and
+          @ref copy_object_level reach it through @ref array_t's or @ref
+          object_t's own emplace_back(), which constructs the element from
+          outside @ref basic_json and so cannot call a private constructor.
+          @ref copy_construct_tag is private, though, and nothing in the
+          public interface hands out a value of it, so outside code can still
+          never name it to call this constructor itself.
+    */
+    basic_json(copy_construct_tag /*unused*/, const basic_json& src)
+        : json_base_class_t(src)
 #if JSON_DIAGNOSTIC_POSITIONS
-        dst.start_position = src.start_position;
-        dst.end_position = src.end_position;
+        , start_position(src.start_position)
+        , end_position(src.end_position)
 #endif
+    {
     }
 
+  private:
+
     /*!
     @brief copy the value of @a src into @a dst, which must not be structured
 
@@ -1079,8 +1099,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     }
 
     /*!
-    @brief copy everything of @a src into the null value @a dst but the children
+    @brief finish the copy @a dst of @a src that a @ref copy_construct_tag
+           constructor started, other than the children of an object or array
 
+    @a dst already has @a src's base class and, with @ref
+    JSON_DIAGNOSTIC_POSITIONS, positions; only its value is still missing.
     Objects and arrays are not copied here; they are appended to @a worklist to
     be created later by @ref copy_iteratively. Until that happens, @a dst remains
     a null value, so that a partially built copy can be destroyed at any point
@@ -1088,8 +1111,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     */
     static void copy_shallow(const basic_json& src, basic_json& dst, copy_worklist_t& worklist)
     {
-        copy_metadata(src, dst);
-
         if (src.m_data.m_type == value_t::object || src.m_data.m_type == value_t::array)
         {
             // defer: dst stays a null value until its container exists
@@ -1110,15 +1131,19 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     {
         const array_t& src_array = *src.m_data.m_value.array;
 
-        // create all elements up front: growing the array afterwards could
-        // invalidate the pointers that are handed to the worklist; resize()
-        // rather than the fill constructor, because not every array type
-        // provides the latter (e.g., ones without a matching allocator-aware
-        // fill constructor)
         dst.m_data.m_value.array = create<array_t>();
         // only now that the array exists may dst stop being a null value
         dst.m_data.m_type = value_t::array;
-        dst.m_data.m_value.array->resize(src_array.size());
+
+        // create every element - its base class already copy-constructed from
+        // its counterpart in src, via the copy_construct_tag constructor -
+        // before any of their addresses are handed to worklist below: growing
+        // the array while that is going on could reallocate it and invalidate
+        // addresses taken from an earlier iteration
+        for (const auto& src_element : src_array)
+        {
+            dst.m_data.m_value.array->emplace_back(copy_construct_tag{}, src_element);
+        }
 
         auto dst_it = dst.m_data.m_value.array->begin();
         for (auto src_it = src_array.cbegin(); src_it != src_array.cend(); ++src_it, ++dst_it)
@@ -1136,12 +1161,14 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
         // build the complete key skeleton and hand it to the object's range
         // constructor: adding the keys one by one would be quadratic for object
-        // types that are backed by a vector, such as nlohmann::ordered_map
+        // types that are backed by a vector, such as nlohmann::ordered_map; each
+        // value's base class is already copy-constructed from its counterpart
+        // in src, via the copy_construct_tag constructor
         scratch.clear();
         scratch.reserve(src_object.size());
         for (const auto& element : src_object)
         {
-            scratch.emplace_back(element.first, basic_json());
+            scratch.emplace_back(element.first, basic_json(copy_construct_tag{}, element.second));
         }
 
         dst.m_data.m_value.object = create<object_t>(std::make_move_iterator(scratch.begin()),

single_include/nlohmann/json.hpp

@@ -20291,29 +20291,19 @@ class json_pointer
                         return nullptr;
                     }
 
-                    // tokens that array_index() rejects with parse_error.106/109
-                    // are passed on to it; all other tokens that it would reject
-                    // with out_of_range.404/410 are detected here, so that this
-                    // also works without exceptions
-                    if (JSON_HEDLEY_UNLIKELY(reference_token.size() > 1 && !(reference_token[0] >= '1' && reference_token[0] <= '9')))
+                    // may throw parse_error.106/109 for a malformed index; an
+                    // index that is syntactically valid but cannot be
+                    // represented (out_of_range.404/410) is treated like an
+                    // out-of-range index below
+                    typename BasicJsonType::size_type idx{};
+                    JSON_TRY
                     {
-                        static_cast<void>(array_index<BasicJsonType>(reference_token)); // throws parse_error.106/109
+                        idx = array_index<BasicJsonType>(reference_token);
                     }
-                    if (JSON_HEDLEY_UNLIKELY(reference_token.empty() || !std::all_of(reference_token.begin(), reference_token.end(), [](const char c)
-                {
-                    return c >= '0' && c <= '9';
-                })))
+                    JSON_INTERNAL_CATCH (detail::out_of_range&)
                     {
                         return nullptr;
                     }
-                    errno = 0; // strtoull() does not reset errno on success
-                    char* p_end = nullptr; // NOLINT(misc-const-correctness)
-                    const unsigned long long magnitude = std::strtoull(reference_token.data(), &p_end, 10); // NOLINT(runtime/int)
-                    if (JSON_HEDLEY_UNLIKELY(errno == ERANGE || magnitude >= static_cast<unsigned long long>((std::numeric_limits<typename BasicJsonType::size_type>::max)()))) // NOLINT(runtime/int)
-                    {
-                        return nullptr;
-                    }
-                    const auto idx = static_cast<typename BasicJsonType::size_type>(magnitude);
 
                     if (JSON_HEDLEY_UNLIKELY(idx >= ptr->m_data.m_value.array->size()))
                     {
@@ -27941,19 +27931,39 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     using copy_scratch_value_t = std::pair<typename object_t::key_type, basic_json>;
     using copy_scratch_t = std::vector<copy_scratch_value_t, AllocatorType<copy_scratch_value_t>>;
 
-    /// @brief copy everything of @a src into @a dst but its type and value
-    static void copy_metadata(const basic_json& src, basic_json& dst)
-    {
-        // a custom base class is only required to be copy-constructible and
-        // move-assignable, so the copy has to go through a temporary
-        static_cast<json_base_class_t&>(dst) = json_base_class_t(static_cast<const json_base_class_t&>(src));
+    /// @brief tag selecting the constructor below; used only to build the
+    /// elements of a deep copy (@ref copy_array_level, @ref copy_object_level)
+    struct copy_construct_tag {};
 
+  public:
+    /*!
+    @brief construct a null value whose base class - and, with @ref
+           JSON_DIAGNOSTIC_POSITIONS, positions - are copied from @a src
+
+    Copy-constructing @ref json_base_class_t here, rather than default-
+    constructing the element and assigning its base class afterwards, means
+    that copying a @ref basic_json only ever requires a copy-constructible
+    base class, and never a move-assignable one as well.
+
+    @note this constructor has to be public: @ref copy_array_level and
+          @ref copy_object_level reach it through @ref array_t's or @ref
+          object_t's own emplace_back(), which constructs the element from
+          outside @ref basic_json and so cannot call a private constructor.
+          @ref copy_construct_tag is private, though, and nothing in the
+          public interface hands out a value of it, so outside code can still
+          never name it to call this constructor itself.
+    */
+    basic_json(copy_construct_tag /*unused*/, const basic_json& src)
+        : json_base_class_t(src)
 #if JSON_DIAGNOSTIC_POSITIONS
-        dst.start_position = src.start_position;
-        dst.end_position = src.end_position;
+        , start_position(src.start_position)
+        , end_position(src.end_position)
 #endif
+    {
     }
 
+  private:
+
     /*!
     @brief copy the value of @a src into @a dst, which must not be structured
 
@@ -28016,8 +28026,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     }
 
     /*!
-    @brief copy everything of @a src into the null value @a dst but the children
+    @brief finish the copy @a dst of @a src that a @ref copy_construct_tag
+           constructor started, other than the children of an object or array
 
+    @a dst already has @a src's base class and, with @ref
+    JSON_DIAGNOSTIC_POSITIONS, positions; only its value is still missing.
     Objects and arrays are not copied here; they are appended to @a worklist to
     be created later by @ref copy_iteratively. Until that happens, @a dst remains
     a null value, so that a partially built copy can be destroyed at any point
@@ -28025,8 +28038,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     */
     static void copy_shallow(const basic_json& src, basic_json& dst, copy_worklist_t& worklist)
     {
-        copy_metadata(src, dst);
-
         if (src.m_data.m_type == value_t::object || src.m_data.m_type == value_t::array)
         {
             // defer: dst stays a null value until its container exists
@@ -28047,15 +28058,19 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     {
         const array_t& src_array = *src.m_data.m_value.array;
 
-        // create all elements up front: growing the array afterwards could
-        // invalidate the pointers that are handed to the worklist; resize()
-        // rather than the fill constructor, because not every array type
-        // provides the latter (e.g., ones without a matching allocator-aware
-        // fill constructor)
         dst.m_data.m_value.array = create<array_t>();
         // only now that the array exists may dst stop being a null value
         dst.m_data.m_type = value_t::array;
-        dst.m_data.m_value.array->resize(src_array.size());
+
+        // create every element - its base class already copy-constructed from
+        // its counterpart in src, via the copy_construct_tag constructor -
+        // before any of their addresses are handed to worklist below: growing
+        // the array while that is going on could reallocate it and invalidate
+        // addresses taken from an earlier iteration
+        for (const auto& src_element : src_array)
+        {
+            dst.m_data.m_value.array->emplace_back(copy_construct_tag{}, src_element);
+        }
 
         auto dst_it = dst.m_data.m_value.array->begin();
         for (auto src_it = src_array.cbegin(); src_it != src_array.cend(); ++src_it, ++dst_it)
@@ -28073,12 +28088,14 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
         // build the complete key skeleton and hand it to the object's range
         // constructor: adding the keys one by one would be quadratic for object
-        // types that are backed by a vector, such as nlohmann::ordered_map
+        // types that are backed by a vector, such as nlohmann::ordered_map; each
+        // value's base class is already copy-constructed from its counterpart
+        // in src, via the copy_construct_tag constructor
         scratch.clear();
         scratch.reserve(src_object.size());
         for (const auto& element : src_object)
         {
-            scratch.emplace_back(element.first, basic_json());
+            scratch.emplace_back(element.first, basic_json(copy_construct_tag{}, element.second));
         }
 
         dst.m_data.m_value.object = create<object_t>(std::make_move_iterator(scratch.begin()),

tests/src/unit-custom-base-class.cpp

@@ -405,3 +405,73 @@ TEST_CASE("JSON Visit Node")
         );
     CHECK(expected.empty());
 }
+
+// A custom base class with a const member: copy-constructible (initializing a
+// const member works fine), but not copy-/move-assignable (assigning one does
+// not). Used to check that copy construction never requires more than that.
+struct const_member_base
+{
+    const int id = 7; // NOLINT(misc-non-private-member-variables-in-classes)
+};
+
+using json_with_const_base = nlohmann::basic_json <
+                             std::map,
+                             std::vector,
+                             std::string,
+                             bool,
+                             std::int64_t,
+                             std::uint64_t,
+                             double,
+                             std::allocator,
+                             nlohmann::adl_serializer,
+                             std::vector<std::uint8_t>,
+                             const_member_base
+                             >;
+
+// build an array nested @a depth levels deep, with the innermost value 1;
+// every level is constructed (never assigned), since const_member_base does
+// not support assignment
+static json_with_const_base make_nested_array(std::size_t depth)
+{
+    if (depth == 0)
+    {
+        return json_with_const_base(1);
+    }
+    return json_with_const_base::array({make_nested_array(depth - 1)});
+}
+
+TEST_CASE("Regression test for issue #5674 - copy construction must not require an assignable base class")
+{
+    SECTION("depth 0")
+    {
+        // as in the original bug report: copy construction only, no assignment
+        const json_with_const_base j = {1, 2};
+        const json_with_const_base copy = j; // NOLINT(performance-unnecessary-copy-initialization)
+
+        CHECK(copy.size() == 2);
+        CHECK(copy.id == 7);
+    }
+
+    SECTION("nested deeper than the copy constructor's descent bound")
+    {
+        // beyond nesting_depth_limit() (128) levels, the copy constructor
+        // copies without the call stack (copy_iteratively / copy_array_level),
+        // which used to assign the base class of every element it created
+        const std::size_t depth = 300;
+
+        const json_with_const_base j = make_nested_array(depth);
+        const json_with_const_base copy = j; // NOLINT(performance-unnecessary-copy-initialization)
+
+        const json_with_const_base* c = &copy;
+        for (std::size_t level = 0; level <= depth; ++level)
+        {
+            CAPTURE(level)
+            REQUIRE(c->id == 7);
+            if (level < depth)
+            {
+                c = &c->at(0);
+            }
+        }
+        CHECK(*c == 1);
+    }
+}

tests/src/unit-disabled_exceptions.cpp

@@ -47,21 +47,6 @@ TEST_CASE("Tests with disabled exceptions")
         delete sax_no_exception::error_string; // NOLINT(cppcoreguidelines-owning-memory)
     }
 
-    SECTION("issue #5672 - value(json_pointer, default) must not abort for array tokens that are not a valid index")
-    {
-        const json j = {1, 2, 3};
-
-        // a syntactically valid index that is out of range for this array
-        CHECK(j.value("/7"_json_pointer, 42) == 42);
-        // a reference token that is not a number at all
-        CHECK(j.value("/1a"_json_pointer, 42) == 42);
-        // the empty reference token (JSON pointer "/")
-        CHECK(j.value("/"_json_pointer, 42) == 42);
-        // an index whose magnitude does not fit into size_type
-        CHECK(j.value("/99999999999999999999999"_json_pointer, 42) == 42);
-        CHECK(j.value("/18446744073709551615"_json_pointer, 42) == 42);
-    }
-
     SECTION("growing an ordered_json object")
     {
         auto j = nlohmann::ordered_json::object();

tests/src/unit-element_access2.cpp

@@ -516,21 +516,6 @@ TEST_CASE_TEMPLATE("element access 2", Json, nlohmann::json, nlohmann::ordered_j
                     CHECK(j_array.value("/-"_json_pointer, 42) == 42);
                     CHECK(j_array_const.value("/-"_json_pointer, 42) == 42);
 
-                    // Test an index with a non-digit after a valid leading digit; this is
-                    // out_of_range (not parse_error) and must not throw (see #5672)
-                    CHECK(j_array.value("/1a"_json_pointer, 42) == 42);
-                    CHECK(j_array_const.value("/1a"_json_pointer, 42) == 42);
-
-                    // Test the empty reference token (JSON pointer "/"); see #5672
-                    CHECK(j_array.value("/"_json_pointer, 42) == 42);
-                    CHECK(j_array_const.value("/"_json_pointer, 42) == 42);
-
-                    // Test an index whose magnitude does not fit into size_type (see #5672)
-                    CHECK(j_array.value("/99999999999999999999999"_json_pointer, 42) == 42);
-                    CHECK(j_array_const.value("/99999999999999999999999"_json_pointer, 42) == 42);
-                    CHECK(j_array.value("/18446744073709551615"_json_pointer, 42) == 42);
-                    CHECK(j_array_const.value("/18446744073709551615"_json_pointer, 42) == 42);
-
 #if !defined(JSON_NOEXCEPTION)
                     // Test malformed index (non-numeric) throws parse_error
                     CHECK_THROWS_WITH_AS(j_array.value("/foo"_json_pointer, 1), "[json.exception.parse_error.109] parse error: array index 'foo' is not a number", typename Json::parse_error&);