Require a container's value_type to match what data() points at

is_contiguous_byte_container accepted any type with a data() returning a
pointer to a single-byte integral plus a size(). That is duck typing: the two
members say nothing about size() counting the units data() points at.

A type where it does not - fixed-size records, say - was routed to the
pointer-based adapter and parsed as [data(), data() + size()) bytes, silently
truncating input the iterator-based adapter had read in full:

    struct record_buffer {
        using value_type = std::array<char, 4>;
        std::string bytes;
        const char* data() const;                        // raw bytes
        std::size_t size() const;                        // in records
        const char* begin() const; const char* end() const;
    };
    json::parse(record_buffer{"[1,2,3,4,5]"});           // parse error at column 3

Requiring the container's own value_type to be that same element type ties the
two together. Every contiguous standard container satisfies it, so std::string,
std::vector<char>, std::array<char, N> and std::string_view keep the fast path;
anything else falls back to the iterator-based adapter, which is always correct.

Co-Authored-By: Claude <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MXDi7NTMKAmoArUZSKMc4T
Signed-off-by: Niels Lohmann <mail@nlohmann.me>

include/nlohmann/detail/input/input_adapters.hpp

@@ -620,23 +620,45 @@ typename iterator_input_adapter_factory<IteratorType, SentinelType>::adapter_typ
     return factory_type::create(first, last);
 }
 
+// The element type a container's data() points at, cv-qualifiers removed.
+// Ill-formed - and therefore SFINAE-friendly - for types without data().
+template<typename ContainerType>
+using container_data_t = typename std::remove_cv<typename std::remove_pointer <
+                         decltype(std::declval<const ContainerType&>().data()) >::type >::type;
+
+// The container's own element type, cv-qualifiers removed. It is looked up on
+// the bare type so it is also found when ContainerType is deduced as a
+// reference by the forwarding-reference overload below.
+template<typename ContainerType>
+using container_value_t = typename std::remove_cv <
+                          typename std::remove_cv<typename std::remove_reference<ContainerType>::type>::type::value_type >::type;
+
 // Detect a container that stores its elements contiguously as single bytes
 // (std::string, std::vector<char/unsigned char>, std::array<char, N>,
 // std::string_view, ...). Such inputs are wrapped in a pointer-based adapter so
 // they benefit from the contiguous fast paths (bulk string scanning, memcpy for
 // binary formats) in every C++ standard - not only in C++20, where the standard
 // library iterators model std::contiguous_iterator and are detected directly.
+//
+// data() and size() on their own would be duck typing: they say nothing about
+// size() counting the units data() points at, and reading [data(), data() +
+// size()) as bytes would be wrong for a type where it does not. Requiring the
+// container's own value_type to be that same single-byte element ties the two
+// together; every contiguous standard container satisfies it. Anything else
+// keeps the iterator-based adapter, which is always correct - only slower.
 template<typename ContainerType, typename = void>
 struct is_contiguous_byte_container : std::false_type {};
 
 template<typename ContainerType>
 struct is_contiguous_byte_container < ContainerType, void_t <
-decltype(std::declval<const ContainerType&>().data()),
+    container_data_t<ContainerType>,
+    container_value_t<ContainerType>,
 decltype(std::declval<const ContainerType&>().size()) >>
             : std::integral_constant < bool,
         std::is_pointer<decltype(std::declval<const ContainerType&>().data())>::value&&
-        std::is_integral<typename std::remove_pointer<decltype(std::declval<const ContainerType&>().data())>::type>::value&&
+        std::is_integral<container_data_t<ContainerType>>::value&&
-        sizeof(typename std::remove_pointer<decltype(std::declval<const ContainerType&>().data())>::type) == 1 > {};
+        sizeof(container_data_t<ContainerType>) == 1 &&
+        std::is_same<container_data_t<ContainerType>, container_value_t<ContainerType>>::value > {};
 
 // Convenience shorthand from container to iterator
 // Enables ADL on begin(container) and end(container)

single_include/nlohmann/json.hpp

@@ -7623,23 +7623,45 @@ typename iterator_input_adapter_factory<IteratorType, SentinelType>::adapter_typ
     return factory_type::create(first, last);
 }
 
+// The element type a container's data() points at, cv-qualifiers removed.
+// Ill-formed - and therefore SFINAE-friendly - for types without data().
+template<typename ContainerType>
+using container_data_t = typename std::remove_cv<typename std::remove_pointer <
+                         decltype(std::declval<const ContainerType&>().data()) >::type >::type;
+
+// The container's own element type, cv-qualifiers removed. It is looked up on
+// the bare type so it is also found when ContainerType is deduced as a
+// reference by the forwarding-reference overload below.
+template<typename ContainerType>
+using container_value_t = typename std::remove_cv <
+                          typename std::remove_cv<typename std::remove_reference<ContainerType>::type>::type::value_type >::type;
+
 // Detect a container that stores its elements contiguously as single bytes
 // (std::string, std::vector<char/unsigned char>, std::array<char, N>,
 // std::string_view, ...). Such inputs are wrapped in a pointer-based adapter so
 // they benefit from the contiguous fast paths (bulk string scanning, memcpy for
 // binary formats) in every C++ standard - not only in C++20, where the standard
 // library iterators model std::contiguous_iterator and are detected directly.
+//
+// data() and size() on their own would be duck typing: they say nothing about
+// size() counting the units data() points at, and reading [data(), data() +
+// size()) as bytes would be wrong for a type where it does not. Requiring the
+// container's own value_type to be that same single-byte element ties the two
+// together; every contiguous standard container satisfies it. Anything else
+// keeps the iterator-based adapter, which is always correct - only slower.
 template<typename ContainerType, typename = void>
 struct is_contiguous_byte_container : std::false_type {};
 
 template<typename ContainerType>
 struct is_contiguous_byte_container < ContainerType, void_t <
-decltype(std::declval<const ContainerType&>().data()),
+    container_data_t<ContainerType>,
+    container_value_t<ContainerType>,
 decltype(std::declval<const ContainerType&>().size()) >>
             : std::integral_constant < bool,
         std::is_pointer<decltype(std::declval<const ContainerType&>().data())>::value&&
-        std::is_integral<typename std::remove_pointer<decltype(std::declval<const ContainerType&>().data())>::type>::value&&
+        std::is_integral<container_data_t<ContainerType>>::value&&
-        sizeof(typename std::remove_pointer<decltype(std::declval<const ContainerType&>().data())>::type) == 1 > {};
+        sizeof(container_data_t<ContainerType>) == 1 &&
+        std::is_same<container_data_t<ContainerType>, container_value_t<ContainerType>>::value > {};
 
 // Convenience shorthand from container to iterator
 // Enables ADL on begin(container) and end(container)

tests/src/unit-user_defined_input.cpp

@@ -18,6 +18,9 @@
 #include <nlohmann/json.hpp>
 using nlohmann::json;
 
+#include <array> // array
+#include <cstddef> // size_t
+#include <cstdint> // uint8_t
 #include <list>
 #include <string> // string
 #include <vector> // vector
@@ -214,6 +217,65 @@ TEST_CASE("Parse with heterogeneous iterator and sentinel types")
     CHECK(j2.at(0) == 1);
 }
 
+// A type whose data() hands out raw bytes but whose size() counts something
+// else - here fixed-size records. Reading [data(), data() + size()) as bytes
+// would silently truncate the input, so data() and size() alone must not be
+// taken as evidence of contiguous byte storage.
+struct record_buffer
+{
+    using value_type = std::array<char, 4>;
+
+    std::string bytes;
+
+    const char* data() const noexcept
+    {
+        return bytes.data();
+    }
+    std::size_t size() const noexcept
+    {
+        return bytes.size() / sizeof(value_type);
+    }
+    const char* begin() const noexcept
+    {
+        return bytes.data();
+    }
+    const char* end() const noexcept
+    {
+        return bytes.data() + bytes.size();
+    }
+};
+
+TEST_CASE("Contiguous byte containers take the pointer adapter")
+{
+    // Containers with contiguous single-byte storage are routed through the
+    // pointer-based adapter so the bulk fast paths apply in every standard, not
+    // only in C++20 where the library iterators model std::contiguous_iterator.
+    CHECK(nlohmann::detail::is_contiguous_byte_container<std::string>::value);
+    CHECK(nlohmann::detail::is_contiguous_byte_container<std::vector<char>>::value);
+    CHECK(nlohmann::detail::is_contiguous_byte_container<std::vector<std::uint8_t>>::value);
+    CHECK(nlohmann::detail::is_contiguous_byte_container<std::array<char, 4>>::value);
+
+    // input_adapter() takes its container by forwarding reference, so the trait
+    // is also asked about reference types
+    CHECK(nlohmann::detail::is_contiguous_byte_container<std::string&>::value);
+    CHECK(nlohmann::detail::is_contiguous_byte_container<const std::string&>::value);
+
+    // everything else keeps the iterator-based adapter
+    CHECK_FALSE(nlohmann::detail::is_contiguous_byte_container<std::list<char>>::value);
+    CHECK_FALSE(nlohmann::detail::is_contiguous_byte_container<std::vector<int>>::value);
+    CHECK_FALSE(nlohmann::detail::is_contiguous_byte_container<const char*>::value);
+
+    // including a type that has data() and size() but whose size() does not
+    // count the units data() points at: its value_type says so
+    CHECK_FALSE(nlohmann::detail::is_contiguous_byte_container<record_buffer>::value);
+
+    // and such a container still parses through its iterators, in full - taking
+    // it for a byte container would stop after data() + size() bytes
+    const record_buffer buffer{"[1,2,3,4,5]"};
+    CHECK(buffer.size() * sizeof(record_buffer::value_type) < buffer.bytes.size());
+    CHECK(json::parse(buffer) == json({1, 2, 3, 4, 5}));
+}
+
 #if defined(__cpp_lib_concepts) && defined(JSON_HAS_CPP_20)
 // JSON_HAS_CPP_20 (do not remove; see note at top of file)
 TEST_CASE("Parse with std::counted_iterator and std::default_sentinel_t")