Merge branch develop into claude/perf-iterator-ranges

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

include/nlohmann/detail/input/input_adapters.hpp

@@ -1348,6 +1348,64 @@ struct iterator_input_adapter_factory<IteratorType, SentinelType, enable_if_t<is
     }
 };
 
+/*!
+@brief whether @a IteratorType is an iterator of std::string or of a
+       std::vector of 1-byte elements
+
+Their elements are contiguous, but before C++20 that cannot be detected from
+the iterator type (std::contiguous_iterator), so an iterator pair of them would
+be read one character at a time through the iterators. They are read as the
+pointer range they are instead, as the containers themselves are (see the
+container overload of input_adapter()). The types are matched exactly, so no
+other iterator can be mistaken for one. (std::basic_string is only matched for
+char: other character types need std::char_traits specializations that the
+standard library need not have.)
+*/
+template<typename CharType>
+struct is_byte_char_type
+{
+    // a member, not an integral_constant argument, which astyle misformats
+    static constexpr bool value = sizeof(CharType) == 1 && std::is_integral<CharType>::value && !std::is_same<CharType, bool>::value;
+};
+
+template<typename IteratorType, typename CharType, bool IsByte = is_byte_char_type<CharType>::value>
+struct is_std_contiguous_byte_iterator_impl : std::false_type {};
+
+// (the containers are only named for byte types)
+template<typename IteratorType, typename CharType>
+struct is_std_contiguous_byte_iterator_impl<IteratorType, CharType, true>
+{
+    static constexpr bool value = !std::is_pointer<IteratorType>::value
+                                  && (std::is_same<IteratorType, typename std::vector<CharType>::iterator>::value
+                                      || std::is_same<IteratorType, typename std::vector<CharType>::const_iterator>::value
+                                      || std::is_same<IteratorType, std::string::iterator>::value
+                                      || std::is_same<IteratorType, std::string::const_iterator>::value);
+};
+
+template<typename IteratorType>
+struct is_std_contiguous_byte_iterator
+    : is_std_contiguous_byte_iterator_impl<IteratorType, typename std::remove_cv<typename std::iterator_traits<IteratorType>::value_type>::type> {};
+
+template<typename IteratorType>
+struct iterator_input_adapter_factory<IteratorType, IteratorType, enable_if_t<is_std_contiguous_byte_iterator<IteratorType>::value>>
+{
+    using iterator_type = IteratorType;
+    using sentinel_type = IteratorType;
+    using char_type = typename std::remove_cv<typename std::iterator_traits<iterator_type>::value_type>::type;
+    using adapter_type = iterator_input_adapter<const char_type*>;
+
+    static adapter_type create(IteratorType first, IteratorType last)
+    {
+        if (first == last)
+        {
+            // (an empty range must not be dereferenced)
+            return adapter_type(nullptr, nullptr);
+        }
+        const char_type* const begin = std::addressof(*first);
+        return adapter_type(begin, begin + (last - first));
+    }
+};
+
 // General purpose iterator-based input (iterator+sentinel pair; SentinelType
 // defaults to IteratorType for the common same-type case, but may differ for
 // C++20 ranges-style iterator+sentinel pairs). Only enable for types that can

single_include/nlohmann/json.hpp

@@ -10457,6 +10457,64 @@ struct iterator_input_adapter_factory<IteratorType, SentinelType, enable_if_t<is
     }
 };
 
+/*!
+@brief whether @a IteratorType is an iterator of std::string or of a
+       std::vector of 1-byte elements
+
+Their elements are contiguous, but before C++20 that cannot be detected from
+the iterator type (std::contiguous_iterator), so an iterator pair of them would
+be read one character at a time through the iterators. They are read as the
+pointer range they are instead, as the containers themselves are (see the
+container overload of input_adapter()). The types are matched exactly, so no
+other iterator can be mistaken for one. (std::basic_string is only matched for
+char: other character types need std::char_traits specializations that the
+standard library need not have.)
+*/
+template<typename CharType>
+struct is_byte_char_type
+{
+    // a member, not an integral_constant argument, which astyle misformats
+    static constexpr bool value = sizeof(CharType) == 1 && std::is_integral<CharType>::value && !std::is_same<CharType, bool>::value;
+};
+
+template<typename IteratorType, typename CharType, bool IsByte = is_byte_char_type<CharType>::value>
+struct is_std_contiguous_byte_iterator_impl : std::false_type {};
+
+// (the containers are only named for byte types)
+template<typename IteratorType, typename CharType>
+struct is_std_contiguous_byte_iterator_impl<IteratorType, CharType, true>
+{
+    static constexpr bool value = !std::is_pointer<IteratorType>::value
+                                  && (std::is_same<IteratorType, typename std::vector<CharType>::iterator>::value
+                                      || std::is_same<IteratorType, typename std::vector<CharType>::const_iterator>::value
+                                      || std::is_same<IteratorType, std::string::iterator>::value
+                                      || std::is_same<IteratorType, std::string::const_iterator>::value);
+};
+
+template<typename IteratorType>
+struct is_std_contiguous_byte_iterator
+    : is_std_contiguous_byte_iterator_impl<IteratorType, typename std::remove_cv<typename std::iterator_traits<IteratorType>::value_type>::type> {};
+
+template<typename IteratorType>
+struct iterator_input_adapter_factory<IteratorType, IteratorType, enable_if_t<is_std_contiguous_byte_iterator<IteratorType>::value>>
+{
+    using iterator_type = IteratorType;
+    using sentinel_type = IteratorType;
+    using char_type = typename std::remove_cv<typename std::iterator_traits<iterator_type>::value_type>::type;
+    using adapter_type = iterator_input_adapter<const char_type*>;
+
+    static adapter_type create(IteratorType first, IteratorType last)
+    {
+        if (first == last)
+        {
+            // (an empty range must not be dereferenced)
+            return adapter_type(nullptr, nullptr);
+        }
+        const char_type* const begin = std::addressof(*first);
+        return adapter_type(begin, begin + (last - first));
+    }
+};
+
 // General purpose iterator-based input (iterator+sentinel pair; SentinelType
 // defaults to IteratorType for the common same-type case, but may differ for
 // C++20 ranges-style iterator+sentinel pairs). Only enable for types that can

tests/src/unit-bson.cpp

@@ -1674,6 +1674,8 @@ TEST_CASE("BSON input that cannot be read is discarded by every overload")
     json _;
     CHECK_THROWS_AS(_ = json::from_bson(input.begin(), input.end()), json::parse_error&);
     CHECK(json::from_bson(input, true, false).is_discarded());
+    // false positive: Infer takes std::integral_constant<bool, false>::value for a pointer
+    // @infer-ignore NULLPTR_DEREFERENCE
     CHECK(json::from_bson(input.begin(), input.end(), true, false).is_discarded());
 #ifndef JSON_TEST_DEPRECATED_FUNCTIONS_DELETED
     CHECK(json::from_bson(input.data(), input.size(), true, false).is_discarded());

tests/src/unit-deserialization.cpp

@@ -32,6 +32,7 @@ using nlohmann::json;
 
 #include <iostream>
 #include <iterator>
+#include <list>
 #include <sstream>
 #include <string>
 #include <valarray>
@@ -1409,3 +1410,77 @@ TEST_CASE("indentation runs of every length around the 8-byte skip")
     CHECK(parse_result(indented("[\n~1]", std::string(17, ' ')), true) == "[1]");
 }
 #endif
+
+#if !defined(JSON_NOEXCEPTION)
+namespace
+{
+/// the value of parsing [first, last), or the message of the exception
+template<typename Iterator>
+std::string outcome_of(Iterator first, Iterator last)
+{
+    try
+    {
+        return json::parse(first, last).dump();
+    }
+    catch (const json::exception& e)
+    {
+        return e.what();
+    }
+}
+
+/// the bytes of @a text as a vector of @a T (explicit casts: no implicit char conversion)
+template<typename T>
+std::vector<T> bytes_as(const std::string& text)
+{
+    std::vector<T> result;
+    result.reserve(text.size());
+    for (const char c : text)
+    {
+        result.push_back(static_cast<T>(c));
+    }
+    return result;
+}
+
+/// a std::string, std::vector<char>, <unsigned char> and <signed char> as
+/// iterator pairs: the same as the byte path (std::list iterators)
+void check_iterator_pairs(const std::string& text)
+{
+    CAPTURE(text)
+    const std::list<char> bytes(text.begin(), text.end());
+    const std::string expected = outcome_of(bytes.begin(), bytes.end());
+    const bool expected_accept = json::accept(bytes.begin(), bytes.end());
+
+    std::string s = text;
+    CHECK(outcome_of(s.begin(), s.end()) == expected);
+    CHECK(outcome_of(s.cbegin(), s.cend()) == expected);
+    CHECK(json::accept(s.cbegin(), s.cend()) == expected_accept);
+
+    const std::vector<char> vc(text.begin(), text.end());
+    CHECK(outcome_of(vc.begin(), vc.end()) == expected);
+    const std::vector<unsigned char> vu = bytes_as<unsigned char>(text);
+    CHECK(outcome_of(vu.begin(), vu.end()) == expected);
+    CHECK(json::accept(vu.begin(), vu.end()) == expected_accept);
+    const std::vector<signed char> vs = bytes_as<signed char>(text);
+    CHECK(outcome_of(vs.begin(), vs.end()) == expected);
+}
+}  // namespace
+
+TEST_CASE("deserialization from iterator pairs of std::string and std::vector")
+{
+    // these are read as the pointer range they are, also before C++20
+    for (const char* text :
+            {
+                "", " ", R"([1, 2.5, "a", true, null, {"k": ["v"]}])", "[1, 2", R"({"a" 1})", "\"\xC3\xA4\"", "\"\xC3\"", "[1]x", "1e400"
+            })
+    {
+        check_iterator_pairs(text);
+    }
+    check_iterator_pairs(std::string("[1]" "\0" "x", 5));
+
+    // an empty range is not dereferenced
+    std::string empty;
+    CHECK_FALSE(json::accept(empty.begin(), empty.end()));
+    json _;
+    CHECK_THROWS_AS(_ = json::parse(empty.begin(), empty.end()), json::parse_error&);
+}
+#endif