diff --git a/docs/mkdocs/docs/api/basic_json/accept.md b/docs/mkdocs/docs/api/basic_json/accept.md index df239713f..dac5f9f36 100644 --- a/docs/mkdocs/docs/api/basic_json/accept.md +++ b/docs/mkdocs/docs/api/basic_json/accept.md @@ -8,8 +8,8 @@ static bool accept(InputType&& i, const bool ignore_trailing_commas = false); // (2) -template -static bool accept(IteratorType first, IteratorType last, +template +static bool accept(IteratorType first, SentinelType last, const bool ignore_comments = false, const bool ignore_trailing_commas = false); ``` @@ -17,10 +17,11 @@ static bool accept(IteratorType first, IteratorType last, Checks whether the input is valid JSON. 1. Reads from a compatible input. -2. Reads from a pair of character iterators +2. Reads from a pair of character iterators, or an iterator and a sentinel of a different type (C++20 ranges support) The value_type of the iterator must be an integral type with a size of 1, 2, or 4 bytes, which will be interpreted - respectively as UTF-8, UTF-16, and UTF-32. + respectively as UTF-8, UTF-16, and UTF-32. If `SentinelType` differs from `IteratorType`, it must be comparable to + the iterator type with `operator!=`. Unlike the [`parse()`](parse.md) function, this function neither throws an exception in case of invalid JSON input (i.e., a parse error) nor creates diagnostic information. @@ -44,6 +45,12 @@ Unlike the [`parse()`](parse.md) function, this function neither throws an excep - a pair of `std::string::iterator` or `std::vector::iterator` - a pair of pointers such as `ptr` and `ptr + len` +`SentinelType` +: defaults to `IteratorType`; may be a different type comparable to `IteratorType` via `operator!=`, for instance. + + - a custom sentinel type for C++20 ranges + - `std::counted_iterator` with a different sentinel type + ## Parameters `i` (in) @@ -61,7 +68,7 @@ Unlike the [`parse()`](parse.md) function, this function neither throws an excep : iterator to the start of the character range `last` (in) -: iterator to the end of the character range +: iterator to the end of the character range, or a sentinel value that compares equal to the end iterator with `operator!=` ## Return value @@ -112,6 +119,7 @@ A UTF-8 byte order mark is silently ignored. - Changed [runtime assertion](../../features/assertions.md) in case of `FILE*` null pointers to exception in version 3.12.0. - Added `ignore_trailing_commas` in version 3.13.0. - Extended container support (1) to include types with lvalue-only ADL `begin`/`end` (matching `std::begin`/`std::end` semantics) in version 3.13.0. +- Extended overload (2) to accept heterogeneous iterator+sentinel pairs (C++20 ranges support) in version 3.13.0. !!! warning "Deprecation" diff --git a/docs/mkdocs/docs/api/basic_json/from_bjdata.md b/docs/mkdocs/docs/api/basic_json/from_bjdata.md index 8558e36ec..150f17aac 100644 --- a/docs/mkdocs/docs/api/basic_json/from_bjdata.md +++ b/docs/mkdocs/docs/api/basic_json/from_bjdata.md @@ -7,8 +7,8 @@ static basic_json from_bjdata(InputType&& i, const bool strict = true, const bool allow_exceptions = true); // (2) -template -static basic_json from_bjdata(IteratorType first, IteratorType last, +template +static basic_json from_bjdata(IteratorType first, SentinelType last, const bool strict = true, const bool allow_exceptions = true); ``` @@ -16,7 +16,7 @@ static basic_json from_bjdata(IteratorType first, IteratorType last, Deserializes a given input to a JSON value using the BJData (Binary JData) serialization format. 1. Reads from a compatible input. -2. Reads from an iterator range. +2. Reads from an iterator range, or an iterator and a sentinel of a different type (C++20 ranges support). The exact mapping and its limitations are described on a [dedicated page](../../features/binary_formats/bjdata.md). @@ -35,6 +35,10 @@ The exact mapping and its limitations are described on a [dedicated page](../../ `IteratorType` : a compatible iterator type +`SentinelType` +: defaults to `IteratorType`; may be a different type comparable to `IteratorType` via `operator!=`, for instance a + custom sentinel type for C++20 ranges + ## Parameters `i` (in) @@ -44,7 +48,7 @@ The exact mapping and its limitations are described on a [dedicated page](../../ : iterator to the start of the input `last` (in) -: iterator to the end of the input +: iterator to the end of the input, or a sentinel value that compares equal to the end iterator with `operator!=` `strict` (in) : whether to expect the input to be consumed until EOF (`#!cpp true` by default) @@ -103,3 +107,4 @@ Linear in the size of the input. - Added in version 3.11.0. - Extended container support (1) to include types with lvalue-only ADL `begin`/`end` (matching `std::begin`/`std::end` semantics) in version 3.13.0. +- Extended overload (2) to accept heterogeneous iterator+sentinel pairs (C++20 ranges support) in version 3.13.0. diff --git a/docs/mkdocs/docs/api/basic_json/from_bson.md b/docs/mkdocs/docs/api/basic_json/from_bson.md index 7f08ca0bd..eb06a7177 100644 --- a/docs/mkdocs/docs/api/basic_json/from_bson.md +++ b/docs/mkdocs/docs/api/basic_json/from_bson.md @@ -7,8 +7,8 @@ static basic_json from_bson(InputType&& i, const bool strict = true, const bool allow_exceptions = true); // (2) -template -static basic_json from_bson(IteratorType first, IteratorType last, +template +static basic_json from_bson(IteratorType first, SentinelType last, const bool strict = true, const bool allow_exceptions = true); ``` @@ -16,7 +16,7 @@ static basic_json from_bson(IteratorType first, IteratorType last, Deserializes a given input to a JSON value using the BSON (Binary JSON) serialization format. 1. Reads from a compatible input. -2. Reads from an iterator range. +2. Reads from an iterator range, or an iterator and a sentinel of a different type (C++20 ranges support). The exact mapping and its limitations are described on a [dedicated page](../../features/binary_formats/bson.md). @@ -35,6 +35,10 @@ The exact mapping and its limitations are described on a [dedicated page](../../ `IteratorType` : a compatible iterator type +`SentinelType` +: defaults to `IteratorType`; may be a different type comparable to `IteratorType` via `operator!=`, for instance a + custom sentinel type for C++20 ranges + ## Parameters `i` (in) @@ -44,7 +48,7 @@ The exact mapping and its limitations are described on a [dedicated page](../../ : iterator to the start of the input `last` (in) -: iterator to the end of the input +: iterator to the end of the input, or a sentinel value that compares equal to the end iterator with `operator!=` `strict` (in) : whether to expect the input to be consumed until EOF (`#!cpp true` by default) @@ -103,6 +107,7 @@ Linear in the size of the input. - Added in version 3.4.0. - Extended container support (1) to include types with lvalue-only ADL `begin`/`end` (matching `std::begin`/`std::end` semantics) in version 3.13.0. +- Extended overload (2) to accept heterogeneous iterator+sentinel pairs (C++20 ranges support) in version 3.13.0. !!! warning "Deprecation" diff --git a/docs/mkdocs/docs/api/basic_json/from_cbor.md b/docs/mkdocs/docs/api/basic_json/from_cbor.md index b736b8581..3792307bd 100644 --- a/docs/mkdocs/docs/api/basic_json/from_cbor.md +++ b/docs/mkdocs/docs/api/basic_json/from_cbor.md @@ -9,8 +9,8 @@ static basic_json from_cbor(InputType&& i, const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error); // (2) -template -static basic_json from_cbor(IteratorType first, IteratorType last, +template +static basic_json from_cbor(IteratorType first, SentinelType last, const bool strict = true, const bool allow_exceptions = true, const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error); @@ -19,7 +19,7 @@ static basic_json from_cbor(IteratorType first, IteratorType last, Deserializes a given input to a JSON value using the CBOR (Concise Binary Object Representation) serialization format. 1. Reads from a compatible input. -2. Reads from an iterator range. +2. Reads from an iterator range, or an iterator and a sentinel of a different type (C++20 ranges support). The exact mapping and its limitations are described on a [dedicated page](../../features/binary_formats/cbor.md). @@ -38,6 +38,10 @@ The exact mapping and its limitations are described on a [dedicated page](../../ `IteratorType` : a compatible iterator type +`SentinelType` +: defaults to `IteratorType`; may be a different type comparable to `IteratorType` via `operator!=`, for instance a + custom sentinel type for C++20 ranges + ## Parameters `i` (in) @@ -47,7 +51,7 @@ The exact mapping and its limitations are described on a [dedicated page](../../ : iterator to the start of the input `last` (in) -: iterator to the end of the input +: iterator to the end of the input, or a sentinel value that compares equal to the end iterator with `operator!=` `strict` (in) : whether to expect the input to be consumed until EOF (`#!cpp true` by default) @@ -113,6 +117,7 @@ Linear in the size of the input. - Added `allow_exceptions` parameter in version 3.2.0. - Added `tag_handler` parameter in version 3.9.0. - Extended container support (1) to include types with lvalue-only ADL `begin`/`end` (matching `std::begin`/`std::end` semantics) in version 3.13.0. +- Extended overload (2) to accept heterogeneous iterator+sentinel pairs (C++20 ranges support) in version 3.13.0. !!! warning "Deprecation" diff --git a/docs/mkdocs/docs/api/basic_json/from_msgpack.md b/docs/mkdocs/docs/api/basic_json/from_msgpack.md index 69f45605f..dd7719804 100644 --- a/docs/mkdocs/docs/api/basic_json/from_msgpack.md +++ b/docs/mkdocs/docs/api/basic_json/from_msgpack.md @@ -7,8 +7,8 @@ static basic_json from_msgpack(InputType&& i, const bool strict = true, const bool allow_exceptions = true); // (2) -template -static basic_json from_msgpack(IteratorType first, IteratorType last, +template +static basic_json from_msgpack(IteratorType first, SentinelType last, const bool strict = true, const bool allow_exceptions = true); ``` @@ -16,7 +16,7 @@ static basic_json from_msgpack(IteratorType first, IteratorType last, Deserializes a given input to a JSON value using the MessagePack serialization format. 1. Reads from a compatible input. -2. Reads from an iterator range. +2. Reads from an iterator range, or an iterator and a sentinel of a different type (C++20 ranges support). The exact mapping and its limitations are described on a [dedicated page](../../features/binary_formats/messagepack.md). @@ -35,6 +35,10 @@ The exact mapping and its limitations are described on a [dedicated page](../../ `IteratorType` : a compatible iterator type +`SentinelType` +: defaults to `IteratorType`; may be a different type comparable to `IteratorType` via `operator!=`, for instance a + custom sentinel type for C++20 ranges + ## Parameters `i` (in) @@ -44,7 +48,7 @@ The exact mapping and its limitations are described on a [dedicated page](../../ : iterator to the start of the input `last` (in) -: iterator to the end of the input +: iterator to the end of the input, or a sentinel value that compares equal to the end iterator with `operator!=` `strict` (in) : whether to expect the input to be consumed until EOF (`#!cpp true` by default) @@ -105,6 +109,7 @@ Linear in the size of the input. - Changed to consume input adapters, removed `start_index` parameter, and added `strict` parameter in version 3.0.0. - Added `allow_exceptions` parameter in version 3.2.0. - Extended container support (1) to include types with lvalue-only ADL `begin`/`end` (matching `std::begin`/`std::end` semantics) in version 3.13.0. +- Extended overload (2) to accept heterogeneous iterator+sentinel pairs (C++20 ranges support) in version 3.13.0. !!! warning "Deprecation" diff --git a/docs/mkdocs/docs/api/basic_json/from_ubjson.md b/docs/mkdocs/docs/api/basic_json/from_ubjson.md index 82eb2d4de..55c68c0ae 100644 --- a/docs/mkdocs/docs/api/basic_json/from_ubjson.md +++ b/docs/mkdocs/docs/api/basic_json/from_ubjson.md @@ -7,8 +7,8 @@ static basic_json from_ubjson(InputType&& i, const bool strict = true, const bool allow_exceptions = true); // (2) -template -static basic_json from_ubjson(IteratorType first, IteratorType last, +template +static basic_json from_ubjson(IteratorType first, SentinelType last, const bool strict = true, const bool allow_exceptions = true); ``` @@ -16,7 +16,7 @@ static basic_json from_ubjson(IteratorType first, IteratorType last, Deserializes a given input to a JSON value using the UBJSON (Universal Binary JSON) serialization format. 1. Reads from a compatible input. -2. Reads from an iterator range. +2. Reads from an iterator range, or an iterator and a sentinel of a different type (C++20 ranges support). The exact mapping and its limitations are described on a [dedicated page](../../features/binary_formats/ubjson.md). @@ -35,6 +35,10 @@ The exact mapping and its limitations are described on a [dedicated page](../../ `IteratorType` : a compatible iterator type +`SentinelType` +: defaults to `IteratorType`; may be a different type comparable to `IteratorType` via `operator!=`, for instance a + custom sentinel type for C++20 ranges + ## Parameters `i` (in) @@ -44,7 +48,7 @@ The exact mapping and its limitations are described on a [dedicated page](../../ : iterator to the start of the input `last` (in) -: iterator to the end of the input +: iterator to the end of the input, or a sentinel value that compares equal to the end iterator with `operator!=` `strict` (in) : whether to expect the input to be consumed until EOF (`#!cpp true` by default) @@ -104,6 +108,7 @@ Linear in the size of the input. - Added in version 3.1.0. - Added `allow_exceptions` parameter in version 3.2.0. - Extended container support (1) to include types with lvalue-only ADL `begin`/`end` (matching `std::begin`/`std::end` semantics) in version 3.13.0. +- Extended overload (2) to accept heterogeneous iterator+sentinel pairs (C++20 ranges support) in version 3.13.0. !!! warning "Deprecation" diff --git a/docs/mkdocs/docs/api/basic_json/parse.md b/docs/mkdocs/docs/api/basic_json/parse.md index 4d202e8a9..4565c8762 100644 --- a/docs/mkdocs/docs/api/basic_json/parse.md +++ b/docs/mkdocs/docs/api/basic_json/parse.md @@ -10,8 +10,8 @@ static basic_json parse(InputType&& i, const bool ignore_trailing_commas = false); // (2) -template -static basic_json parse(IteratorType first, IteratorType last, +template +static basic_json parse(IteratorType first, SentinelType last, const parser_callback_t cb = nullptr, const bool allow_exceptions = true, const bool ignore_comments = false, @@ -19,10 +19,11 @@ static basic_json parse(IteratorType first, IteratorType last, ``` 1. Deserialize from a compatible input. -2. Deserialize from a pair of character iterators +2. Deserialize from a pair of character iterators, or an iterator and a sentinel of a different type (C++20 ranges support) The `value_type` of the iterator must be an integral type with size of 1, 2, or 4 bytes, which will be interpreted - respectively as UTF-8, UTF-16, and UTF-32. + respectively as UTF-8, UTF-16, and UTF-32. If `SentinelType` differs from `IteratorType`, it must be comparable to + the iterator type with `operator!=`. ## Template parameters @@ -43,6 +44,12 @@ static basic_json parse(IteratorType first, IteratorType last, - a pair of `std::string::iterator` or `std::vector::iterator` - a pair of pointers such as `ptr` and `ptr + len` +`SentinelType` +: defaults to `IteratorType`; may be a different type comparable to `IteratorType` via `operator!=`, for instance. + + - a custom sentinel type for C++20 ranges + - `std::counted_iterator` with a different sentinel type + ## Parameters `i` (in) @@ -67,7 +74,7 @@ static basic_json parse(IteratorType first, IteratorType last, : iterator to the start of a character range `last` (in) -: iterator to the end of a character range +: iterator to the end of a character range, or a sentinel value that compares equal to the end iterator with `operator!=` ## Return value @@ -238,6 +245,7 @@ Invalid Unicode escapes and unpaired surrogates in the input are reported as - Changed [runtime assertion](../../features/assertions.md) in case of `FILE*` null pointers to exception in version 3.12.0. - Added `ignore_trailing_commas` in version 3.13.0. - Extended container support (1) to include types with lvalue-only ADL `begin`/`end` (matching `std::begin`/`std::end` semantics) in version 3.13.0. +- Extended overload (2) to accept heterogeneous iterator+sentinel pairs (C++20 ranges support) in version 3.13.0. !!! warning "Deprecation" diff --git a/docs/mkdocs/docs/api/basic_json/sax_parse.md b/docs/mkdocs/docs/api/basic_json/sax_parse.md index 81fa461a0..606ab9bbe 100644 --- a/docs/mkdocs/docs/api/basic_json/sax_parse.md +++ b/docs/mkdocs/docs/api/basic_json/sax_parse.md @@ -11,8 +11,8 @@ static bool sax_parse(InputType&& i, const bool ignore_trailing_commas = false); // (2) -template -static bool sax_parse(IteratorType first, IteratorType last, +template +static bool sax_parse(IteratorType first, SentinelType last, SAX* sax, input_format_t format = input_format_t::json, const bool strict = true, @@ -23,10 +23,11 @@ static bool sax_parse(IteratorType first, IteratorType last, Read from input and generate SAX events 1. Read from a compatible input. -2. Read from a pair of character iterators +2. Read from a pair of character iterators, or an iterator and a sentinel of a different type (C++20 ranges support) The value_type of the iterator must be an integral type with a size of 1, 2, or 4 bytes, which will be interpreted - respectively as UTF-8, UTF-16, and UTF-32. + respectively as UTF-8, UTF-16, and UTF-32. If `SentinelType` differs from `IteratorType`, it must be comparable to + the iterator type with `operator!=`. The SAX event lister must follow the interface of [`json_sax`](../json_sax/index.md). @@ -46,6 +47,9 @@ The SAX event lister must follow the interface of [`json_sax`](../json_sax/index : a compatible iterator type for overload (2); a pair of character iterators whose `value_type` is an integral type with a size of 1, 2, or 4 bytes (interpreted respectively as UTF-8, UTF-16, and UTF-32) +`SentinelType` +: defaults to `IteratorType`; may be a different type comparable to `IteratorType` via `operator!=`, for overload (2) + `SAX` : a class fulfilling the SAX event listener interface; see [`json_sax`](../json_sax/index.md) @@ -76,7 +80,7 @@ The SAX event lister must follow the interface of [`json_sax`](../json_sax/index : iterator to the start of a character range `last` (in) -: iterator to the end of a character range +: iterator to the end of a character range, or a sentinel value that compares equal to the end iterator with `operator!=` ## Return value @@ -128,6 +132,7 @@ A UTF-8 byte order mark is silently ignored. - Ignoring comments via `ignore_comments` added in version 3.9.0. - Added `ignore_trailing_commas` in version 3.13.0. - Extended container support (1) to include types with lvalue-only ADL `begin`/`end` (matching `std::begin`/`std::end` semantics) in version 3.13.0. +- Extended overload (2) to accept heterogeneous iterator+sentinel pairs (C++20 ranges support) in version 3.13.0. !!! warning "Deprecation" diff --git a/include/nlohmann/detail/input/input_adapters.hpp b/include/nlohmann/detail/input/input_adapters.hpp index 52d221b54..1ef8a6af7 100644 --- a/include/nlohmann/detail/input/input_adapters.hpp +++ b/include/nlohmann/detail/input/input_adapters.hpp @@ -155,7 +155,9 @@ class input_stream_adapter // General-purpose iterator-based adapter. It might not be as fast as // theoretically possible for some containers, but it is extremely versatile. -template +// SentinelType defaults to IteratorType for backward compatibility, but may +// be a different type (e.g., a C++20 sentinel or counted_iterator). +template class iterator_input_adapter { public: @@ -169,9 +171,10 @@ class iterator_input_adapter // in wide_string_input_adapter, which does not expose this). static constexpr bool supports_seek = std::is_same::iterator_category, std::random_access_iterator_tag>::value + && std::is_same::value && sizeof(char_type) == 1; - iterator_input_adapter(IteratorType first, IteratorType last) + iterator_input_adapter(IteratorType first, SentinelType last) : begin(first), current(std::move(first)), end(std::move(last)) {} @@ -216,12 +219,14 @@ class iterator_input_adapter private: // whether IteratorType refers to a contiguous range and therefore supports // a std::memcpy fast path (pointers always do; in C++20 we can also detect - // library iterators such as those of std::vector and std::string) + // library iterators such as those of std::vector and std::string). + // The fast path also requires SentinelType == IteratorType so std::distance works. static constexpr bool iterator_is_contiguous = + std::is_same::value && ( #if defined(__cpp_lib_concepts) && defined(JSON_HAS_CPP_20) - std::contiguous_iterator || + std::contiguous_iterator || #endif - std::is_pointer::value; + std::is_pointer::value); // contiguous fast path: bulk copy the remaining range with std::memcpy template @@ -267,7 +272,7 @@ class iterator_input_adapter IteratorType begin; IteratorType current; - IteratorType end; + SentinelType end; template friend struct wide_string_input_helper; @@ -453,19 +458,54 @@ class wide_string_input_adapter std::size_t utf8_bytes_filled = 0; }; -template +template struct iterator_input_adapter_factory { using iterator_type = IteratorType; + using sentinel_type = SentinelType; using char_type = typename std::iterator_traits::value_type; - using adapter_type = iterator_input_adapter; + using adapter_type = iterator_input_adapter; - static adapter_type create(IteratorType first, IteratorType last) + static adapter_type create(IteratorType first, SentinelType last) { return adapter_type(std::move(first), std::move(last)); } }; +// Detection: whether IteratorType and SentinelType can be compared with != +template +struct can_compare_ne_impl : std::false_type {}; + +template +struct can_compare_ne_impl < IteratorType, SentinelType, + void_t < decltype(std::declval() != std::declval()) >> + : std::true_type {}; + +// Workaround for reversed operator order +template +struct can_compare_ne_reversed : std::false_type {}; + +template +struct can_compare_ne_reversed < IteratorType, SentinelType, + void_t < decltype(std::declval() != std::declval()) >> + : std::true_type {}; + +template +struct can_compare_ne_either_order : std::integral_constant < bool, + can_compare_ne_impl::value || + can_compare_ne_reversed::value > {}; + +// std::nullptr_t is excluded explicitly: a literal `nullptr` passed as a +// trailing default argument (e.g. parse(s, nullptr, ...)) must never be +// mistaken for a sentinel, and some compilers (e.g. GCC 4.8) unreliably +// SFINAE the `operator!=` detection above for std::nullptr_t against +// container/string types, which would otherwise make such calls ambiguous +// with the compatible-input overload. +template +struct can_compare_ne : std::integral_constant < bool, + !std::is_same::value && + can_compare_ne_either_order::value > {}; + template struct is_iterator_of_multibyte { @@ -476,25 +516,31 @@ struct is_iterator_of_multibyte }; }; -template -struct iterator_input_adapter_factory::value>> +template +struct iterator_input_adapter_factory::value>> { using iterator_type = IteratorType; + using sentinel_type = SentinelType; using char_type = typename std::iterator_traits::value_type; - using base_adapter_type = iterator_input_adapter; + using base_adapter_type = iterator_input_adapter; using adapter_type = wide_string_input_adapter; - static adapter_type create(IteratorType first, IteratorType last) + static adapter_type create(IteratorType first, SentinelType last) { return adapter_type(base_adapter_type(std::move(first), std::move(last))); } }; -// General purpose iterator-based input -template -typename iterator_input_adapter_factory::adapter_type input_adapter(IteratorType first, IteratorType last) +// 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 +// be compared with !=. +template < typename IteratorType, typename SentinelType = IteratorType, + typename = typename std::enable_if < + can_compare_ne::value >::type > +typename iterator_input_adapter_factory::adapter_type input_adapter(IteratorType first, SentinelType last) { - using factory_type = iterator_input_adapter_factory; + using factory_type = iterator_input_adapter_factory; return factory_type::create(first, last); } diff --git a/include/nlohmann/json.hpp b/include/nlohmann/json.hpp index 3d9fe8f5e..a460bb29f 100644 --- a/include/nlohmann/json.hpp +++ b/include/nlohmann/json.hpp @@ -4083,12 +4083,13 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec return result; } - /// @brief deserialize from a pair of character iterators + /// @brief deserialize from a pair of character iterators (or an iterator+sentinel pair, C++20 ranges support) /// @sa https://json.nlohmann.me/api/basic_json/parse/ - template + template::value, int> = 0> JSON_HEDLEY_WARN_UNUSED_RESULT static basic_json parse(IteratorType first, - IteratorType last, + SentinelType last, parser_callback_t cb = nullptr, const bool allow_exceptions = true, const bool ignore_comments = false, @@ -4122,10 +4123,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec return parser(detail::input_adapter(std::forward(i)), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true); } - /// @brief check if the input is valid JSON + /// @brief check if the input is valid JSON (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @sa https://json.nlohmann.me/api/basic_json/accept/ - template - static bool accept(IteratorType first, IteratorType last, + template::value, int> = 0> + static bool accept(IteratorType first, SentinelType last, const bool ignore_comments = false, const bool ignore_trailing_commas = false) { @@ -4157,11 +4159,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec : detail::binary_reader(std::move(ia), format).sax_parse(format, sax, strict); } - /// @brief generate SAX events + /// @brief generate SAX events (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @sa https://json.nlohmann.me/api/basic_json/sax_parse/ - template + template::value, int> = 0> JSON_HEDLEY_NON_NULL(3) - static bool sax_parse(IteratorType first, IteratorType last, SAX* sax, + static bool sax_parse(IteratorType first, SentinelType last, SAX* sax, input_format_t format = input_format_t::json, const bool strict = true, const bool ignore_comments = false, @@ -4461,11 +4464,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec return res ? result : basic_json(value_t::discarded); } - /// @brief create a JSON value from an input in CBOR format + /// @brief create a JSON value from an input in CBOR format (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @sa https://json.nlohmann.me/api/basic_json/from_cbor/ - template + template::value, int> = 0> JSON_HEDLEY_WARN_UNUSED_RESULT - static basic_json from_cbor(IteratorType first, IteratorType last, + static basic_json from_cbor(IteratorType first, SentinelType last, const bool strict = true, const bool allow_exceptions = true, const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error) @@ -4518,11 +4522,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec return res ? result : basic_json(value_t::discarded); } - /// @brief create a JSON value from an input in MessagePack format + /// @brief create a JSON value from an input in MessagePack format (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @sa https://json.nlohmann.me/api/basic_json/from_msgpack/ - template + template::value, int> = 0> JSON_HEDLEY_WARN_UNUSED_RESULT - static basic_json from_msgpack(IteratorType first, IteratorType last, + static basic_json from_msgpack(IteratorType first, SentinelType last, const bool strict = true, const bool allow_exceptions = true) { @@ -4572,11 +4577,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec return res ? result : basic_json(value_t::discarded); } - /// @brief create a JSON value from an input in UBJSON format + /// @brief create a JSON value from an input in UBJSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @sa https://json.nlohmann.me/api/basic_json/from_ubjson/ - template + template::value, int> = 0> JSON_HEDLEY_WARN_UNUSED_RESULT - static basic_json from_ubjson(IteratorType first, IteratorType last, + static basic_json from_ubjson(IteratorType first, SentinelType last, const bool strict = true, const bool allow_exceptions = true) { @@ -4626,11 +4632,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec return res ? result : basic_json(value_t::discarded); } - /// @brief create a JSON value from an input in BJData format + /// @brief create a JSON value from an input in BJData format (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @sa https://json.nlohmann.me/api/basic_json/from_bjdata/ - template + template::value, int> = 0> JSON_HEDLEY_WARN_UNUSED_RESULT - static basic_json from_bjdata(IteratorType first, IteratorType last, + static basic_json from_bjdata(IteratorType first, SentinelType last, const bool strict = true, const bool allow_exceptions = true) { @@ -4656,11 +4663,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec return res ? result : basic_json(value_t::discarded); } - /// @brief create a JSON value from an input in BSON format + /// @brief create a JSON value from an input in BSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @sa https://json.nlohmann.me/api/basic_json/from_bson/ - template + template::value, int> = 0> JSON_HEDLEY_WARN_UNUSED_RESULT - static basic_json from_bson(IteratorType first, IteratorType last, + static basic_json from_bson(IteratorType first, SentinelType last, const bool strict = true, const bool allow_exceptions = true) { diff --git a/single_include/nlohmann/json.hpp b/single_include/nlohmann/json.hpp index 6952210c1..99fceb63b 100644 --- a/single_include/nlohmann/json.hpp +++ b/single_include/nlohmann/json.hpp @@ -7142,7 +7142,9 @@ class input_stream_adapter // General-purpose iterator-based adapter. It might not be as fast as // theoretically possible for some containers, but it is extremely versatile. -template +// SentinelType defaults to IteratorType for backward compatibility, but may +// be a different type (e.g., a C++20 sentinel or counted_iterator). +template class iterator_input_adapter { public: @@ -7156,9 +7158,10 @@ class iterator_input_adapter // in wide_string_input_adapter, which does not expose this). static constexpr bool supports_seek = std::is_same::iterator_category, std::random_access_iterator_tag>::value + && std::is_same::value && sizeof(char_type) == 1; - iterator_input_adapter(IteratorType first, IteratorType last) + iterator_input_adapter(IteratorType first, SentinelType last) : begin(first), current(std::move(first)), end(std::move(last)) {} @@ -7203,12 +7206,14 @@ class iterator_input_adapter private: // whether IteratorType refers to a contiguous range and therefore supports // a std::memcpy fast path (pointers always do; in C++20 we can also detect - // library iterators such as those of std::vector and std::string) + // library iterators such as those of std::vector and std::string). + // The fast path also requires SentinelType == IteratorType so std::distance works. static constexpr bool iterator_is_contiguous = + std::is_same::value && ( #if defined(__cpp_lib_concepts) && defined(JSON_HAS_CPP_20) - std::contiguous_iterator || + std::contiguous_iterator || #endif - std::is_pointer::value; + std::is_pointer::value); // contiguous fast path: bulk copy the remaining range with std::memcpy template @@ -7254,7 +7259,7 @@ class iterator_input_adapter IteratorType begin; IteratorType current; - IteratorType end; + SentinelType end; template friend struct wide_string_input_helper; @@ -7440,19 +7445,54 @@ class wide_string_input_adapter std::size_t utf8_bytes_filled = 0; }; -template +template struct iterator_input_adapter_factory { using iterator_type = IteratorType; + using sentinel_type = SentinelType; using char_type = typename std::iterator_traits::value_type; - using adapter_type = iterator_input_adapter; + using adapter_type = iterator_input_adapter; - static adapter_type create(IteratorType first, IteratorType last) + static adapter_type create(IteratorType first, SentinelType last) { return adapter_type(std::move(first), std::move(last)); } }; +// Detection: whether IteratorType and SentinelType can be compared with != +template +struct can_compare_ne_impl : std::false_type {}; + +template +struct can_compare_ne_impl < IteratorType, SentinelType, + void_t < decltype(std::declval() != std::declval()) >> + : std::true_type {}; + +// Workaround for reversed operator order +template +struct can_compare_ne_reversed : std::false_type {}; + +template +struct can_compare_ne_reversed < IteratorType, SentinelType, + void_t < decltype(std::declval() != std::declval()) >> + : std::true_type {}; + +template +struct can_compare_ne_either_order : std::integral_constant < bool, + can_compare_ne_impl::value || + can_compare_ne_reversed::value > {}; + +// std::nullptr_t is excluded explicitly: a literal `nullptr` passed as a +// trailing default argument (e.g. parse(s, nullptr, ...)) must never be +// mistaken for a sentinel, and some compilers (e.g. GCC 4.8) unreliably +// SFINAE the `operator!=` detection above for std::nullptr_t against +// container/string types, which would otherwise make such calls ambiguous +// with the compatible-input overload. +template +struct can_compare_ne : std::integral_constant < bool, + !std::is_same::value && + can_compare_ne_either_order::value > {}; + template struct is_iterator_of_multibyte { @@ -7463,25 +7503,31 @@ struct is_iterator_of_multibyte }; }; -template -struct iterator_input_adapter_factory::value>> +template +struct iterator_input_adapter_factory::value>> { using iterator_type = IteratorType; + using sentinel_type = SentinelType; using char_type = typename std::iterator_traits::value_type; - using base_adapter_type = iterator_input_adapter; + using base_adapter_type = iterator_input_adapter; using adapter_type = wide_string_input_adapter; - static adapter_type create(IteratorType first, IteratorType last) + static adapter_type create(IteratorType first, SentinelType last) { return adapter_type(base_adapter_type(std::move(first), std::move(last))); } }; -// General purpose iterator-based input -template -typename iterator_input_adapter_factory::adapter_type input_adapter(IteratorType first, IteratorType last) +// 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 +// be compared with !=. +template < typename IteratorType, typename SentinelType = IteratorType, + typename = typename std::enable_if < + can_compare_ne::value >::type > +typename iterator_input_adapter_factory::adapter_type input_adapter(IteratorType first, SentinelType last) { - using factory_type = iterator_input_adapter_factory; + using factory_type = iterator_input_adapter_factory; return factory_type::create(first, last); } @@ -25084,12 +25130,13 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec return result; } - /// @brief deserialize from a pair of character iterators + /// @brief deserialize from a pair of character iterators (or an iterator+sentinel pair, C++20 ranges support) /// @sa https://json.nlohmann.me/api/basic_json/parse/ - template + template::value, int> = 0> JSON_HEDLEY_WARN_UNUSED_RESULT static basic_json parse(IteratorType first, - IteratorType last, + SentinelType last, parser_callback_t cb = nullptr, const bool allow_exceptions = true, const bool ignore_comments = false, @@ -25123,10 +25170,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec return parser(detail::input_adapter(std::forward(i)), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true); } - /// @brief check if the input is valid JSON + /// @brief check if the input is valid JSON (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @sa https://json.nlohmann.me/api/basic_json/accept/ - template - static bool accept(IteratorType first, IteratorType last, + template::value, int> = 0> + static bool accept(IteratorType first, SentinelType last, const bool ignore_comments = false, const bool ignore_trailing_commas = false) { @@ -25158,11 +25206,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec : detail::binary_reader(std::move(ia), format).sax_parse(format, sax, strict); } - /// @brief generate SAX events + /// @brief generate SAX events (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @sa https://json.nlohmann.me/api/basic_json/sax_parse/ - template + template::value, int> = 0> JSON_HEDLEY_NON_NULL(3) - static bool sax_parse(IteratorType first, IteratorType last, SAX* sax, + static bool sax_parse(IteratorType first, SentinelType last, SAX* sax, input_format_t format = input_format_t::json, const bool strict = true, const bool ignore_comments = false, @@ -25462,11 +25511,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec return res ? result : basic_json(value_t::discarded); } - /// @brief create a JSON value from an input in CBOR format + /// @brief create a JSON value from an input in CBOR format (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @sa https://json.nlohmann.me/api/basic_json/from_cbor/ - template + template::value, int> = 0> JSON_HEDLEY_WARN_UNUSED_RESULT - static basic_json from_cbor(IteratorType first, IteratorType last, + static basic_json from_cbor(IteratorType first, SentinelType last, const bool strict = true, const bool allow_exceptions = true, const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error) @@ -25519,11 +25569,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec return res ? result : basic_json(value_t::discarded); } - /// @brief create a JSON value from an input in MessagePack format + /// @brief create a JSON value from an input in MessagePack format (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @sa https://json.nlohmann.me/api/basic_json/from_msgpack/ - template + template::value, int> = 0> JSON_HEDLEY_WARN_UNUSED_RESULT - static basic_json from_msgpack(IteratorType first, IteratorType last, + static basic_json from_msgpack(IteratorType first, SentinelType last, const bool strict = true, const bool allow_exceptions = true) { @@ -25573,11 +25624,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec return res ? result : basic_json(value_t::discarded); } - /// @brief create a JSON value from an input in UBJSON format + /// @brief create a JSON value from an input in UBJSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @sa https://json.nlohmann.me/api/basic_json/from_ubjson/ - template + template::value, int> = 0> JSON_HEDLEY_WARN_UNUSED_RESULT - static basic_json from_ubjson(IteratorType first, IteratorType last, + static basic_json from_ubjson(IteratorType first, SentinelType last, const bool strict = true, const bool allow_exceptions = true) { @@ -25627,11 +25679,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec return res ? result : basic_json(value_t::discarded); } - /// @brief create a JSON value from an input in BJData format + /// @brief create a JSON value from an input in BJData format (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @sa https://json.nlohmann.me/api/basic_json/from_bjdata/ - template + template::value, int> = 0> JSON_HEDLEY_WARN_UNUSED_RESULT - static basic_json from_bjdata(IteratorType first, IteratorType last, + static basic_json from_bjdata(IteratorType first, SentinelType last, const bool strict = true, const bool allow_exceptions = true) { @@ -25657,11 +25710,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec return res ? result : basic_json(value_t::discarded); } - /// @brief create a JSON value from an input in BSON format + /// @brief create a JSON value from an input in BSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @sa https://json.nlohmann.me/api/basic_json/from_bson/ - template + template::value, int> = 0> JSON_HEDLEY_WARN_UNUSED_RESULT - static basic_json from_bson(IteratorType first, IteratorType last, + static basic_json from_bson(IteratorType first, SentinelType last, const bool strict = true, const bool allow_exceptions = true) { diff --git a/tests/src/test_utils.hpp b/tests/src/test_utils.hpp index 37afa21e8..baa802f71 100644 --- a/tests/src/test_utils.hpp +++ b/tests/src/test_utils.hpp @@ -30,4 +30,17 @@ inline std::vector read_binary_file(const std::string& filename) return byte_vector; } +// sentinel for istreambuf_iterator; compares != true until EOF is reached +// lets tests read a file directly via the new iterator+sentinel overloads +// instead of buffering the whole file into a vector first. +// Only the iterator-first direction (it != sentinel) is ever evaluated by +// the library's parse loop, so no reversed-order overload is needed. +struct istreambuf_sentinel +{ + friend bool operator!=(const std::istreambuf_iterator& it, const istreambuf_sentinel& /*unused*/) noexcept + { + return it != std::istreambuf_iterator(); + } +}; + } // namespace utils diff --git a/tests/src/unit-bjdata.cpp b/tests/src/unit-bjdata.cpp index c8459315d..5af4afac1 100644 --- a/tests/src/unit-bjdata.cpp +++ b/tests/src/unit-bjdata.cpp @@ -3699,6 +3699,15 @@ TEST_CASE("Universal Binary JSON Specification Examples 1") } } +TEST_CASE("Parse BJData directly from a file using iterator and sentinel") +{ + std::string const filename = TEST_DATA_DIRECTORY "/json_testsuite/sample.json.bjdata"; + std::ifstream file(filename, std::ios::binary); + const std::istreambuf_iterator first(file); + const json parsed = json::from_bjdata(first, utils::istreambuf_sentinel{}); + CHECK((parsed.is_object() || parsed.is_array())); +} + #if !defined(JSON_NOEXCEPTION) TEST_CASE("all BJData first bytes") { diff --git a/tests/src/unit-bson.cpp b/tests/src/unit-bson.cpp index eed70352e..28837d75e 100644 --- a/tests/src/unit-bson.cpp +++ b/tests/src/unit-bson.cpp @@ -1208,6 +1208,19 @@ TEST_CASE("BSON numerical data") } } +TEST_CASE("Parse BSON directly from a file using iterator and sentinel") +{ + std::string const filename = TEST_DATA_DIRECTORY "/json.org/1.json"; + + std::ifstream f_json(filename); + const json expected = json::parse(f_json); + + std::ifstream file(filename + ".bson", std::ios::binary); + const std::istreambuf_iterator first(file); + const json parsed = json::from_bson(first, utils::istreambuf_sentinel{}); + CHECK(parsed == expected); +} + TEST_CASE("BSON roundtrips" * doctest::skip()) { SECTION("reference files") diff --git a/tests/src/unit-cbor.cpp b/tests/src/unit-cbor.cpp index 52c808027..af7364299 100644 --- a/tests/src/unit-cbor.cpp +++ b/tests/src/unit-cbor.cpp @@ -1921,6 +1921,15 @@ TEST_CASE("single CBOR roundtrip") } } +TEST_CASE("Parse CBOR directly from a file using iterator and sentinel") +{ + std::string const filename = TEST_DATA_DIRECTORY "/json_testsuite/sample.json.cbor"; + std::ifstream file(filename, std::ios::binary); + const std::istreambuf_iterator first(file); + const json parsed = json::from_cbor(first, utils::istreambuf_sentinel{}); + CHECK((parsed.is_object() || parsed.is_array())); +} + #if !defined(JSON_NOEXCEPTION) TEST_CASE("CBOR regressions") { diff --git a/tests/src/unit-msgpack.cpp b/tests/src/unit-msgpack.cpp index 02fb7a2e4..4358cd464 100644 --- a/tests/src/unit-msgpack.cpp +++ b/tests/src/unit-msgpack.cpp @@ -1641,6 +1641,15 @@ TEST_CASE("single MessagePack roundtrip") } } +TEST_CASE("Parse MessagePack directly from a file using iterator and sentinel") +{ + std::string const filename = TEST_DATA_DIRECTORY "/json_testsuite/sample.json.msgpack"; + std::ifstream file(filename, std::ios::binary); + const std::istreambuf_iterator first(file); + const json parsed = json::from_msgpack(first, utils::istreambuf_sentinel{}); + CHECK((parsed.is_object() || parsed.is_array())); +} + TEST_CASE("MessagePack roundtrips" * doctest::skip()) { SECTION("input from msgpack-python") diff --git a/tests/src/unit-ubjson.cpp b/tests/src/unit-ubjson.cpp index 99d07d966..8242a0cc8 100644 --- a/tests/src/unit-ubjson.cpp +++ b/tests/src/unit-ubjson.cpp @@ -2393,6 +2393,15 @@ TEST_CASE("Universal Binary JSON Specification Examples 1") } } +TEST_CASE("Parse UBJSON directly from a file using iterator and sentinel") +{ + std::string const filename = TEST_DATA_DIRECTORY "/json_testsuite/sample.json.ubjson"; + std::ifstream file(filename, std::ios::binary); + const std::istreambuf_iterator first(file); + const json parsed = json::from_ubjson(first, utils::istreambuf_sentinel{}); + CHECK((parsed.is_object() || parsed.is_array())); +} + #if !defined(JSON_NOEXCEPTION) TEST_CASE("all UBJSON first bytes") { diff --git a/tests/src/unit-user_defined_input.cpp b/tests/src/unit-user_defined_input.cpp index 1a9b6394b..cb93439e5 100644 --- a/tests/src/unit-user_defined_input.cpp +++ b/tests/src/unit-user_defined_input.cpp @@ -168,4 +168,37 @@ TEST_CASE("Custom iterator") CHECK(as_json.at(3) == 4); } +// Custom sentinel type for testing heterogeneous iterator+sentinel support +struct CustomSentinel +{ + const char* end_ptr; + + // only the iterator-first direction (it != sentinel) is ever evaluated by + // the library's parse loop; a reversed-order overload would go unused and + // trip -Wunneeded-internal-declaration under -Weverything + friend bool operator!=(const char* it, const CustomSentinel& sentinel) + { + return it != sentinel.end_ptr; + } +}; + +TEST_CASE("Parse with heterogeneous iterator and sentinel types") +{ + const std::string json_str = R"({"key":"value"})"; + const char* end_ptr = json_str.data() + json_str.size(); + + // Parse using pointer and sentinel (different types) + json j = json::parse(json_str.data(), CustomSentinel{end_ptr}); + CHECK(j["key"] == "value"); + + // Accept using pointer and sentinel + CHECK(json::accept(json_str.data(), CustomSentinel{end_ptr})); + + // Test that the same-type case still works + std::string raw_data = R"([1,2,3])"; + std::list data(raw_data.begin(), raw_data.end()); + json j2 = json::parse(data.begin(), data.end()); + CHECK(j2.at(0) == 1); +} + } // namespace