Merge pull request #46 from OpenVicProject/fix/char-detection

Add runtime encoding detection and conversion 

12 files changed, 108 insertions, 259 deletions

diff --git a/include/openvic-dataloader/detail/utility/Concepts.hpp b/include/openvic-dataloader/detail/Concepts.hpp
index 0ba91cc..79e04a9 100644
--- a/include/openvic-dataloader/detail/utility/Concepts.hpp
+++ b/include/openvic-dataloader/detail/Concepts.hpp
@@ -6,7 +6,6 @@
 #include <utility>
 
 namespace ovdl {
-	struct NodeLocation;
 	struct File;
 	namespace detail {
 		enum class buffer_error : std::uint8_t;
@@ -15,7 +14,7 @@ namespace ovdl {
 
 namespace ovdl::detail {
 	template<typename T, typename... Ts>
-	concept any_of = (std::same_as<T, Ts> || ...);
+	concept any_of = std::disjunction_v<std::is_same<T, Ts>...>;
 
 	template<typename T>
 	concept HasCstr =
@@ -42,4 +41,9 @@ namespace ovdl::detail {
 		{ T::eof() } -> std::same_as<typename T::int_type>;
 		{ T::to_int_type(typename T::char_type {}) } -> std::same_as<typename T::int_type>;
 	};
+
+	template<typename T, typename R, typename... Args>
+	concept Invocable_R = std::invocable<T, Args...> && requires(Args&&... args) {
+		{ invoke(forward<Args>(args)...) } -> std::convertible_to<R>;
+	};
 }
\ No newline at end of file
diff --git a/include/openvic-dataloader/detail/utility/Constexpr.hpp b/include/openvic-dataloader/detail/Constexpr.hpp
index 49479c5..49479c5 100644
--- a/include/openvic-dataloader/detail/utility/Constexpr.hpp
+++ b/include/openvic-dataloader/detail/Constexpr.hpp
diff --git a/include/openvic-dataloader/detail/Encoding.hpp b/include/openvic-dataloader/detail/Encoding.hpp
new file mode 100644
index 0000000..12a0524
--- /dev/null
+++ b/include/openvic-dataloader/detail/Encoding.hpp
@@ -0,0 +1,13 @@
+#pragma once
+
+#include <cstdint>
+
+namespace ovdl::detail {
+	enum class Encoding : std::int8_t {
+		Unknown,
+		Ascii,
+		Utf8,
+		Windows1251,
+		Windows1252
+	};
+}
\ No newline at end of file
diff --git a/include/openvic-dataloader/detail/utility/ErrorRange.hpp b/include/openvic-dataloader/detail/ErrorRange.hpp
index 7d5ca13..7d5ca13 100644
--- a/include/openvic-dataloader/detail/utility/ErrorRange.hpp
+++ b/include/openvic-dataloader/detail/ErrorRange.hpp
diff --git a/include/openvic-dataloader/detail/LexyFwdDeclaration.hpp b/include/openvic-dataloader/detail/LexyFwdDeclaration.hpp
deleted file mode 100644
index 554c88d..0000000
--- a/include/openvic-dataloader/detail/LexyFwdDeclaration.hpp
+++ /dev/null
@@ -1,8 +0,0 @@
-#pragma once
-
-namespace lexy {
-	struct default_encoding;
-
-	template<typename Encoding, typename MemoryResource>
-	struct buffer;
-}
\ No newline at end of file
diff --git a/include/openvic-dataloader/detail/LexyReportError.hpp b/include/openvic-dataloader/detail/LexyReportError.hpp
deleted file mode 100644
index 3c32bd1..0000000
--- a/include/openvic-dataloader/detail/LexyReportError.hpp
+++ /dev/null
@@ -1,107 +0,0 @@
-#pragma once
-
-#include <cstddef>
-#include <sstream>
-#include <utility>
-#include <vector>
-
-#include <openvic-dataloader/ParseData.hpp>
-#include <openvic-dataloader/ParseError.hpp>
-
-#include <lexy/input_location.hpp>
-#include <lexy/visualize.hpp>
-
-#include "openvic-dataloader/detail/utility/Concepts.hpp"
-
-#include <lexy_ext/report_error.hpp>
-
-namespace ovdl::detail {
-	template<typename OutputIterator>
-	struct _ReportError {
-		OutputIterator _iter;
-		lexy::visualization_options _opts;
-		const char* _path;
-
-		struct _sink {
-			OutputIterator _iter;
-			lexy::visualization_options _opts;
-			const char* _path;
-			std::size_t _count;
-			std::vector<ParseError> _errors;
-
-			using return_type = std::vector<ParseError>;
-
-			template<typename Input, typename Reader, typename Tag>
-			void operator()(const lexy::error_context<Input>& context, const lexy::error<Reader, Tag>& error) {
-				_iter = lexy_ext::_detail::write_error(_iter, context, error, _opts, _path);
-				++_count;
-
-				// Convert the context location and error location into line/column information.
-				auto context_location = lexy::get_input_location(context.input(), context.position());
-				auto location = lexy::get_input_location(context.input(), error.position(), context_location.anchor());
-
-				std::basic_stringstream<typename Reader::encoding::char_type> message;
-
-				// Write the main annotation.
-				if constexpr (std::is_same_v<Tag, lexy::expected_literal>) {
-					auto string = lexy::_detail::make_literal_lexeme<typename Reader::encoding>(error.string(), error.length());
-
-					message << "expected '" << string.data() << '\'';
-				} else if constexpr (std::is_same_v<Tag, lexy::expected_keyword>) {
-					auto string = lexy::_detail::make_literal_lexeme<typename Reader::encoding>(error.string(), error.length());
-
-					message << "expected keyword '" << string.data() << '\'';
-				} else if constexpr (std::is_same_v<Tag, lexy::expected_char_class>) {
-					message << "expected " << error.name();
-				} else {
-					message << error.message();
-				}
-
-				_errors.push_back(
-					ParseError {
-						ParseError::Type::Fatal, // TODO: distinguish recoverable errors from fatal errors
-						std::move(message.str()),
-						0, // TODO: implement proper error codes
-						ParseData {
-							context.production(),
-							context_location.line_nr(),
-							context_location.column_nr(),
-						},
-						location.line_nr(),
-						location.column_nr(),
-					});
-			}
-
-			return_type finish() && {
-				if (_count != 0)
-					*_iter++ = '\n';
-				return _errors;
-			}
-		};
-		constexpr auto sink() const {
-			return _sink { _iter, _opts, _path, 0 };
-		}
-
-		/// Specifies a path that will be printed alongside the diagnostic.
-		constexpr _ReportError path(const char* path) const {
-			return { _iter, _opts, path };
-		}
-
-		constexpr _ReportError path(const detail::HasCstr auto& path_object) const {
-			return path(path_object.c_str());
-		}
-
-		/// Specifies an output iterator where the errors are written to.
-		template<typename OI>
-		constexpr _ReportError<OI> to(OI out) const {
-			return { out, _opts, _path };
-		}
-
-		/// Overrides visualization options.
-		constexpr _ReportError opts(lexy::visualization_options opts) const {
-			return { _iter, opts, _path };
-		}
-	};
-
-	constexpr auto ReporError = _ReportError<lexy::stderr_output_iterator> {};
-}
\ No newline at end of file
diff --git a/include/openvic-dataloader/detail/OStreamOutputIterator.hpp b/include/openvic-dataloader/detail/OStreamOutputIterator.hpp
index 8f120c7..81f6c89 100644
--- a/include/openvic-dataloader/detail/OStreamOutputIterator.hpp
+++ b/include/openvic-dataloader/detail/OStreamOutputIterator.hpp
@@ -1,6 +1,5 @@
 #pragma once
 
-#include <memory>
 #include <ostream>
 
 namespace ovdl::detail {
diff --git a/include/openvic-dataloader/detail/Utility.hpp b/include/openvic-dataloader/detail/Utility.hpp
new file mode 100644
index 0000000..8d9e159
--- /dev/null
+++ b/include/openvic-dataloader/detail/Utility.hpp
@@ -0,0 +1,89 @@
+#pragma once
+
+#include <cstdint>
+#include <tuple>
+#include <type_traits>
+#include <variant>
+
+#include <openvic-dataloader/detail/Concepts.hpp>
+
+namespace ovdl::detail {
+	[[noreturn]] inline void unreachable() {
+		// Uses compiler specific extensions if possible.
+		// Even if no extension is used, undefined behavior is still raised by
+		// an empty function body and the noreturn attribute.
+#ifdef __GNUC__ // GCC, Clang, ICC
+		__builtin_unreachable();
+#elif defined(_MSC_VER) // MSVC
+		__assume(false);
+#endif
+	}
+
+	template<typename EnumT>
+		requires std::is_enum_v<EnumT>
+	constexpr std::underlying_type_t<EnumT> to_underlying(EnumT e) {
+		return static_cast<std::underlying_type_t<EnumT>>(e);
+	}
+
+	template<typename EnumT>
+		requires std::is_enum_v<EnumT>
+	constexpr EnumT from_underlying(std::underlying_type_t<EnumT> ut) {
+		return static_cast<EnumT>(ut);
+	}
+
+	template<typename Type, typename... Types>
+	struct TypeRegister {
+		using tuple_type = std::tuple<Type, Types...>;
+		using variant_type = std::variant<Type, Types...>;
+
+		template<typename QueriedType>
+		struct _id_getter {
+			static constexpr std::uint32_t type_id() {
+				static_assert(any_of<QueriedType, Type, Types...>, "Cannot query an non-registered type");
+
+				if constexpr (std::is_same_v<Type, QueriedType>) return 0;
+				else return 1 + TypeRegister<Types...>::template _id_getter<QueriedType>::type_id();
+			};
+		};
+
+		template<typename QueriedType>
+		static constexpr std::uint32_t type_id() {
+
+			return _id_getter<QueriedType>::type_id();
+		}
+
+		template<std::uint32_t Id>
+		using type_by_id = std::tuple_element_t<Id, tuple_type>;
+	};
+
+	template<typename...>
+	struct type_concat;
+
+	template<typename... Ts, template<typename...> typename TT, typename... TTs>
+	struct type_concat<TT<TTs...>, Ts...> {
+		using type = TT<TTs..., Ts...>;
+	};
+
+	template<typename... Ts>
+	using type_concat_t = type_concat<Ts...>::type;
+
+	template<typename...>
+	struct type_prepend;
+
+	template<typename... Ts, template<typename...> typename TT, typename... TTs>
+	struct type_prepend<TT<TTs...>, Ts...> {
+		using type = TT<Ts..., TTs...>;
+	};
+
+	template<typename... Ts>
+	using type_prepend_t = type_prepend<Ts...>::type;
+
+	template<typename Type, template<typename...> typename Template>
+	struct is_instance_of : std::false_type {};
+
+	template<typename... Ts, template<typename...> typename Template>
+	struct is_instance_of<Template<Ts...>, Template> : std::true_type {};
+
+	template<typename Type, template<typename...> typename Template>
+	static constexpr auto is_instance_of_v = is_instance_of<Type, Template>::value;
+}
\ No newline at end of file
diff --git a/include/openvic-dataloader/detail/utility/PointerHash.hpp b/include/openvic-dataloader/detail/utility/PointerHash.hpp
deleted file mode 100644
index c0d28bc..0000000
--- a/include/openvic-dataloader/detail/utility/PointerHash.hpp
+++ /dev/null
@@ -1,23 +0,0 @@
-#pragma once
-
-#include <cstdint>
-
-namespace ovdl::detail {
-	/* hash any pointer */
-	template<typename T>
-	struct PointerHash {
-		using type = T;
-		using ptr_type = T*;
-		using const_type = const T;
-		using const_ptr_type = const T*;
-		using const_ptr_const_type = const const_ptr_type;
-		constexpr std::size_t operator()(const_ptr_const_type pointer) const {
-			auto addr = reinterpret_cast<uintptr_t>(pointer);
-#if SIZE_MAX < UINTPTR_MAX
-			/* size_t is not large enough to hold the pointer’s memory address */
-			addr %= SIZE_MAX; /* truncate the address so it is small enough to fit in a size_t */
-#endif
-			return addr;
-		}
-	};
-}
\ No newline at end of file
diff --git a/include/openvic-dataloader/detail/utility/SelfType.hpp b/include/openvic-dataloader/detail/utility/SelfType.hpp
deleted file mode 100644
index 5209700..0000000
--- a/include/openvic-dataloader/detail/utility/SelfType.hpp
+++ /dev/null
@@ -1,28 +0,0 @@
-#pragma once
-
-#include <type_traits>
-
-namespace ovdl::detail {
-#if !defined(_MSC_VER)
-#pragma GCC diagnostic push
-#pragma clang diagnostic ignored "-Wunknown-warning-option"
-#pragma GCC diagnostic ignored "-Wnon-template-friend"
-#endif
-	template<typename T>
-	struct Reader {
-		friend auto adl_GetSelfType(Reader<T>);
-	};
-
-	template<typename T, typename U>
-	struct Writer {
-		friend auto adl_GetSelfType(Reader<T>) { return U {}; }
-	};
-#if !defined(_MSC_VER)
-#pragma GCC diagnostic pop
-#endif
-
-	inline void adl_GetSelfType() {}
-
-	template<typename T>
-	using Read = std::remove_pointer_t<decltype(adl_GetSelfType(Reader<T> {}))>;
-}
diff --git a/include/openvic-dataloader/detail/utility/TypeName.hpp b/include/openvic-dataloader/detail/utility/TypeName.hpp
deleted file mode 100644
index 1a34a0f..0000000
--- a/include/openvic-dataloader/detail/utility/TypeName.hpp
+++ /dev/null
@@ -1,52 +0,0 @@
-#pragma once
-
-#include <array>
-#include <cstddef>
-#include <string_view>
-#include <utility>
-
-namespace ovdl::detail {
-
-	template<std::size_t... Idxs>
-	constexpr auto substring_as_array(std::string_view str, std::index_sequence<Idxs...>) {
-		return std::array { str[Idxs]... };
-	}
-
-	template<typename T>
-	constexpr auto type_name_array() {
-#if defined(__clang__)
-		constexpr auto prefix = std::string_view { "[T = " };
-		constexpr auto suffix = std::string_view { "]" };
-		constexpr auto function = std::string_view { __PRETTY_FUNCTION__ };
-#elif defined(__GNUC__)
-		constexpr auto prefix = std::string_view { "with T = " };
-		constexpr auto suffix = std::string_view { "]" };
-		constexpr auto function = std::string_view { __PRETTY_FUNCTION__ };
-#elif defined(_MSC_VER)
-		constexpr auto prefix = std::string_view { "type_name_array<" };
-		constexpr auto suffix = std::string_view { ">(void)" };
-		constexpr auto function = std::string_view { __FUNCSIG__ };
-#else
-#error Unsupported compiler
-#endif
-
-		constexpr auto start = function.find(prefix) + prefix.size();
-		constexpr auto end = function.rfind(suffix);
-
-		static_assert(start < end);
-
-		constexpr auto name = function.substr(start, (end - start));
-		return substring_as_array(name, std::make_index_sequence<name.size()> {});
-	}
-
-	template<typename T>
-	struct type_name_holder {
-		static inline constexpr auto value = type_name_array<T>();
-	};
-
-	template<typename T>
-	constexpr auto type_name() -> std::string_view {
-		constexpr auto& value = type_name_holder<T>::value;
-		return std::string_view { value.data(), value.size() };
-	}
-}
\ No newline at end of file
diff --git a/include/openvic-dataloader/detail/utility/Utility.hpp b/include/openvic-dataloader/detail/utility/Utility.hpp
deleted file mode 100644
index 138a029..0000000
--- a/include/openvic-dataloader/detail/utility/Utility.hpp
+++ /dev/null
@@ -1,38 +0,0 @@
-#pragma once
-
-#include <string_view>
-#include <type_traits>
-
-#include "openvic-dataloader/detail/utility/TypeName.hpp"
-
-namespace ovdl::detail {
-	[[noreturn]] inline void unreachable() {
-		// Uses compiler specific extensions if possible.
-		// Even if no extension is used, undefined behavior is still raised by
-		// an empty function body and the noreturn attribute.
-#ifdef __GNUC__ // GCC, Clang, ICC
-		__builtin_unreachable();
-#elif defined(_MSC_VER) // MSVC
-		__assume(false);
-#endif
-	}
-
-	template<typename Kind>
-	constexpr std::string_view get_kind_name() {
-		constexpr auto name = type_name<Kind>();
-
-		return name;
-	}
-
-	template<typename EnumT>
-		requires std::is_enum_v<EnumT>
-	constexpr std::underlying_type_t<EnumT> to_underlying(EnumT e) {
-		return static_cast<std::underlying_type_t<EnumT>>(e);
-	}
-
-	template<typename EnumT>
-		requires std::is_enum_v<EnumT>
-	constexpr EnumT from_underlying(std::underlying_type_t<EnumT> ut) {
-		return static_cast<EnumT>(ut);
-	}
-}
\ No newline at end of file