Rework Grammar and Parser

Properly construct headless binary with basic validation and print functionality

Add Error and Warning structs to Parser
Add FileNode pointer getter to Parser
Change all `char8_t*` and `const char8_t` to `const char*` in Parser
Add Parser move operators and Parser deconstructor
Add BufferHandler PIMPL object to Parser
Add UTF-8 file Warning

Add proper Grammar value retrieval
Simplify AST node resolution for Grammar

Add AbstractSyntaxTree for v2script data parser:
	Has compile-time embedded type information accessible at compile-time and runtime
	Optionally compiled AST print functionality

Add detail/TypeName.hpp
Add detail/SelfType.hpp
Add detail/DetectUtf8.hpp
Add detail/Errors.hpp
Add detail/Warnings.hpp

Add `OPENVIC_DATALOADER_PRINT_NODES` for headless construction
Fix wrong environment reference for headless construction in SConstruct

5 files changed, 138 insertions, 0 deletions

diff --git a/src/openvic-dataloader/detail/DetectUtf8.hpp b/src/openvic-dataloader/detail/DetectUtf8.hpp
new file mode 100644
index 0000000..b2969ce
--- /dev/null
+++ b/src/openvic-dataloader/detail/DetectUtf8.hpp
@@ -0,0 +1,52 @@
+#pragma once
+
+#include "detail/LexyLitRange.hpp"
+#include <lexy/action/match.hpp>
+#include <lexy/dsl.hpp>
+
+namespace ovdl::detail {
+	namespace detect_utf8 {
+
+		template<bool INCLUDE_ASCII>
+		struct DetectUtf8 {
+			struct not_utf8 {
+				static constexpr auto name = "not utf8";
+			};
+
+			static constexpr auto rule = [] {
+				constexpr auto is_not_ascii_flag = lexy::dsl::context_flag<DetectUtf8>;
+
+				// & 0b10000000 == 0b00000000
+				constexpr auto ascii_values = lexydsl::make_range<0b00000000, 0b01111111>();
+				// & 0b11100000 == 0b11000000
+				constexpr auto two_byte = lexydsl::make_range<0b11000000, 0b11011111>();
+				// & 0b11110000 == 0b11100000
+				constexpr auto three_byte = lexydsl::make_range<0b11100000, 0b11101111>();
+				// & 0b11111000 == 0b11110000
+				constexpr auto four_byte = lexydsl::make_range<0b11110000, 0b11110111>();
+				// & 0b11000000 == 0b10000000
+				constexpr auto check_bytes = lexydsl::make_range<0b10000000, 0b10111111>();
+
+				constexpr auto utf8_check =
+					((four_byte >> lexy::dsl::times<3>(check_bytes)) |
+						(three_byte >> lexy::dsl::times<2>(check_bytes)) |
+						(two_byte >> lexy::dsl::times<1>(check_bytes))) >>
+					is_not_ascii_flag.set();
+
+				return is_not_ascii_flag.template create<INCLUDE_ASCII>() +
+					   lexy::dsl::while_(utf8_check | ascii_values) +
+					   lexy::dsl::must(is_not_ascii_flag.is_set()).template error<not_utf8>;
+			}();
+		};
+	}
+
+	template<typename Input>
+	constexpr bool is_utf8_no_ascii(const Input& input) {
+		return lexy::match<detect_utf8::DetectUtf8<false>>(input);
+	}
+
+	template<typename Input>
+	constexpr bool is_utf8(const Input& input) {
+		return lexy::match<detect_utf8::DetectUtf8<true>>(input);
+	}
+}
\ No newline at end of file
diff --git a/src/openvic-dataloader/detail/Errors.hpp b/src/openvic-dataloader/detail/Errors.hpp
new file mode 100644
index 0000000..f8ed21b
--- /dev/null
+++ b/src/openvic-dataloader/detail/Errors.hpp
@@ -0,0 +1,19 @@
+#pragma once
+
+#include "openvic-dataloader/v2script/Parser.hpp"
+
+namespace ovdl::v2script::errors {
+	inline const v2script::Parser::Error make_no_file_error(const char* file_path) {
+		std::string message;
+		if (!file_path) {
+			message = "File path not specified.";
+		} else {
+			message = "File '" + std::string(file_path) + "' was not found.";
+		}
+
+		return v2script::Parser::Error { Parser::Error::Type::Fatal, message, 1 };
+	}
+}
+
+namespace ovdl::ovscript::errors {
+}
\ No newline at end of file
diff --git a/src/openvic-dataloader/detail/LexyLitRange.hpp b/src/openvic-dataloader/detail/LexyLitRange.hpp
new file mode 100644
index 0000000..a6761a8
--- /dev/null
+++ b/src/openvic-dataloader/detail/LexyLitRange.hpp
@@ -0,0 +1,16 @@
+#pragma once
+
+#include <lexy/dsl/literal.hpp>
+
+namespace ovdl::detail::lexydsl {
+	template<unsigned char LOW, unsigned char HIGH>
+	consteval auto make_range() {
+		if constexpr (LOW == HIGH) {
+			return lexy::dsl::lit_c<LOW>;
+		} else if constexpr (LOW == (HIGH - 1)) {
+			return lexy::dsl::lit_c<LOW> / lexy::dsl::lit_c<HIGH>;
+		} else {
+			return lexy::dsl::lit_c<LOW> / make_range<LOW + 1, HIGH>();
+		}
+	}
+}
\ No newline at end of file
diff --git a/src/openvic-dataloader/detail/NullBuff.hpp b/src/openvic-dataloader/detail/NullBuff.hpp
new file mode 100644
index 0000000..baf9e1b
--- /dev/null
+++ b/src/openvic-dataloader/detail/NullBuff.hpp
@@ -0,0 +1,30 @@
+#pragma once
+
+#include <ostream>
+
+namespace ovdl::detail {
+	template<class cT, class traits = std::char_traits<cT>>
+	class basic_nullbuf : public std::basic_streambuf<cT, traits> {
+		typename traits::int_type overflow(typename traits::int_type c) {
+			return traits::not_eof(c); // indicate success
+		}
+	};
+
+	template<class cT, class traits = std::char_traits<cT>>
+	class basic_onullstream : public std::basic_ostream<cT, traits> {
+	public:
+		basic_onullstream() : std::basic_ios<cT, traits>(&m_sbuf),
+							  std::basic_ostream<cT, traits>(&m_sbuf) {
+			std::basic_ios<cT, traits>::init(&m_sbuf);
+		}
+
+	private:
+		basic_nullbuf<cT, traits> m_sbuf;
+	};
+
+	typedef basic_onullstream<char> onullstream;
+	typedef basic_onullstream<wchar_t> wonullstream;
+
+	inline onullstream cnull;
+	inline onullstream wcnull;
+}
\ No newline at end of file
diff --git a/src/openvic-dataloader/detail/Warnings.hpp b/src/openvic-dataloader/detail/Warnings.hpp
new file mode 100644
index 0000000..f854fa8
--- /dev/null
+++ b/src/openvic-dataloader/detail/Warnings.hpp
@@ -0,0 +1,21 @@
+#pragma once
+
+#include "openvic-dataloader/v2script/Parser.hpp"
+
+namespace ovdl::v2script::warnings {
+	inline const v2script::Parser::Warning make_utf8_warning(const char* file_path) {
+		constexpr std::string_view message_suffix = "This may cause problems. Prefer Windows-1252 encoding.";
+
+		std::string message;
+		if (!file_path) {
+			message = "Buffer is a UTF-8 encoded string. " + std::string(message_suffix);
+		} else {
+			message = "File '" + std::string(file_path) + "' is a UTF-8 encoded file. " + std::string(message_suffix);
+		}
+
+		return v2script::Parser::Warning { message, 1 };
+	}
+}
+
+namespace ovdl::ovscript::warnings {
+}
\ No newline at end of file