diff options
Diffstat (limited to 'src/openvic-dataloader')
21 files changed, 1690 insertions, 74 deletions
diff --git a/src/openvic-dataloader/csv/CsvGrammar.hpp b/src/openvic-dataloader/csv/CsvGrammar.hpp new file mode 100644 index 0000000..edce97b --- /dev/null +++ b/src/openvic-dataloader/csv/CsvGrammar.hpp @@ -0,0 +1,129 @@ +#pragma once + +#include <initializer_list> +#include <string> +#include <tuple> +#include <type_traits> +#include <vector> + +#include <openvic-dataloader/csv/LineObject.hpp> + +#include <lexy/callback.hpp> +#include <lexy/dsl.hpp> + +// Grammar Definitions // +namespace ovdl::csv::grammar { + struct StringValue { + static constexpr auto escaped_symbols = lexy::symbol_table<char> // + .map<'"'>('"') + .map<'\''>('\'') + .map<'\\'>('\\') + .map<'/'>('/') + .map<'b'>('\b') + .map<'f'>('\f') + .map<'n'>('\n') + .map<'r'>('\r') + .map<'t'>('\t'); + /// This doesn't actually do anything, so this might to be manually parsed if vic2's CSV parser creates a " from "" + static constexpr auto escaped_quote = lexy::symbol_table<char> // + .map<'"'>('"'); + static constexpr auto rule = [] { + // Arbitrary code points + auto c = -lexy::dsl::lit_c<'"'>; + + auto back_escape = lexy::dsl::backslash_escape // + .symbol<escaped_symbols>(); + + auto quote_escape = lexy::dsl::escape(lexy::dsl::lit_c<'"'>) // + .symbol<escaped_quote>(); + + return lexy::dsl::quoted(c, back_escape, quote_escape); + }(); + + static constexpr auto value = lexy::as_string<std::string>; + }; + + template<auto Sep> + struct PlainValue { + static constexpr auto rule = lexy::dsl::identifier(-(Sep / lexy::dsl::lit_c<'\n'>)); + static constexpr auto value = lexy::as_string<std::string>; + }; + + template<auto Sep> + struct Value { + static constexpr auto rule = lexy::dsl::p<StringValue> | lexy::dsl::p<PlainValue<Sep>>; + static constexpr auto value = lexy::forward<std::string>; + }; + + template<auto Sep> + struct SeperatorCount { + static constexpr auto rule = lexy::dsl::list(Sep); + static constexpr auto value = lexy::count; + }; + + template<auto Sep> + struct LineEnd { + static constexpr auto rule = lexy::dsl::list(lexy::dsl::p<Value<Sep>>, lexy::dsl::trailing_sep(lexy::dsl::p<SeperatorCount<Sep>>)); + static constexpr auto value = lexy::fold_inplace<csv::LineObject>( + std::initializer_list<csv::LineObject::value_type> {}, + [](csv::LineObject& result, auto&& arg) { + if constexpr (std::is_same_v<std::decay_t<decltype(arg)>, std::size_t>) { + // Count seperators, adds to previous value, making it a position + using position_type = csv::LineObject::position_type; + result.emplace_back(static_cast<position_type>(arg + std::get<0>(result.back())), ""); + } else { + if (result.empty()) result.emplace_back(0u, LEXY_MOV(arg)); + else { + auto& [pos, value] = result.back(); + value = arg; + } + } + }); + }; + + template<auto Sep> + struct Line { + + static constexpr auto suffix_setter(csv::LineObject& line) { + auto& [position, value] = line.back(); + if (value.empty()) { + line.set_suffix_end(position); + line.pop_back(); + } else { + line.set_suffix_end(position + 1); + } + }; + + static constexpr auto rule = lexy::dsl::p<LineEnd<Sep>> | lexy::dsl::p<SeperatorCount<Sep>> >> lexy::dsl::p<LineEnd<Sep>>; + static constexpr auto value = + lexy::callback<csv::LineObject>( + [](csv::LineObject&& line) { + suffix_setter(line); + return LEXY_MOV(line); + }, + [](std::size_t prefix_count, csv::LineObject&& line) { + line.set_prefix_end(prefix_count); + // position needs to be adjusted to prefix + for (auto& [position, value] : line) { + position += prefix_count; + } + suffix_setter(line); + return LEXY_MOV(line); + }); + }; + + template<auto Sep> + struct File { + static constexpr auto rule = + lexy::dsl::whitespace(lexy::dsl::newline) + + lexy::dsl::opt(lexy::dsl::list(lexy::dsl::p<Line<Sep>>, lexy::dsl::trailing_sep(lexy::dsl::eol))); + + static constexpr auto value = lexy::as_list<std::vector<csv::LineObject>>; + }; + + using CommaFile = File<lexy::dsl::lit_c<','>>; + using ColonFile = File<lexy::dsl::lit_c<':'>>; + using SemiColonFile = File<lexy::dsl::lit_c<';'>>; + using TabFile = File<lexy::dsl::lit_c<'\t'>>; + using BarFile = File<lexy::dsl::lit_c<'|'>>; +}
\ No newline at end of file diff --git a/src/openvic-dataloader/csv/Parser.cpp b/src/openvic-dataloader/csv/Parser.cpp new file mode 100644 index 0000000..8a99085 --- /dev/null +++ b/src/openvic-dataloader/csv/Parser.cpp @@ -0,0 +1,151 @@ +#include <memory> +#include <vector> + +#include <openvic-dataloader/csv/LineObject.hpp> +#include <openvic-dataloader/csv/Parser.hpp> + +#include <lexy/action/parse.hpp> +#include <lexy/encoding.hpp> +#include <lexy/input/buffer.hpp> +#include <lexy/input/file.hpp> + +#include "csv/CsvGrammar.hpp" +#include "detail/BasicBufferHandler.hpp" +#include "detail/Errors.hpp" +#include "detail/LexyReportError.hpp" +#include "detail/OStreamOutputIterator.hpp" + +using namespace ovdl; +using namespace ovdl::csv; + +/// BufferHandler /// + +class Parser::BufferHandler final : public detail::BasicBufferHandler<lexy::utf8_char_encoding> { +public: + template<typename Node, typename ErrorCallback> + std::optional<std::vector<ParseError>> parse(const ErrorCallback& callback) { + auto result = lexy::parse<Node>(_buffer, callback); + if (!result) { + return result.errors(); + } + _lines = std::move(result.value()); + return std::nullopt; + } + + std::vector<csv::LineObject>& get_lines() { + return _lines; + } + +private: + std::vector<csv::LineObject> _lines; +}; + +/// BufferHandler /// + +Parser::Parser() + : _buffer_handler(std::make_unique<BufferHandler>()) { + set_error_log_to_stderr(); +} + +Parser::Parser(Parser&&) = default; +Parser& Parser::operator=(Parser&&) = default; +Parser::~Parser() = default; + +Parser Parser::from_buffer(const char* data, std::size_t size) { + Parser result; + return std::move(result.load_from_buffer(data, size)); +} + +Parser Parser::from_buffer(const char* start, const char* end) { + Parser result; + return std::move(result.load_from_buffer(start, end)); +} + +Parser Parser::from_string(const std::string_view string) { + Parser result; + return std::move(result.load_from_string(string)); +} + +Parser Parser::from_file(const char* path) { + Parser result; + return std::move(result.load_from_file(path)); +} + +Parser Parser::from_file(const std::filesystem::path& path) { + Parser result; + return std::move(result.load_from_file(path)); +} + +/// +/// @brief Executes a function on _buffer_handler that is expected to load a buffer +/// +/// Expected Use: +/// @code {.cpp} +/// _run_load_func(&BufferHandler::<load_function>, <arguments>); +/// @endcode +/// +/// @tparam Type +/// @tparam Args +/// @param func +/// @param args +/// +template<typename... Args> +constexpr void Parser::_run_load_func(detail::LoadCallback<BufferHandler, Args...> auto func, Args... args) { + _warnings.clear(); + _errors.clear(); + _has_fatal_error = false; + if (auto error = func(_buffer_handler.get(), std::forward<Args>(args)...); error) { + _has_fatal_error = error.value().type == ParseError::Type::Fatal; + _errors.push_back(error.value()); + _error_stream.get() << "Error: " << _errors.back().message << '\n'; + } +} + +constexpr Parser& Parser::load_from_buffer(const char* data, std::size_t size) { + // Type can't be deduced? + _run_load_func(std::mem_fn(&BufferHandler::load_buffer_size), data, size); + return *this; +} + +constexpr Parser& Parser::load_from_buffer(const char* start, const char* end) { + // Type can't be deduced? + _run_load_func(std::mem_fn(&BufferHandler::load_buffer), start, end); + return *this; +} + +constexpr Parser& Parser::load_from_string(const std::string_view string) { + return load_from_buffer(string.data(), string.size()); +} + +constexpr Parser& Parser::load_from_file(const char* path) { + _file_path = path; + // Type can be deduced?? + _run_load_func(std::mem_fn(&BufferHandler::load_file), path); + return *this; +} + +Parser& Parser::load_from_file(const std::filesystem::path& path) { + return load_from_file(path.string().c_str()); +} + +constexpr Parser& Parser::load_from_file(const detail::Has_c_str auto& path) { + return load_from_file(path.c_str()); +} + +bool Parser::parse_csv() { + if (!_buffer_handler->is_valid()) { + return false; + } + + auto errors = _buffer_handler->parse<csv::grammar::SemiColonFile>(ovdl::detail::ReporError.path(_file_path).to(detail::OStreamOutputIterator { _error_stream })); + if (errors) { + _errors.reserve(errors->size()); + for (auto& err : errors.value()) { + _has_fatal_error |= err.type == ParseError::Type::Fatal; + _errors.push_back(err); + } + return false; + } + _lines = std::move(_buffer_handler->get_lines()); + return true; +}
\ No newline at end of file diff --git a/src/openvic-dataloader/detail/BasicBufferHandler.hpp b/src/openvic-dataloader/detail/BasicBufferHandler.hpp new file mode 100644 index 0000000..ba2cef9 --- /dev/null +++ b/src/openvic-dataloader/detail/BasicBufferHandler.hpp @@ -0,0 +1,44 @@ +#pragma once + +#include <optional> + +#include <openvic-dataloader/ParseError.hpp> + +#include <lexy/encoding.hpp> +#include <lexy/input/buffer.hpp> +#include <lexy/input/file.hpp> + +#include "detail/Errors.hpp" + +namespace ovdl::detail { + template<typename Encoding = lexy::default_encoding, typename MemoryResource = void> + class BasicBufferHandler { + public: + constexpr bool is_valid() const { + return _buffer.size() != 0; + } + + constexpr std::optional<ovdl::ParseError> load_buffer_size(const char* data, std::size_t size) { + _buffer = lexy::buffer<Encoding, MemoryResource>(data, size); + return std::nullopt; + } + + constexpr std::optional<ovdl::ParseError> load_buffer(const char* start, const char* end) { + _buffer = lexy::buffer<Encoding, MemoryResource>(start, end); + return std::nullopt; + } + + std::optional<ovdl::ParseError> load_file(const char* path) { + auto file = lexy::read_file<Encoding, lexy::encoding_endianness::bom, MemoryResource>(path); + if (!file) { + return ovdl::errors::make_no_file_error(path); + } + + _buffer = file.buffer(); + return std::nullopt; + } + + protected: + lexy::buffer<Encoding, MemoryResource> _buffer; + }; +}
\ No newline at end of file diff --git a/src/openvic-dataloader/detail/BasicParser.cpp b/src/openvic-dataloader/detail/BasicParser.cpp new file mode 100644 index 0000000..ee1b516 --- /dev/null +++ b/src/openvic-dataloader/detail/BasicParser.cpp @@ -0,0 +1,47 @@ +#include <iostream> +#include <ostream> + +#include <openvic-dataloader/detail/BasicParser.hpp> + +#include "detail/NullBuff.hpp" + +using namespace ovdl; +using namespace ovdl::detail; + +BasicParser::BasicParser() : _error_stream(detail::cnull) {} + +void BasicParser::set_error_log_to_null() { + set_error_log_to(detail::cnull); +} + +void BasicParser::set_error_log_to_stderr() { + set_error_log_to(std::cerr); +} + +void BasicParser::set_error_log_to_stdout() { + set_error_log_to(std::cout); +} + +void BasicParser::set_error_log_to(std::basic_ostream<char>& stream) { + _error_stream = stream; +} + +bool BasicParser::has_error() const { + return !_errors.empty(); +} + +bool BasicParser::has_fatal_error() const { + return _has_fatal_error; +} + +bool BasicParser::has_warning() const { + return !_warnings.empty(); +} + +const std::vector<ovdl::ParseError>& BasicParser::get_errors() const { + return _errors; +} + +const std::vector<ovdl::ParseWarning>& BasicParser::get_warnings() const { + return _warnings; +}
\ No newline at end of file diff --git a/src/openvic-dataloader/detail/DetectUtf8.hpp b/src/openvic-dataloader/detail/DetectUtf8.hpp new file mode 100644 index 0000000..2045b3c --- /dev/null +++ b/src/openvic-dataloader/detail/DetectUtf8.hpp @@ -0,0 +1,53 @@ +#pragma once + +#include <lexy/action/match.hpp> +#include <lexy/dsl.hpp> + +#include "detail/LexyLitRange.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..f53bedc --- /dev/null +++ b/src/openvic-dataloader/detail/Errors.hpp @@ -0,0 +1,23 @@ +#pragma once + +#include "openvic-dataloader/v2script/Parser.hpp" + +namespace ovdl::errors { + inline const ParseError 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 ParseError { ParseError::Type::Fatal, message, 1 }; + } +} + +namespace ovdl::v2script::errors { + +} + +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/LexyReportError.hpp b/src/openvic-dataloader/detail/LexyReportError.hpp new file mode 100644 index 0000000..684b5db --- /dev/null +++ b/src/openvic-dataloader/detail/LexyReportError.hpp @@ -0,0 +1,102 @@ +#pragma once + +#include <cstddef> +#include <sstream> +#include <string> +#include <utility> +#include <vector> + +#include <openvic-dataloader/ParseData.hpp> +#include <openvic-dataloader/ParseError.hpp> + +#include <lexy/input_location.hpp> +#include <lexy/visualize.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 }; + } + + /// 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/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/OStreamOutputIterator.hpp b/src/openvic-dataloader/detail/OStreamOutputIterator.hpp new file mode 100644 index 0000000..81f6c89 --- /dev/null +++ b/src/openvic-dataloader/detail/OStreamOutputIterator.hpp @@ -0,0 +1,21 @@ +#pragma once + +#include <ostream> + +namespace ovdl::detail { + struct OStreamOutputIterator { + std::reference_wrapper<std::ostream> _stream; + + auto operator*() const noexcept { + return *this; + } + auto operator++(int) const noexcept { + return *this; + } + + OStreamOutputIterator& operator=(char c) { + _stream.get().put(c); + return *this; + } + }; +}
\ 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..fc0fbed --- /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 ParseWarning 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 ParseWarning { message, 1 }; + } +} + +namespace ovdl::ovscript::warnings { +}
\ No newline at end of file diff --git a/src/openvic-dataloader/v2script/AbstractSyntaxTree.cpp b/src/openvic-dataloader/v2script/AbstractSyntaxTree.cpp new file mode 100644 index 0000000..f9fb716 --- /dev/null +++ b/src/openvic-dataloader/v2script/AbstractSyntaxTree.cpp @@ -0,0 +1,247 @@ +#include <iomanip> +#include <sstream> +#include <string> +#include <utility> +#include <vector> + +#include <stddef.h> + +#include <openvic-dataloader/v2script/AbstractSyntaxTree.hpp> + +using namespace ovdl::v2script::ast; + +void ovdl::v2script::ast::copy_into_node_ptr_vector(const std::vector<NodePtr>& source, std::vector<NodeUPtr>& dest) { + dest.clear(); + dest.reserve(source.size()); + for (auto&& p : source) { + dest.push_back(NodeUPtr { p }); + } +} + +AbstractStringNode::AbstractStringNode(std::string&& name) : _name(std::move(name)) {} +std::ostream& AbstractStringNode::print(std::ostream& stream, size_t indent) const { + return stream << _name; +} + +#define OVDL_AST_STRING_NODE_DEF(NAME, ...) \ + NAME::NAME(std::string&& name) : AbstractStringNode(std::move(name)) {} \ + std::ostream& NAME::print(std::ostream& stream, size_t indent) const __VA_ARGS__ + +OVDL_AST_STRING_NODE_DEF(IdentifierNode, { + return stream << _name; +}); + +OVDL_AST_STRING_NODE_DEF(StringNode, { + return stream << '"' << _name << '"'; +}); + +OVDL_AST_STRING_NODE_DEF(FactorNode, { + return stream << "factor = " << _name; +}); + +OVDL_AST_STRING_NODE_DEF(MonthNode, { + return stream << "months = " << _name; +}); + +OVDL_AST_STRING_NODE_DEF(NameNode, { + return stream << "name = " << _name; +}); + +OVDL_AST_STRING_NODE_DEF(FireOnlyNode, { + return stream << "fire_only_once = " << _name; +}); + +OVDL_AST_STRING_NODE_DEF(IdNode, { + return stream << "id = " << _name; +}); + +OVDL_AST_STRING_NODE_DEF(TitleNode, { + return stream << "title = " << _name; +}); + +OVDL_AST_STRING_NODE_DEF(DescNode, { + return stream << "desc = " << _name; +}); + +OVDL_AST_STRING_NODE_DEF(PictureNode, { + return stream << "picture = " << _name; +}); + +OVDL_AST_STRING_NODE_DEF(IsTriggeredNode, { + return stream << "is_triggered_only = " << _name; +}); + +#undef OVDL_AST_STRING_NODE_DEF + +AssignNode::AssignNode(NodeCPtr name, NodePtr init) + : _initializer(std::move(init)) { + if (name->is_type<IdentifierNode>()) { + _name = cast_node_cptr<IdentifierNode>(name)._name; + } +} + +std::ostream& Node::print_ptr(std::ostream& stream, NodeCPtr node, size_t indent) { + return node != nullptr ? node->print(stream, indent) : stream << "<NULL>"; +} + +static std::ostream& print_newline_indent(std::ostream& stream, size_t indent) { + return stream << "\n" + << std::setw(indent) << std::setfill('\t') << ""; +} + +/* Starts with a newline and ends at the end of a line, and so + * should be followed by a call to print_newline_indent. + */ +static std::ostream& print_nodeuptr_vector(const std::vector<NodeUPtr>& nodes, + std::ostream& stream, size_t indent) { + for (NodeUPtr const& node : nodes) { + print_newline_indent(stream, indent); + Node::print_ptr(stream, node.get(), indent); + } + return stream; +} + +AbstractListNode::AbstractListNode(const std::vector<NodePtr>& statements) { + copy_into_node_ptr_vector(statements, _statements); +} +std::ostream& AbstractListNode::print(std::ostream& stream, size_t indent) const { + stream << '{'; + if (!_statements.empty()) { + print_nodeuptr_vector(_statements, stream, indent + 1); + print_newline_indent(stream, indent); + } + return stream << "}"; +} + +#define OVDL_AST_LIST_NODE_DEF(NAME, ...) \ + NAME::NAME(const std::vector<NodePtr>& statements) : AbstractListNode(statements) {} \ + std::ostream& NAME::print(std::ostream& stream, size_t indent) const __VA_ARGS__ + +OVDL_AST_LIST_NODE_DEF(FileNode, { + print_nodeuptr_vector(_statements, stream, indent); + return print_newline_indent(stream, indent); +}); + +OVDL_AST_LIST_NODE_DEF(ListNode, { + stream << '{'; + if (!_statements.empty()) { + print_nodeuptr_vector(_statements, stream, indent + 1); + print_newline_indent(stream, indent); + } + return stream << "}"; +}); + +OVDL_AST_LIST_NODE_DEF(ModifierNode, { + stream << "modifier = {"; + if (!_statements.empty()) { + print_nodeuptr_vector(_statements, stream, indent + 1); + print_newline_indent(stream, indent); + } + return stream << '}'; +}); + +OVDL_AST_LIST_NODE_DEF(MtthNode, { + stream << "mean_time_to_happen = {"; + if (!_statements.empty()) { + print_nodeuptr_vector(_statements, stream, indent + 1); + print_newline_indent(stream, indent); + } + return stream << '}'; +}); + +OVDL_AST_LIST_NODE_DEF(EventOptionNode, { + stream << "option = {"; + if (!_statements.empty()) { + print_nodeuptr_vector(_statements, stream, indent + 1); + print_newline_indent(stream, indent); + } + return stream << '}'; +}); + +OVDL_AST_LIST_NODE_DEF(BehaviorListNode, { + stream << "ai_chance = {"; // may be ai_chance or ai_will_do + if (!_statements.empty()) { + print_nodeuptr_vector(_statements, stream, indent + 1); + print_newline_indent(stream, indent); + } + return stream << '}'; +}); + +OVDL_AST_LIST_NODE_DEF(DecisionListNode, { + stream << "political_decisions = {"; + if (!_statements.empty()) { + print_nodeuptr_vector(_statements, stream, indent + 1); + print_newline_indent(stream, indent); + } + return stream << '}'; +}); + +#undef OVDL_AST_LIST_NODE_DEF + +EventNode::EventNode(Type type, const std::vector<NodePtr>& statements) : _type(type) { + copy_into_node_ptr_vector(statements, _statements); +} +std::ostream& EventNode::print(std::ostream& stream, size_t indent) const { + switch (_type) { + case Type::Country: stream << "country_event = "; break; + case Type::Province: stream << "province_event = "; break; + } + stream << '{'; + if (!_statements.empty()) { + print_nodeuptr_vector(_statements, stream, indent + 1); + print_newline_indent(stream, indent); + } + return stream << '}'; +} + +DecisionNode::DecisionNode(NodePtr name, const std::vector<NodePtr>& statements) : _name(std::move(name)) { + copy_into_node_ptr_vector(statements, _statements); +} +std::ostream& DecisionNode::print(std::ostream& stream, size_t indent) const { + print_ptr(stream, _name.get(), indent) << " = {"; + if (!_statements.empty()) { + print_nodeuptr_vector(_statements, stream, indent + 1); + print_newline_indent(stream, indent); + } + return stream << '}'; +} + +ExecutionNode::ExecutionNode(Type type, NodePtr name, NodePtr init) : _type(type), + _name(std::move(name)), + _initializer(std::move(init)) { +} +std::ostream& ExecutionNode::print(std::ostream& stream, size_t indent) const { + print_ptr(stream, _name.get(), indent) << " = "; + if (_initializer) { + Node::print_ptr(stream, _initializer.get(), indent + 1); + } + return stream; +} + +ExecutionListNode::ExecutionListNode(ExecutionNode::Type type, const std::vector<NodePtr>& statements) : _type(type) { + copy_into_node_ptr_vector(statements, _statements); +} +std::ostream& ExecutionListNode::print(std::ostream& stream, size_t indent) const { + // Only way to make a valid declared parsable file + stream << "{ "; + switch (_type) { + case ExecutionNode::Type::Effect: stream << "effect = {"; break; + case ExecutionNode::Type::Trigger: stream << "trigger = {"; break; + } + if (!_statements.empty()) { + print_nodeuptr_vector(_statements, stream, indent + 1); + print_newline_indent(stream, indent); + } + return stream << "}}"; +} + +Node::operator std::string() const { + std::stringstream ss; + ss << *this; + return ss.str(); +} + +std::ostream& AssignNode::print(std::ostream& stream, size_t indent) const { + stream << _name << " = "; + return Node::print_ptr(stream, _initializer.get(), indent); +} diff --git a/src/openvic-dataloader/v2script/AiBehaviorGrammar.hpp b/src/openvic-dataloader/v2script/AiBehaviorGrammar.hpp new file mode 100644 index 0000000..012820f --- /dev/null +++ b/src/openvic-dataloader/v2script/AiBehaviorGrammar.hpp @@ -0,0 +1,34 @@ +#pragma once + +#include <openvic-dataloader/v2script/AbstractSyntaxTree.hpp> + +#include <lexy/dsl.hpp> + +#include "ModifierGrammar.hpp" +#include "SimpleGrammar.hpp" +#include "TriggerGrammar.hpp" + +namespace ovdl::v2script::grammar { + struct AiBehaviorList { + static constexpr auto rule = lexy::dsl::list(lexy::dsl::p<FactorStatement> | lexy::dsl::p<ModifierStatement>); + + static constexpr auto value = + lexy::as_list<std::vector<ast::NodePtr>> >> + lexy::callback<ast::NodePtr>( + [](auto&& list) { + return ast::make_node_ptr<ast::BehaviorListNode>(LEXY_MOV(list)); + }); + }; + + struct AiBehaviorBlock { + static constexpr auto rule = lexy::dsl::curly_bracketed.opt(lexy::dsl::p<AiBehaviorList>); + + static constexpr auto value = lexy::callback<ast::NodePtr>( + [](auto&& list) { + return LEXY_MOV(list); + }, + [](lexy::nullopt = {}) { + return lexy::nullopt {}; + }); + }; +}
\ No newline at end of file diff --git a/src/openvic-dataloader/v2script/DecisionGrammar.hpp b/src/openvic-dataloader/v2script/DecisionGrammar.hpp new file mode 100644 index 0000000..93ba0f5 --- /dev/null +++ b/src/openvic-dataloader/v2script/DecisionGrammar.hpp @@ -0,0 +1,128 @@ +#pragma once + +#include <memory> +#include <string> +#include <vector> + +#include <openvic-dataloader/v2script/AbstractSyntaxTree.hpp> + +#include <lexy/callback.hpp> +#include <lexy/callback/adapter.hpp> +#include <lexy/callback/container.hpp> +#include <lexy/dsl.hpp> +#include <lexy/dsl/option.hpp> + +#include "AiBehaviorGrammar.hpp" +#include "EffectGrammar.hpp" +#include "SimpleGrammar.hpp" +#include "TriggerGrammar.hpp" + +// Decision Grammar Definitions // +namespace ovdl::v2script::grammar { + ////////////////// + // Macros + ////////////////// +// Produces <KW_NAME>_rule and <KW_NAME>_p +#define OVDL_GRAMMAR_KEYWORD_DEFINE(KW_NAME) \ + struct KW_NAME##_rule { \ + static constexpr auto keyword = LEXY_KEYWORD(#KW_NAME, lexy::dsl::inline_<Identifier>); \ + static constexpr auto rule = keyword >> lexy::dsl::equal_sign; \ + static constexpr auto value = lexy::noop; \ + }; \ + static constexpr auto KW_NAME##_p = lexy::dsl::p<KW_NAME##_rule> + +// Produces <KW_NAME>_rule and <KW_NAME>_p and <KW_NAME>_rule::flag and <KW_NAME>_rule::too_many_error +#define OVDL_GRAMMAR_KEYWORD_FLAG_DEFINE(KW_NAME) \ + struct KW_NAME##_rule { \ + static constexpr auto keyword = LEXY_KEYWORD(#KW_NAME, lexy::dsl::inline_<Identifier>); \ + static constexpr auto rule = keyword >> lexy::dsl::equal_sign; \ + static constexpr auto value = lexy::noop; \ + static constexpr auto flag = lexy::dsl::context_flag<struct KW_NAME##_context>; \ + struct too_many_error { \ + static constexpr auto name = "expected left side " #KW_NAME " to be found once"; \ + }; \ + }; \ + static constexpr auto KW_NAME##_p = lexy::dsl::p<KW_NAME##_rule> >> (lexy::dsl::must(KW_NAME##_rule::flag.is_reset()).error<KW_NAME##_rule::too_many_error> + KW_NAME##_rule::flag.set()) + ////////////////// + // Macros + ////////////////// + struct DecisionStatement { + template<auto Production, typename AstNode> + struct _StringStatement { + static constexpr auto rule = Production >> (lexy::dsl::p<StringExpression> | lexy::dsl::p<Identifier>); + static constexpr auto value = lexy::forward<ast::NodePtr>; + }; + template<auto Production, typename AstNode> + static constexpr auto StringStatement = lexy::dsl::p<_StringStatement<Production, AstNode>>; + + OVDL_GRAMMAR_KEYWORD_FLAG_DEFINE(potential); + OVDL_GRAMMAR_KEYWORD_FLAG_DEFINE(allow); + OVDL_GRAMMAR_KEYWORD_FLAG_DEFINE(effect); + OVDL_GRAMMAR_KEYWORD_FLAG_DEFINE(ai_will_do); + + static constexpr auto rule = [] { + constexpr auto create_flags = + potential_rule::flag.create() + + allow_rule::flag.create() + + effect_rule::flag.create() + + ai_will_do_rule::flag.create(); + + constexpr auto potential_statement = potential_p >> lexy::dsl::p<TriggerBlock>; + constexpr auto allow_statement = allow_p >> lexy::dsl::p<TriggerBlock>; + constexpr auto effect_statement = effect_p >> lexy::dsl::p<TriggerBlock>; + constexpr auto ai_will_do_statement = ai_will_do_p >> lexy::dsl::p<AiBehaviorBlock>; + + return lexy::dsl::p<Identifier> >> + (create_flags + lexy::dsl::equal_sign + + lexy::dsl::curly_bracketed.list( + potential_statement | + allow_statement | + effect_statement | + ai_will_do_statement | + lexy::dsl::p<SimpleAssignmentStatement>)); + }(); + + static constexpr auto value = + lexy::as_list<std::vector<ast::NodePtr>> >> + lexy::callback<ast::NodePtr>( + [](auto&& name, auto&& list) { + return ast::make_node_ptr<ast::DecisionNode>(LEXY_MOV(name), LEXY_MOV(list)); + }, + [](auto&& name, lexy::nullopt = {}) { + return ast::make_node_ptr<ast::DecisionNode>(LEXY_MOV(name)); + }); + }; + + struct DecisionList { + static constexpr auto rule = + LEXY_KEYWORD("political_decisions", lexy::dsl::inline_<Identifier>) >> + (lexy::dsl::equal_sign + lexy::dsl::curly_bracketed.opt_list(lexy::dsl::p<DecisionStatement>)); + + static constexpr auto value = + lexy::as_list<std::vector<ast::NodePtr>> >> + lexy::callback<ast::NodePtr>( + [](auto&& list) { + return ast::make_node_ptr<ast::DecisionListNode>(LEXY_MOV(list)); + }, + [](lexy::nullopt = {}) { + return lexy::nullopt {}; + }); + }; + + struct DecisionFile { + // Allow arbitrary spaces between individual tokens. + static constexpr auto whitespace = whitespace_specifier | comment_specifier; + + static constexpr auto rule = + lexy::dsl::terminator(lexy::dsl::eof).list( // + lexy::dsl::p<DecisionList> | // + lexy::dsl::p<SimpleAssignmentStatement>); + + static constexpr auto value = lexy::as_list<std::vector<ast::NodePtr>> >> lexy::new_<ast::FileNode, ast::NodePtr>; + }; + +#undef OVDL_GRAMMAR_KEYWORD_DEFINE +#undef OVDL_GRAMMAR_KEYWORD_FLAG_DEFINE +#undef OVDL_GRAMMAR_KEYWORD_STATEMENT +#undef OVDL_GRAMMAR_KEYWORD_FLAG_STATEMENT +}
\ No newline at end of file diff --git a/src/openvic-dataloader/v2script/EffectGrammar.hpp b/src/openvic-dataloader/v2script/EffectGrammar.hpp new file mode 100644 index 0000000..9f164b2 --- /dev/null +++ b/src/openvic-dataloader/v2script/EffectGrammar.hpp @@ -0,0 +1,42 @@ +#pragma once + +#include <openvic-dataloader/v2script/AbstractSyntaxTree.hpp> + +#include <lexy/callback.hpp> +#include <lexy/dsl.hpp> + +#include "SimpleGrammar.hpp" + +namespace ovdl::v2script::grammar { + struct EffectStatement { + static constexpr auto rule = lexy::dsl::inline_<SimpleAssignmentStatement>; + + static constexpr auto value = lexy::callback<ast::NodePtr>( + [](auto name, auto&& initalizer) { + return ast::make_node_ptr<ast::ExecutionNode>(ast::ExecutionNode::Type::Effect, LEXY_MOV(name), LEXY_MOV(initalizer)); + }); + }; + + struct EffectList { + static constexpr auto rule = lexy::dsl::list(lexy::dsl::p<SimpleAssignmentStatement>); + + static constexpr auto value = + lexy::as_list<std::vector<ast::NodePtr>> >> + lexy::callback<ast::NodePtr>( + [](auto&& list) { + return ast::make_node_ptr<ast::ExecutionListNode>(ast::ExecutionNode::Type::Effect, LEXY_MOV(list)); + }); + }; + + struct EffectBlock { + static constexpr auto rule = lexy::dsl::curly_bracketed.opt(lexy::dsl::p<EffectList>); + + static constexpr auto value = lexy::callback<ast::NodePtr>( + [](auto&& list) { + return LEXY_MOV(list); + }, + [](lexy::nullopt = {}) { + return lexy::nullopt {}; + }); + }; +}
\ No newline at end of file diff --git a/src/openvic-dataloader/v2script/EventGrammar.hpp b/src/openvic-dataloader/v2script/EventGrammar.hpp new file mode 100644 index 0000000..93a52bf --- /dev/null +++ b/src/openvic-dataloader/v2script/EventGrammar.hpp @@ -0,0 +1,183 @@ +#pragma once + +#include <memory> +#include <string> +#include <vector> + +#include <openvic-dataloader/v2script/AbstractSyntaxTree.hpp> + +#include <lexy/callback.hpp> +#include <lexy/dsl.hpp> + +#include "AiBehaviorGrammar.hpp" +#include "EffectGrammar.hpp" +#include "ModifierGrammar.hpp" +#include "SimpleGrammar.hpp" +#include "TriggerGrammar.hpp" + +// Event Grammar Definitions // +namespace ovdl::v2script::grammar { + ////////////////// + // Macros + ////////////////// +// Produces <KW_NAME>_rule and <KW_NAME>_p +#define OVDL_GRAMMAR_KEYWORD_DEFINE(KW_NAME) \ + struct KW_NAME##_rule { \ + static constexpr auto keyword = LEXY_KEYWORD(#KW_NAME, lexy::dsl::inline_<Identifier>); \ + static constexpr auto rule = keyword >> lexy::dsl::equal_sign; \ + static constexpr auto value = lexy::noop; \ + }; \ + static constexpr auto KW_NAME##_p = lexy::dsl::p<KW_NAME##_rule> + +// Produces <KW_NAME>_rule and <KW_NAME>_p and <KW_NAME>_rule::flag and <KW_NAME>_rule::too_many_error +#define OVDL_GRAMMAR_KEYWORD_FLAG_DEFINE(KW_NAME) \ + struct KW_NAME##_rule { \ + static constexpr auto keyword = LEXY_KEYWORD(#KW_NAME, lexy::dsl::inline_<Identifier>); \ + static constexpr auto rule = keyword >> lexy::dsl::equal_sign; \ + static constexpr auto value = lexy::noop; \ + static constexpr auto flag = lexy::dsl::context_flag<struct KW_NAME##_context>; \ + struct too_many_error { \ + static constexpr auto name = "expected left side " #KW_NAME " to be found once"; \ + }; \ + }; \ + static constexpr auto KW_NAME##_p = lexy::dsl::p<KW_NAME##_rule> >> (lexy::dsl::must(KW_NAME##_rule::flag.is_reset()).error<KW_NAME##_rule::too_many_error> + KW_NAME##_rule::flag.set()) + ////////////////// + // Macros + ////////////////// + static constexpr auto event_symbols = lexy::symbol_table<ast::EventNode::Type> // + .map<LEXY_SYMBOL("country_event")>(ast::EventNode::Type::Country) + .map<LEXY_SYMBOL("province_event")>(ast::EventNode::Type::Province); + + struct EventMtthStatement { + OVDL_GRAMMAR_KEYWORD_DEFINE(months); + + struct MonthValue { + static constexpr auto rule = lexy::dsl::inline_<Identifier>; + static constexpr auto value = lexy::as_string<std::string> | lexy::new_<ast::MonthNode, ast::NodePtr>; + }; + + static constexpr auto rule = lexy::dsl::list( + (months_p >> lexy::dsl::p<MonthValue>) | + lexy::dsl::p<ModifierStatement>); + + static constexpr auto value = + lexy::as_list<std::vector<ast::NodePtr>> >> + lexy::callback<ast::NodePtr>( + [](auto&& list) { + return ast::make_node_ptr<ast::MtthNode>(LEXY_MOV(list)); + }); + }; + + template<auto Production, typename AstNode> + struct _StringStatement { + static constexpr auto rule = Production >> (lexy::dsl::p<StringExpression> | lexy::dsl::p<Identifier>); + static constexpr auto value = + lexy::callback<ast::NodePtr>( + [](auto&& value) { + auto result = ast::make_node_ptr<AstNode>(std::move(static_cast<ast::AbstractStringNode*>(value)->_name)); + delete value; + return result; + }); + }; + template<auto Production, typename AstNode> + static constexpr auto StringStatement = lexy::dsl::p<_StringStatement<Production, AstNode>>; + + struct EventOptionList { + OVDL_GRAMMAR_KEYWORD_FLAG_DEFINE(name); + OVDL_GRAMMAR_KEYWORD_FLAG_DEFINE(ai_chance); + + static constexpr auto rule = [] { + constexpr auto create_flags = name_rule::flag.create() + ai_chance_rule::flag.create(); + + constexpr auto name_statement = StringStatement<name_p, ast::NameNode>; + constexpr auto ai_chance_statement = ai_chance_p >> lexy::dsl::curly_bracketed(lexy::dsl::p<AiBehaviorList>); + + return create_flags + lexy::dsl::list(name_statement | ai_chance_statement | lexy::dsl::p<EffectList>); + }(); + + static constexpr auto value = + lexy::as_list<std::vector<ast::NodePtr>> >> + lexy::callback<ast::NodePtr>( + [](auto&& list) { + return ast::make_node_ptr<ast::EventOptionNode>(LEXY_MOV(list)); + }); + }; + + struct EventStatement { + OVDL_GRAMMAR_KEYWORD_FLAG_DEFINE(id); + OVDL_GRAMMAR_KEYWORD_FLAG_DEFINE(title); + OVDL_GRAMMAR_KEYWORD_FLAG_DEFINE(desc); + OVDL_GRAMMAR_KEYWORD_FLAG_DEFINE(picture); + OVDL_GRAMMAR_KEYWORD_FLAG_DEFINE(is_triggered_only); + OVDL_GRAMMAR_KEYWORD_FLAG_DEFINE(fire_only_once); + OVDL_GRAMMAR_KEYWORD_FLAG_DEFINE(immediate); + OVDL_GRAMMAR_KEYWORD_FLAG_DEFINE(mean_time_to_happen); + OVDL_GRAMMAR_KEYWORD_DEFINE(trigger); + OVDL_GRAMMAR_KEYWORD_DEFINE(option); + + static constexpr auto rule = [] { + constexpr auto symbol_value = lexy::dsl::symbol<event_symbols>(lexy::dsl::inline_<Identifier>); + + constexpr auto create_flags = + id_rule::flag.create() + + title_rule::flag.create() + + desc_rule::flag.create() + + picture_rule::flag.create() + + is_triggered_only_rule::flag.create() + + fire_only_once_rule::flag.create() + + immediate_rule::flag.create() + + mean_time_to_happen_rule::flag.create(); + + constexpr auto id_statement = StringStatement<id_p, ast::IdNode>; + constexpr auto title_statement = StringStatement<title_p, ast::TitleNode>; + constexpr auto desc_statement = StringStatement<desc_p, ast::DescNode>; + constexpr auto picture_statement = StringStatement<picture_p, ast::PictureNode>; + constexpr auto is_triggered_only_statement = StringStatement<is_triggered_only_p, ast::IsTriggeredNode>; + constexpr auto fire_only_once_statement = StringStatement<fire_only_once_p, ast::FireOnlyNode>; + constexpr auto immediate_statement = immediate_p >> lexy::dsl::p<EffectBlock>; + constexpr auto mean_time_to_happen_statement = mean_time_to_happen_p >> lexy::dsl::curly_bracketed(lexy::dsl::p<EventMtthStatement>); + + constexpr auto trigger_statement = trigger_p >> lexy::dsl::curly_bracketed.opt(lexy::dsl::p<TriggerList>); + constexpr auto option_statement = option_p >> lexy::dsl::curly_bracketed(lexy::dsl::p<EventOptionList>); + + return symbol_value >> + (create_flags + lexy::dsl::equal_sign + + lexy::dsl::curly_bracketed.opt_list( + id_statement | + title_statement | + desc_statement | + picture_statement | + is_triggered_only_statement | + fire_only_once_statement | + immediate_statement | + mean_time_to_happen_statement | + trigger_statement | + option_statement | + lexy::dsl::p<SimpleAssignmentStatement>)); + }(); + + static constexpr auto value = + lexy::as_list<std::vector<ast::NodePtr>> >> + lexy::callback<ast::NodePtr>( + [](auto& type, auto&& list) { + return ast::make_node_ptr<ast::EventNode>(type, LEXY_MOV(list)); + }, + [](auto& type, lexy::nullopt = {}) { + return ast::make_node_ptr<ast::EventNode>(type); + }); + }; + + struct EventFile { + // Allow arbitrary spaces between individual tokens. + static constexpr auto whitespace = whitespace_specifier | comment_specifier; + + static constexpr auto rule = lexy::dsl::terminator(lexy::dsl::eof).list(lexy::dsl::p<EventStatement> | lexy::dsl::p<SimpleAssignmentStatement>); + + static constexpr auto value = lexy::as_list<std::vector<ast::NodePtr>> >> lexy::new_<ast::FileNode, ast::NodePtr>; + }; + +#undef OVDL_GRAMMAR_KEYWORD_DEFINE +#undef OVDL_GRAMMAR_KEYWORD_FLAG_DEFINE +#undef OVDL_GRAMMAR_KEYWORD_STATEMENT +#undef OVDL_GRAMMAR_KEYWORD_FLAG_STATEMENT +}
\ No newline at end of file diff --git a/src/openvic-dataloader/v2script/Grammar.cpp b/src/openvic-dataloader/v2script/Grammar.cpp deleted file mode 100644 index ec9fac2..0000000 --- a/src/openvic-dataloader/v2script/Grammar.cpp +++ /dev/null @@ -1,74 +0,0 @@ -#include <lexy/dsl.hpp> -#include <openvic-dataloader/v2script/Parser.hpp> - -using namespace ovdl::v2script; - -// Node Definitions // -namespace dsl = lexy::dsl; - -namespace ovdl::v2script::nodes { - struct StatementListBlock; - - static constexpr auto whitespace_specifier = dsl::code_point.range<0x09, 0x0A>() / dsl::lit_cp<0x0D> / dsl::lit_cp<0x20>; - static constexpr auto comment_specifier = LEXY_LIT("#") >> dsl::until(dsl::newline).or_eof(); - - static constexpr auto data_specifier = - dsl::ascii::alpha_digit_underscore / - dsl::code_point.range<0x25, 0x27>() / dsl::lit_cp<0x2B> / dsl::code_point.range<0x2D, 0x2E>() / - dsl::lit_cp<0x3A> / - dsl::lit_cp<0x8A> / dsl::lit_cp<0x8C> / dsl::lit_cp<0x8E> / - dsl::lit_cp<0x92> / dsl::lit_cp<0x9A> / dsl::lit_cp<0x9C> / dsl::code_point.range<0x9E, 0x9F>() / - dsl::code_point.range<0xC0, 0xD6>() / dsl::code_point.range<0xD8, 0xF6>() / dsl::code_point.range<0xF8, 0xFF>(); - - static constexpr auto data_char_class = LEXY_CHAR_CLASS("DataSpecifier", data_specifier); - - struct Identifier { - static constexpr auto rule = dsl::identifier(data_char_class); - }; - - struct StringExpression { - static constexpr auto escaped_symbols = lexy::symbol_table<char> // - .map<'"'>('"') - .map<'\''>('\'') - .map<'\\'>('\\') - .map<'/'>('/') - .map<'b'>('\b') - .map<'f'>('\f') - .map<'n'>('\n') - .map<'r'>('\r') - .map<'t'>('\t'); - static constexpr auto rule = [] { - // Arbitrary code points that aren't control characters. - auto c = -dsl::unicode::control; - - // Escape sequences start with a backlash. - // They either map one of the symbols, - // or a Unicode code point of the form uXXXX. - auto escape = dsl::backslash_escape // - .symbol<escaped_symbols>() - .rule(dsl::lit_c<'u'> >> dsl::code_point_id<4>); - return dsl::quoted(c, escape); - }(); - }; - - struct AssignmentStatement { - static constexpr auto rule = dsl::p<Identifier> >> - (dsl::equal_sign >> - (dsl::p<Identifier> | dsl::p<StringExpression> | dsl::recurse_branch<StatementListBlock>) | - dsl::else_ >> dsl::return_); - }; - - struct StatementListBlock { - static constexpr auto rule = - dsl::curly_bracketed.open() >> - dsl::opt(dsl::list(dsl::p<AssignmentStatement>)) + dsl::opt(dsl::semicolon) + - dsl::curly_bracketed.close(); - }; - - struct File { - // Allow arbitrary spaces between individual tokens. - static constexpr auto whitespace = whitespace_specifier | comment_specifier; - - static constexpr auto rule = dsl::terminator(dsl::eof).list(dsl::p<AssignmentStatement>); - }; -} diff --git a/src/openvic-dataloader/v2script/ModifierGrammar.hpp b/src/openvic-dataloader/v2script/ModifierGrammar.hpp new file mode 100644 index 0000000..ad0704a --- /dev/null +++ b/src/openvic-dataloader/v2script/ModifierGrammar.hpp @@ -0,0 +1,33 @@ +#pragma once + +#include <openvic-dataloader/v2script/AbstractSyntaxTree.hpp> + +#include <lexy/dsl.hpp> + +#include "SimpleGrammar.hpp" +#include "TriggerGrammar.hpp" + +namespace ovdl::v2script::grammar { + constexpr auto modifier_keyword = LEXY_KEYWORD("modifier", lexy::dsl::inline_<Identifier>); + constexpr auto factor_keyword = LEXY_KEYWORD("factor", lexy::dsl::inline_<Identifier>); + + struct FactorStatement { + static constexpr auto rule = factor_keyword >> lexy::dsl::equal_sign + lexy::dsl::inline_<Identifier>; + static constexpr auto value = lexy::as_string<std::string> | lexy::new_<ast::FactorNode, ast::NodePtr>; + }; + + struct ModifierStatement { + static constexpr auto rule = + modifier_keyword >> + lexy::dsl::curly_bracketed.list( + lexy::dsl::p<FactorStatement> | + lexy::dsl::p<TriggerList>); + + static constexpr auto value = + lexy::as_list<std::vector<ast::NodePtr>> >> + lexy::callback<ast::NodePtr>( + [](auto&& list) { + return make_node_ptr<ast::ModifierNode>(LEXY_MOV(list)); + }); + }; +}
\ No newline at end of file diff --git a/src/openvic-dataloader/v2script/Parser.cpp b/src/openvic-dataloader/v2script/Parser.cpp new file mode 100644 index 0000000..07d6455 --- /dev/null +++ b/src/openvic-dataloader/v2script/Parser.cpp @@ -0,0 +1,224 @@ +#include "openvic-dataloader/v2script/Parser.hpp" + +#include <functional> +#include <iostream> +#include <memory> +#include <optional> +#include <string> +#include <utility> +#include <vector> + +#include <openvic-dataloader/ParseError.hpp> +#include <openvic-dataloader/ParseWarning.hpp> +#include <openvic-dataloader/detail/Concepts.hpp> +#include <openvic-dataloader/v2script/AbstractSyntaxTree.hpp> + +#include <lexy/action/parse.hpp> +#include <lexy/encoding.hpp> +#include <lexy/input/buffer.hpp> +#include <lexy/input/file.hpp> +#include <lexy/lexeme.hpp> +#include <lexy/visualize.hpp> + +#include "SimpleGrammar.hpp" +#include "detail/BasicBufferHandler.hpp" +#include "detail/DetectUtf8.hpp" +#include "detail/Errors.hpp" +#include "detail/LexyReportError.hpp" +#include "detail/NullBuff.hpp" +#include "detail/OStreamOutputIterator.hpp" +#include "detail/Warnings.hpp" +#include "v2script/DecisionGrammar.hpp" +#include "v2script/EventGrammar.hpp" + +using namespace ovdl; +using namespace ovdl::v2script; + +/// BufferHandler /// + +class Parser::BufferHandler final : public detail::BasicBufferHandler<> { +public: + constexpr bool is_exclusive_utf8() const { + return detail::is_utf8_no_ascii(_buffer); + } + + template<typename Node, typename ErrorCallback> + std::optional<std::vector<ParseError>> parse(const ErrorCallback& callback) { + auto result = lexy::parse<Node>(_buffer, callback); + if (!result) { + return result.errors(); + } + // This is mighty frustrating + _root = std::unique_ptr<ast::Node>(result.value()); + return std::nullopt; + } + + std::unique_ptr<ast::Node>& get_root() { + return _root; + } + +private: + std::unique_ptr<ast::Node> _root; +}; + +/// BufferHandler /// + +Parser::Parser() + : _buffer_handler(std::make_unique<BufferHandler>()) { + set_error_log_to_stderr(); +} + +Parser::Parser(Parser&&) = default; +Parser& Parser::operator=(Parser&&) = default; +Parser::~Parser() = default; + +Parser Parser::from_buffer(const char* data, std::size_t size) { + Parser result; + return std::move(result.load_from_buffer(data, size)); +} + +Parser Parser::from_buffer(const char* start, const char* end) { + Parser result; + return std::move(result.load_from_buffer(start, end)); +} + +Parser Parser::from_string(const std::string_view string) { + Parser result; + return std::move(result.load_from_string(string)); +} + +Parser Parser::from_file(const char* path) { + Parser result; + return std::move(result.load_from_file(path)); +} + +Parser Parser::from_file(const std::filesystem::path& path) { + Parser result; + return std::move(result.load_from_file(path)); +} + +/// +/// @brief Executes a function on _buffer_handler that is expected to load a buffer +/// +/// Expected Use: +/// @code {.cpp} +/// _run_load_func(&BufferHandler::<load_function>, <arguments>); +/// @endcode +/// +/// @tparam Type +/// @tparam Args +/// @param func +/// @param args +/// +template<typename... Args> +constexpr void Parser::_run_load_func(detail::LoadCallback<BufferHandler, Args...> auto func, Args... args) { + _warnings.clear(); + _errors.clear(); + _has_fatal_error = false; + if (auto error = func(_buffer_handler.get(), std::forward<Args>(args)...); error) { + _has_fatal_error = error.value().type == ParseError::Type::Fatal; + _errors.push_back(error.value()); + _error_stream.get() << "Error: " << _errors.back().message << '\n'; + } +} + +constexpr Parser& Parser::load_from_buffer(const char* data, std::size_t size) { + // Type can't be deduced? + _run_load_func(std::mem_fn(&BufferHandler::load_buffer_size), data, size); + return *this; +} + +constexpr Parser& Parser::load_from_buffer(const char* start, const char* end) { + // Type can't be deduced? + _run_load_func(std::mem_fn(&BufferHandler::load_buffer), start, end); + return *this; +} + +constexpr Parser& Parser::load_from_string(const std::string_view string) { + return load_from_buffer(string.data(), string.size()); +} + +constexpr Parser& Parser::load_from_file(const char* path) { + _file_path = path; + // Type can be deduced?? + _run_load_func(std::mem_fn(&BufferHandler::load_file), path); + return *this; +} + +Parser& Parser::load_from_file(const std::filesystem::path& path) { + return load_from_file(path.string().c_str()); +} + +constexpr Parser& Parser::load_from_file(const detail::Has_c_str auto& path) { + return load_from_file(path.c_str()); +} + +bool Parser::simple_parse() { + if (!_buffer_handler->is_valid()) { + return false; + } + + if (_buffer_handler->is_exclusive_utf8()) { + _warnings.push_back(warnings::make_utf8_warning(_file_path)); + } + + auto errors = _buffer_handler->parse<grammar::File>(ovdl::detail::ReporError.path(_file_path).to(detail::OStreamOutputIterator { _error_stream })); + if (errors) { + _errors.reserve(errors->size()); + for (auto& err : errors.value()) { + _has_fatal_error |= err.type == ParseError::Type::Fatal; + _errors.push_back(err); + } + return false; + } + _file_node.reset(static_cast<ast::FileNode*>(_buffer_handler->get_root().release())); + return true; +} + +bool Parser::event_parse() { + if (!_buffer_handler->is_valid()) { + return false; + } + + if (_buffer_handler->is_exclusive_utf8()) { + _warnings.push_back(warnings::make_utf8_warning(_file_path)); + } + + auto errors = _buffer_handler->parse<grammar::EventFile>(ovdl::detail::ReporError.path(_file_path).to(detail::OStreamOutputIterator { _error_stream })); + if (errors) { + _errors.reserve(errors->size()); + for (auto& err : errors.value()) { + _has_fatal_error |= err.type == ParseError::Type::Fatal; + _errors.push_back(err); + } + return false; + } + _file_node.reset(static_cast<ast::FileNode*>(_buffer_handler->get_root().release())); + return true; +} + +bool Parser::decision_parse() { + if (!_buffer_handler->is_valid()) { + return false; + } + + if (_buffer_handler->is_exclusive_utf8()) { + _warnings.push_back(warnings::make_utf8_warning(_file_path)); + } + + auto errors = _buffer_handler->parse<grammar::DecisionFile>(ovdl::detail::ReporError.path(_file_path).to(detail::OStreamOutputIterator { _error_stream })); + if (errors) { + _errors.reserve(errors->size()); + for (auto& err : errors.value()) { + _has_fatal_error |= err.type == ParseError::Type::Fatal; + _errors.push_back(err); + } + return false; + } + _file_node.reset(static_cast<ast::FileNode*>(_buffer_handler->get_root().release())); + return true; +} + +const FileNode* Parser::get_file_node() const { + return _file_node.get(); +}
\ No newline at end of file diff --git a/src/openvic-dataloader/v2script/SimpleGrammar.hpp b/src/openvic-dataloader/v2script/SimpleGrammar.hpp new file mode 100644 index 0000000..c91935e --- /dev/null +++ b/src/openvic-dataloader/v2script/SimpleGrammar.hpp @@ -0,0 +1,120 @@ +#pragma once + +#include <memory> +#include <string> +#include <vector> + +#include <openvic-dataloader/v2script/AbstractSyntaxTree.hpp> + +#include <lexy/callback.hpp> +#include <lexy/dsl.hpp> + +#include "detail/LexyLitRange.hpp" + +// Grammar Definitions // +namespace ovdl::v2script::grammar { + struct StatementListBlock; + + static constexpr auto whitespace_specifier = lexy::dsl::ascii::blank / lexy::dsl::ascii::newline; + static constexpr auto comment_specifier = LEXY_LIT("#") >> lexy::dsl::until(lexy::dsl::newline).or_eof(); + + static constexpr auto data_specifier = + lexy::dsl::ascii::alpha_digit_underscore / + LEXY_ASCII_ONE_OF("%&'") / lexy::dsl::lit_c<0x2B> / LEXY_ASCII_ONE_OF("-.") / + lexy::dsl::ascii::digit / lexy::dsl::lit_c<0x3A> / + lexy::dsl::lit_c<0x40> / lexy::dsl::ascii::upper / lexy::dsl::lit_c<0x5F> / + lexy::dsl::ascii::lower / lexy::dsl::lit_b<0x8A> / lexy::dsl::lit_b<0x8C> / lexy::dsl::lit_b<0x8E> / + lexy::dsl::lit_b<0x92> / lexy::dsl::lit_b<0x97> / lexy::dsl::lit_b<0x9A> / lexy::dsl::lit_b<0x9C> / lexy::dsl::lit_b<0x9E> / lexy::dsl::lit_b<0x9F> / + lexy::dsl::lit_b<0xC0> / + ovdl::detail::lexydsl::make_range<0xC0, 0xD6>() / ovdl::detail::lexydsl::make_range<0xD8, 0xF6>() / ovdl::detail::lexydsl::make_range<0xF8, 0xFF>(); + + static constexpr auto data_char_class = LEXY_CHAR_CLASS("DataSpecifier", data_specifier); + + struct Identifier { + static constexpr auto rule = lexy::dsl::identifier(data_char_class); + static constexpr auto value = lexy::as_string<std::string> | lexy::new_<ast::IdentifierNode, ast::NodePtr>; + }; + + struct StringExpression { + static constexpr auto escaped_symbols = lexy::symbol_table<char> // + .map<'"'>('"') + .map<'\''>('\'') + .map<'\\'>('\\') + .map<'/'>('/') + .map<'b'>('\b') + .map<'f'>('\f') + .map<'n'>('\n') + .map<'r'>('\r') + .map<'t'>('\t'); + static constexpr auto rule = [] { + // Arbitrary code points that aren't control characters. + auto c = ovdl::detail::lexydsl::make_range<0x20, 0xFF>() - lexy::dsl::ascii::control; + + // Escape sequences start with a backlash. + // They either map one of the symbols, + // or a Unicode code point of the form uXXXX. + auto escape = lexy::dsl::backslash_escape // + .symbol<escaped_symbols>(); + return lexy::dsl::quoted(c, escape); + }(); + + static constexpr auto value = lexy::as_string<std::string> >> lexy::new_<ast::StringNode, ast::NodePtr>; + }; + + struct SimpleAssignmentStatement { + static constexpr auto rule = + lexy::dsl::p<Identifier> >> + lexy::dsl::equal_sign + + (lexy::dsl::p<Identifier> | lexy::dsl::p<StringExpression> | lexy::dsl::recurse_branch<StatementListBlock>); + + static constexpr auto value = lexy::callback<ast::NodePtr>( + [](auto name, auto&& initalizer) { + return make_node_ptr<ast::AssignNode>(LEXY_MOV(name), LEXY_MOV(initalizer)); + }); + }; + + struct AssignmentStatement { + static constexpr auto rule = + lexy::dsl::p<Identifier> >> + (lexy::dsl::equal_sign >> + (lexy::dsl::p<Identifier> | lexy::dsl::p<StringExpression> | lexy::dsl::recurse_branch<StatementListBlock>) | + lexy::dsl::else_ >> lexy::dsl::return_) | + lexy::dsl::p<StringExpression>; + + static constexpr auto value = lexy::callback<ast::NodePtr>( + [](auto name, lexy::nullopt = {}) { + return LEXY_MOV(name); + }, + [](auto name, auto&& initalizer) { + return make_node_ptr<ast::AssignNode>(LEXY_MOV(name), LEXY_MOV(initalizer)); + }); + }; + + struct StatementListBlock { + static constexpr auto rule = + lexy::dsl::curly_bracketed( + lexy::dsl::opt(lexy::dsl::list(lexy::dsl::p<AssignmentStatement>)) + lexy::dsl::opt(lexy::dsl::semicolon)); + + static constexpr auto value = + lexy::as_list<std::vector<ast::NodePtr>> >> + lexy::callback<ast::NodePtr>( + [](lexy::nullopt = {}, lexy::nullopt = {}) { + return ast::make_node_ptr<ast::ListNode>(); + }, + [](auto&& list, lexy::nullopt = {}) { + return make_node_ptr<ast::ListNode>(LEXY_MOV(list)); + }, + [](auto& list) { + return make_node_ptr<ast::ListNode>(list); + }); + }; + + struct File { + // Allow arbitrary spaces between individual tokens. + static constexpr auto whitespace = whitespace_specifier | comment_specifier; + + static constexpr auto rule = lexy::dsl::terminator(lexy::dsl::eof).list(lexy::dsl::p<AssignmentStatement>); + + static constexpr auto value = lexy::as_list<std::vector<ast::NodePtr>> >> lexy::new_<ast::FileNode, ast::NodePtr>; + }; +} diff --git a/src/openvic-dataloader/v2script/TriggerGrammar.hpp b/src/openvic-dataloader/v2script/TriggerGrammar.hpp new file mode 100644 index 0000000..290fb70 --- /dev/null +++ b/src/openvic-dataloader/v2script/TriggerGrammar.hpp @@ -0,0 +1,42 @@ +#pragma once + +#include <openvic-dataloader/v2script/AbstractSyntaxTree.hpp> + +#include <lexy/callback.hpp> +#include <lexy/dsl.hpp> + +#include "SimpleGrammar.hpp" + +namespace ovdl::v2script::grammar { + struct TriggerStatement { + static constexpr auto rule = lexy::dsl::inline_<SimpleAssignmentStatement>; + + static constexpr auto value = lexy::callback<ast::NodePtr>( + [](auto name, auto&& initalizer) { + return ast::make_node_ptr<ast::ExecutionNode>(ast::ExecutionNode::Type::Trigger, LEXY_MOV(name), LEXY_MOV(initalizer)); + }); + }; + + struct TriggerList { + static constexpr auto rule = lexy::dsl::list(lexy::dsl::p<SimpleAssignmentStatement>); + + static constexpr auto value = + lexy::as_list<std::vector<ast::NodePtr>> >> + lexy::callback<ast::NodePtr>( + [](auto&& list) { + return ast::make_node_ptr<ast::ExecutionListNode>(ast::ExecutionNode::Type::Trigger, LEXY_MOV(list)); + }); + }; + + struct TriggerBlock { + static constexpr auto rule = lexy::dsl::curly_bracketed.opt(lexy::dsl::p<TriggerList>); + + static constexpr auto value = lexy::callback<ast::NodePtr>( + [](auto&& list) { + return LEXY_MOV(list); + }, + [](lexy::nullopt = {}) { + return lexy::nullopt {}; + }); + }; +}
\ No newline at end of file |