aboutsummaryrefslogtreecommitdiff
path: root/include/openvic-dataloader/csv
diff options
context:
space:
mode:
author Spartan322 <Megacake1234@gmail.com>2023-07-28 06:52:00 +0200
committer Spartan322 <Megacake1234@gmail.com>2023-09-02 14:28:21 +0200
commit7440a5d1433eec4bf87e3723022db187e7f61b1a (patch)
tree2bb062c320fa2227b18956617b94d0e8800420d8 /include/openvic-dataloader/csv
parente941573f47fb867ff75c8a2cf78302b754ffbeee (diff)
Rework Grammar and Parser
Add proper headless binary construction: Includes basic validation 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 to v2script Add proper Grammar value retrieval Add AbstractSyntaxTree for v2script data parser: Has compile-time embedded type information accessible at compile-time and runtime Has Tab-based print functionality Fix wrong environment reference for headless construction in SConstruct Add error retrieval Add BasicCallbackOStreamBuffer for callback streaming Add CallbackStreamBuffer for char Add CallbackWStreamBuffer for wchar_t Add BasicCallbackStream Add CallbackStream for char Add CallbackWStream for wchar_t Add grammar for events and decisions Add event_parse to Parser Add decision_parse to Parser Add .clang-format Ignore dirty lexy module Add CSV parser and grammar: Creates std::vector<csv::LineObject> for a list of lines Add BasicParser and BasicBufferHandler to reduce code reduplication
Diffstat (limited to 'include/openvic-dataloader/csv')
-rw-r--r--include/openvic-dataloader/csv/LineObject.hpp84
-rw-r--r--include/openvic-dataloader/csv/Parser.hpp42
2 files changed, 126 insertions, 0 deletions
diff --git a/include/openvic-dataloader/csv/LineObject.hpp b/include/openvic-dataloader/csv/LineObject.hpp
new file mode 100644
index 0000000..0494ffb
--- /dev/null
+++ b/include/openvic-dataloader/csv/LineObject.hpp
@@ -0,0 +1,84 @@
+#pragma once
+
+#include <cstddef>
+#include <cstdint>
+#include <functional>
+#include <initializer_list>
+#include <optional>
+#include <string>
+#include <string_view>
+#include <tuple>
+#include <vector>
+
+namespace ovdl::csv {
+ /// LineObject should be able to recognize the differences between:
+ /// Input -> Indexes == ""
+ /// ;;a;b;c;; -> 0,1,5,6+ == ""
+ /// a;b;c -> 3+ == ""
+ /// a;;b;c;; -> 1,4,5+ == ""
+ /// a;b;;c; -> 2,4+ == ""
+ /// a;b;c;; -> 3,4+ == ""
+ /// a;b;c; -> 3+ == ""
+ /// ;a;b;c -> 0,4+ == ""
+ ///
+ /// If this is incorrect, please report an issue.
+ class LineObject final : public std::vector<std::tuple<std::uint32_t, std::string>> {
+ public:
+ // Stored position of value
+ using position_type = std::uint32_t;
+ // Value
+ using inner_value_type = std::string;
+ using container_type = std::vector<std::tuple<position_type, inner_value_type>>;
+
+ constexpr LineObject() = default;
+ constexpr LineObject(LineObject&) = default;
+ constexpr LineObject(LineObject&&) = default;
+ constexpr LineObject(const LineObject&) = default;
+
+ constexpr LineObject& operator=(const LineObject& other) = default;
+ constexpr LineObject& operator=(LineObject&& other) = default;
+
+ constexpr ~LineObject() = default;
+
+ constexpr LineObject(std::initializer_list<value_type> pos_and_val) : container_type(pos_and_val) {
+ }
+
+ constexpr LineObject(position_type prefix_end, std::initializer_list<value_type> pos_and_val, position_type suffix_end = 0)
+ : container_type(pos_and_val),
+ _prefix_end(prefix_end),
+ _suffix_end(suffix_end) {
+ }
+
+ /// Special Functionality
+ /// Retrieves value, produces "" for empty values
+ constexpr std::string_view get_value_for(std::size_t position) const {
+ if (position <= _prefix_end || position >= _suffix_end) return "";
+ for (const auto& [pos, val] : *this) {
+ if (pos == position) return val;
+ }
+ return "";
+ }
+ /// Tries to retrieve reference, produces nullopt for empty values
+ constexpr std::optional<const std::reference_wrapper<const std::string>> try_get_string_at(std::size_t position) const {
+ if (position <= _prefix_end || position > _suffix_end) return std::nullopt;
+ for (const auto& [pos, val] : *this) {
+ if (pos == position) return std::cref(val);
+ }
+ return std::nullopt;
+ }
+
+ constexpr position_type prefix_end() const { return _prefix_end; }
+ constexpr void set_prefix_end(position_type value) { _prefix_end = value; }
+
+ constexpr position_type suffix_end() const { return _suffix_end; }
+ constexpr void set_suffix_end(position_type value) { _suffix_end = value; }
+
+ constexpr std::size_t value_count() const { return _suffix_end; }
+
+ private:
+ // Should be position of first valid value on line
+ position_type _prefix_end;
+ // Should be position after last value or position after last seperator
+ position_type _suffix_end;
+ };
+} \ No newline at end of file
diff --git a/include/openvic-dataloader/csv/Parser.hpp b/include/openvic-dataloader/csv/Parser.hpp
new file mode 100644
index 0000000..3497864
--- /dev/null
+++ b/include/openvic-dataloader/csv/Parser.hpp
@@ -0,0 +1,42 @@
+#pragma once
+
+#include <openvic-dataloader/csv/LineObject.hpp>
+#include <openvic-dataloader/detail/BasicParser.hpp>
+
+namespace ovdl::csv {
+ class Parser final : public detail::BasicParser {
+ public:
+ Parser();
+
+ static Parser from_buffer(const char* data, std::size_t size);
+ static Parser from_buffer(const char* start, const char* end);
+ static Parser from_string(const std::string_view string);
+ static Parser from_file(const char* path);
+ static Parser from_file(const std::filesystem::path& path);
+
+ constexpr Parser& load_from_buffer(const char* data, std::size_t size);
+ constexpr Parser& load_from_buffer(const char* start, const char* end);
+ constexpr Parser& load_from_string(const std::string_view string);
+ constexpr Parser& load_from_file(const char* path);
+ Parser& load_from_file(const std::filesystem::path& path);
+
+ constexpr Parser& load_from_file(const detail::Has_c_str auto& path);
+
+ bool parse_csv();
+
+ const std::vector<csv::LineObject> get_lines() const;
+
+ Parser(Parser&&);
+ Parser& operator=(Parser&&);
+
+ ~Parser();
+
+ private:
+ class BufferHandler;
+ std::unique_ptr<BufferHandler> _buffer_handler;
+ std::vector<csv::LineObject> _lines;
+
+ template<typename... Args>
+ constexpr void _run_load_func(detail::LoadCallback<BufferHandler, Args...> auto func, Args... args);
+ };
+} \ No newline at end of file