ASE/src/refactory_scripts/loaders/ts_pini_loader.py

"""
TS Pini (Total Station) data loader - Refactored version with async support.

This script processes Total Station survey data from multiple instrument types
(Leica, Trimble S7, S9) and manages complex monitoring with multi-level alarms.

**STATUS**: Essential refactoring - Base structure with coordinate transformations.
**TODO**: Complete alarm management, threshold checking, and additional monitoring.

Replaces the legacy TS_PiniScript.py (2,587 lines) with a modular, maintainable architecture.
"""

import asyncio
import logging
import sys
from datetime import datetime
from enum import IntEnum
from pathlib import Path

import utm
from pyproj import Transformer

from refactory_scripts.config import DatabaseConfig
from refactory_scripts.utils import execute_query, get_db_connection

logger = logging.getLogger(__name__)


class StationType(IntEnum):
    """Total Station instrument types."""

    LEICA = 1
    TRIMBLE_S7 = 4
    TRIMBLE_S9 = 7
    TRIMBLE_S7_INVERTED = 10  # x-y coordinates inverted


class CoordinateSystem(IntEnum):
    """Coordinate system types for transformations."""

    CH1903 = 6  # Swiss coordinate system (old)
    UTM = 7  # Universal Transverse Mercator
    CH1903_PLUS = 10  # Swiss coordinate system LV95 (new)
    LAT_LON = 0  # Default: already in lat/lon


class TSPiniLoader:
    """
    Loads Total Station Pini survey data with coordinate transformations and alarm management.

    This loader handles:
    - Multiple station types (Leica, Trimble S7/S9)
    - Coordinate system transformations (CH1903, UTM, lat/lon)
    - Target point (mira) management
    - Multi-level alarm system (TODO: complete implementation)
    - Additional monitoring for railways, walls, trusses (TODO)
    """

    # Folder name mappings for special cases
    FOLDER_MAPPINGS = {
        "[276_208_TS0003]": "TS0003",
        "[Neuchatel_CDP]": "TS7",
        "[TS0006_EP28]": "TS0006_EP28",
        "[TS0007_ChesaArcoiris]": "TS0007_ChesaArcoiris",
        "[TS0006_EP28_3]": "TS0006_EP28_3",
        "[TS0006_EP28_4]": "TS0006_EP28_4",
        "[TS0006_EP28_5]": "TS0006_EP28_5",
        "[TS18800]": "TS18800",
        "[Granges_19 100]": "Granges_19 100",
        "[Granges_19 200]": "Granges_19 200",
        "[Chesa_Arcoiris_2]": "Chesa_Arcoiris_2",
        "[TS0006_EP28_1]": "TS0006_EP28_1",
        "[TS_PS_Petites_Croisettes]": "TS_PS_Petites_Croisettes",
        "[_Chesa_Arcoiris_1]": "_Chesa_Arcoiris_1",
        "[TS_test]": "TS_test",
        "[TS-VIME]": "TS-VIME",
    }

    def __init__(self, db_config: DatabaseConfig):
        """
        Initialize the TS Pini loader.

        Args:
            db_config: Database configuration object
        """
        self.db_config = db_config
        self.conn = None

    async def __aenter__(self):
        """Async context manager entry."""
        self.conn = await get_db_connection(self.db_config.as_dict())
        return self

    async def __aexit__(self, exc_type, exc_val, exc_tb):
        """Async context manager exit."""
        if self.conn:
            self.conn.close()

    def _extract_folder_name(self, file_path: Path) -> str:
        """
        Extract and normalize folder name from file path.

        Handles special folder name mappings for specific projects.

        Args:
            file_path: Path to the CSV file

        Returns:
            Normalized folder name
        """
        # Get folder name from path
        folder_name = file_path.parent.name

        # Check for special mappings in filename
        filename = file_path.name
        for pattern, mapped_name in self.FOLDER_MAPPINGS.items():
            if pattern in filename:
                logger.debug(f"Mapped folder: {pattern} -> {mapped_name}")
                return mapped_name

        return folder_name

    async def _get_project_info(self, folder_name: str) -> dict | None:
        """
        Get project information from database based on folder name.

        Args:
            folder_name: Folder/station name

        Returns:
            Dictionary with project info or None if not found
        """
        query = """
            SELECT
                l.id as lavoro_id,
                s.id as site_id,
                st.type_id,
                s.upgeo_sist_coordinate,
                s.upgeo_utmzone,
                s.upgeo_utmhemisphere
            FROM upgeo_st as st
            LEFT JOIN upgeo_lavori as l ON st.lavoro_id = l.id
            LEFT JOIN sites as s ON s.id = l.site_id
            WHERE st.name = %s
        """

        result = await execute_query(self.conn, query, (folder_name,), fetch_one=True)

        if not result:
            logger.error(f"Project not found for folder: {folder_name}")
            return None

        return {
            "lavoro_id": result["lavoro_id"],
            "site_id": result["site_id"],
            "station_type": result["type_id"],
            "coordinate_system": int(result["upgeo_sist_coordinate"]),
            "utm_zone": result["upgeo_utmzone"],
            "utm_hemisphere": result["upgeo_utmhemisphere"] != "S",  # True for North
        }

    def _parse_csv_row(self, row: list[str], station_type: int) -> tuple[str, str, str, str, str]:
        """
        Parse CSV row based on station type.

        Different station types have different column orders.

        Args:
            row: List of CSV values
            station_type: Station type identifier

        Returns:
            Tuple of (mira_name, easting, northing, height, timestamp)
        """
        if station_type == StationType.LEICA:
            # Leica format: name, easting, northing, height, timestamp
            mira_name = row[0]
            easting = row[1]
            northing = row[2]
            height = row[3]
            # Convert timestamp: DD.MM.YYYY HH:MM:SS.fff -> YYYY-MM-DD HH:MM:SS
            timestamp = datetime.strptime(row[4], "%d.%m.%Y %H:%M:%S.%f").strftime("%Y-%m-%d %H:%M:%S")

        elif station_type in (StationType.TRIMBLE_S7, StationType.TRIMBLE_S9):
            # Trimble S7/S9 format: timestamp, name, northing, easting, height
            timestamp = row[0]
            mira_name = row[1]
            northing = row[2]
            easting = row[3]
            height = row[4]

        elif station_type == StationType.TRIMBLE_S7_INVERTED:
            # Trimble S7 inverted: timestamp, name, easting(row[2]), northing(row[3]), height
            timestamp = row[0]
            mira_name = row[1]
            northing = row[3]  # Inverted!
            easting = row[2]  # Inverted!
            height = row[4]

        else:
            raise ValueError(f"Unknown station type: {station_type}")

        return mira_name, easting, northing, height, timestamp

    def _transform_coordinates(
        self, easting: float, northing: float, coord_system: int, utm_zone: str = None, utm_hemisphere: bool = True
    ) -> tuple[float, float]:
        """
        Transform coordinates to lat/lon based on coordinate system.

        Args:
            easting: Easting coordinate
            northing: Northing coordinate
            coord_system: Coordinate system type
            utm_zone: UTM zone (required for UTM system)
            utm_hemisphere: True for Northern, False for Southern

        Returns:
            Tuple of (latitude, longitude)
        """
        if coord_system == CoordinateSystem.CH1903:
            # Old Swiss coordinate system transformation
            y = easting
            x = northing
            y_ = (y - 2600000) / 1000000
            x_ = (x - 1200000) / 1000000

            lambda_ = 2.6779094 + 4.728982 * y_ + 0.791484 * y_ * x_ + 0.1306 * y_ * x_**2 - 0.0436 * y_**3
            phi_ = 16.9023892 + 3.238272 * x_ - 0.270978 * y_**2 - 0.002528 * x_**2 - 0.0447 * y_**2 * x_ - 0.0140 * x_**3

            lat = phi_ * 100 / 36
            lon = lambda_ * 100 / 36

        elif coord_system == CoordinateSystem.UTM:
            # UTM to lat/lon
            if not utm_zone:
                raise ValueError("UTM zone required for UTM coordinate system")

            result = utm.to_latlon(easting, northing, utm_zone, northern=utm_hemisphere)
            lat = result[0]
            lon = result[1]

        elif coord_system == CoordinateSystem.CH1903_PLUS:
            # New Swiss coordinate system (LV95) using EPSG:21781 -> EPSG:4326
            transformer = Transformer.from_crs("EPSG:21781", "EPSG:4326")
            lat, lon = transformer.transform(easting, northing)

        else:
            # Already in lat/lon
            lon = easting
            lat = northing

        logger.debug(f"Transformed coordinates: ({easting}, {northing}) -> ({lat:.6f}, {lon:.6f})")
        return lat, lon

    async def _get_or_create_mira(self, mira_name: str, lavoro_id: int) -> int | None:
        """
        Get existing mira (target point) ID or create new one if allowed.

        Args:
            mira_name: Name of the target point
            lavoro_id: Project ID

        Returns:
            Mira ID or None if creation not allowed
        """
        # Check if mira exists
        query = """
            SELECT m.id as mira_id, m.name
            FROM upgeo_mire as m
            JOIN upgeo_lavori as l ON m.lavoro_id = l.id
            WHERE m.name = %s AND m.lavoro_id = %s
        """

        result = await execute_query(self.conn, query, (mira_name, lavoro_id), fetch_one=True)

        if result:
            return result["mira_id"]

        # Mira doesn't exist - check if we can create it
        logger.info(f"Mira '{mira_name}' not found, attempting to create...")

        # TODO: Implement mira creation logic
        # This requires checking company limits and updating counters
        # For now, return None to skip
        logger.warning("Mira creation not yet implemented in refactored version")
        return None

    async def _insert_survey_data(
        self,
        mira_id: int,
        timestamp: str,
        northing: float,
        easting: float,
        height: float,
        lat: float,
        lon: float,
        coord_system: int,
    ) -> bool:
        """
        Insert survey data into ELABDATAUPGEO table.

        Args:
            mira_id: Target point ID
            timestamp: Survey timestamp
            northing: Northing coordinate
            easting: Easting coordinate
            height: Elevation
            lat: Latitude
            lon: Longitude
            coord_system: Coordinate system type

        Returns:
            True if insert was successful
        """
        query = """
            INSERT IGNORE INTO ELABDATAUPGEO
            (mira_id, EventTimestamp, north, east, elevation, lat, lon, sist_coordinate)
            VALUES (%s, %s, %s, %s, %s, %s, %s, %s)
        """

        params = (mira_id, timestamp, northing, easting, height, lat, lon, coord_system)

        try:
            await execute_query(self.conn, query, params)
            logger.debug(f"Inserted survey data for mira_id {mira_id} at {timestamp}")
            return True
        except Exception as e:
            logger.error(f"Failed to insert survey data: {e}")
            return False

    async def _process_thresholds_and_alarms(self, lavoro_id: int, processed_miras: list[int]) -> None:
        """
        Process thresholds and create alarms for monitored points.

        **TODO**: This is a stub for the complex alarm system.
        The complete implementation requires:
        - Multi-level threshold checking (3 levels: attention, intervention, immediate)
        - 5 dimensions: N, E, H, R2D, R3D
        - Email and SMS notifications
        - Time-series analysis
        - Railway/wall/truss specific monitoring

        Args:
            lavoro_id: Project ID
            processed_miras: List of mira IDs that were processed
        """
        logger.warning("Threshold and alarm processing is not yet implemented")
        logger.info(f"Would process alarms for {len(processed_miras)} miras in lavoro {lavoro_id}")

        # TODO: Implement alarm system
        # 1. Load threshold configurations from upgeo_lavori and upgeo_mire tables
        # 2. Query latest survey data for each mira
        # 3. Calculate displacements (N, E, H, R2D, R3D)
        # 4. Check against 3-level thresholds
        # 5. Create alarms if thresholds exceeded
        # 6. Handle additional monitoring (railways, walls, trusses)

    async def process_file(self, file_path: str | Path) -> bool:
        """
        Process a Total Station CSV file and load data into the database.

        **Current Implementation**: Core data loading with coordinate transformations.
        **TODO**: Complete alarm and additional monitoring implementation.

        Args:
            file_path: Path to the CSV file to process

        Returns:
            True if processing was successful, False otherwise
        """
        file_path = Path(file_path)

        if not file_path.exists():
            logger.error(f"File not found: {file_path}")
            return False

        try:
            logger.info(f"Processing Total Station file: {file_path.name}")

            # Extract folder name
            folder_name = self._extract_folder_name(file_path)
            logger.info(f"Station/Project: {folder_name}")

            # Get project information
            project_info = await self._get_project_info(folder_name)
            if not project_info:
                return False

            station_type = project_info["station_type"]
            coord_system = project_info["coordinate_system"]
            lavoro_id = project_info["lavoro_id"]

            logger.info(f"Station type: {station_type}, Coordinate system: {coord_system}")

            # Read and parse CSV file
            with open(file_path, encoding="utf-8") as f:
                lines = [line.rstrip() for line in f.readlines()]

            # Skip header
            if lines:
                lines = lines[1:]

            processed_count = 0
            processed_miras = []

            # Process each survey point
            for line in lines:
                if not line:
                    continue

                row = line.split(",")

                try:
                    # Parse row based on station type
                    mira_name, easting, northing, height, timestamp = self._parse_csv_row(row, station_type)

                    # Transform coordinates to lat/lon
                    lat, lon = self._transform_coordinates(
                        float(easting),
                        float(northing),
                        coord_system,
                        project_info.get("utm_zone"),
                        project_info.get("utm_hemisphere"),
                    )

                    # Get or create mira
                    mira_id = await self._get_or_create_mira(mira_name, lavoro_id)

                    if not mira_id:
                        logger.warning(f"Skipping mira '{mira_name}' - not found and creation not allowed")
                        continue

                    # Insert survey data
                    success = await self._insert_survey_data(
                        mira_id, timestamp, float(northing), float(easting), float(height), lat, lon, coord_system
                    )

                    if success:
                        processed_count += 1
                        if mira_id not in processed_miras:
                            processed_miras.append(mira_id)

                except Exception as e:
                    logger.error(f"Failed to process row: {e}")
                    logger.debug(f"Row data: {row}")
                    continue

            logger.info(f"Processed {processed_count} survey points for {len(processed_miras)} miras")

            # Process thresholds and alarms (TODO: complete implementation)
            if processed_miras:
                await self._process_thresholds_and_alarms(lavoro_id, processed_miras)

            return True

        except Exception as e:
            logger.error(f"Failed to process file {file_path}: {e}", exc_info=True)
            return False


async def main(file_path: str):
    """
    Main entry point for the TS Pini loader.

    Args:
        file_path: Path to the CSV file to process
    """
    # Setup logging
    logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s")

    logger.info("TS Pini Loader started")
    logger.info(f"Processing file: {file_path}")
    logger.warning("NOTE: Alarm system not yet fully implemented in this refactored version")

    try:
        # Load configuration
        db_config = DatabaseConfig()

        # Process file
        async with TSPiniLoader(db_config) as loader:
            success = await loader.process_file(file_path)

        if success:
            logger.info("Processing completed successfully")
            return 0
        else:
            logger.error("Processing failed")
            return 1

    except Exception as e:
        logger.error(f"Unexpected error: {e}", exc_info=True)
        return 1

    finally:
        logger.info("TS Pini Loader finished")


if __name__ == "__main__":
    if len(sys.argv) < 2:
        print("Usage: python ts_pini_loader.py <path_to_csv_file>")
        print("\nNOTE: This is an essential refactoring of the legacy TS_PiniScript.py")
        print("      Core functionality (data loading, coordinates) is implemented.")
        print("      Alarm system and additional monitoring require completion.")
        sys.exit(1)

    exit_code = asyncio.run(main(sys.argv[1]))
    sys.exit(exit_code)