Astrape/gibil/classes/weather/builder.py

from __future__ import annotations

from datetime import date, datetime, timezone
from typing import Any
from urllib.parse import urlencode
from urllib.request import urlopen
import json

from gibil.classes.models import (
    WeatherForecastPoint,
    WeatherForecastRun,
    WeatherResolvedTruth,
)


class OpenMeteoClient:
    """Fetches external weather forecasts from Open-Meteo."""

    base_url = "https://api.open-meteo.com/v1/forecast"

    def build_url(
        self,
        latitude: float,
        longitude: float,
        forecast_hours: int = 48,
        timezone_name: str = "UTC",
    ) -> str:
        params = {
            "latitude": latitude,
            "longitude": longitude,
            "hourly": ",".join(
                [
                    "temperature_2m",
                    "shortwave_radiation",
                    "cloud_cover",
                ]
            ),
            "forecast_hours": forecast_hours,
            "timezone": timezone_name,
        }
        return f"{self.base_url}?{urlencode(params)}"

    def fetch_forecast(
        self,
        latitude: float,
        longitude: float,
        forecast_hours: int = 48,
    ) -> WeatherForecastRun:
        url = self.build_url(latitude, longitude, forecast_hours)
        with urlopen(url, timeout=10) as response:
            payload = json.loads(response.read().decode("utf-8"))

        return OpenMeteoParser().parse_forecast(
            payload=payload,
            latitude=latitude,
            longitude=longitude,
            issued_at=datetime.now(timezone.utc),
        )


class OpenMeteoArchiveClient:
    """Fetches historical weather data from Open-Meteo archive."""

    base_url = "https://archive-api.open-meteo.com/v1/archive"

    def build_url(
        self,
        latitude: float,
        longitude: float,
        start_date: date,
        end_date: date,
        timezone_name: str = "UTC",
    ) -> str:
        params = {
            "latitude": latitude,
            "longitude": longitude,
            "start_date": start_date.isoformat(),
            "end_date": end_date.isoformat(),
            "hourly": ",".join(
                [
                    "temperature_2m",
                    "shortwave_radiation",
                    "cloud_cover",
                ]
            ),
            "timezone": timezone_name,
        }
        return f"{self.base_url}?{urlencode(params)}"

    def fetch_resolved_truth(
        self,
        latitude: float,
        longitude: float,
        start_date: date,
        end_date: date,
    ) -> list[WeatherResolvedTruth]:
        url = self.build_url(latitude, longitude, start_date, end_date)
        with urlopen(url, timeout=20) as response:
            payload = json.loads(response.read().decode("utf-8"))

        return OpenMeteoArchiveParser().parse_resolved_truth(payload)


class OpenMeteoParser:
    """Converts Open-Meteo JSON into clean external forecast records."""

    def parse_forecast(
        self,
        payload: dict[str, Any],
        latitude: float,
        longitude: float,
        issued_at: datetime,
    ) -> WeatherForecastRun:
        hourly = payload.get("hourly", {})
        times = hourly.get("time", [])
        temperatures = hourly.get("temperature_2m", [])
        radiation = hourly.get("shortwave_radiation", [])
        cloud_cover = hourly.get("cloud_cover", [])

        points: list[WeatherForecastPoint] = []
        for index, raw_time in enumerate(times):
            target_at = self._parse_time(raw_time)
            horizon_hours = max(
                0, round((target_at - issued_at).total_seconds() / 3600)
            )

            points.append(
                WeatherForecastPoint(
                    issued_at=issued_at,
                    target_at=target_at,
                    horizon_hours=horizon_hours,
                    temperature_c=self._at(temperatures, index),
                    shortwave_radiation_w_m2=self._at(radiation, index),
                    cloud_cover_pct=self._at(cloud_cover, index),
                )
            )

        return WeatherForecastRun(
            issued_at=issued_at,
            source="open_meteo",
            latitude=latitude,
            longitude=longitude,
            points=points,
        )

    def _parse_time(self, raw_time: str) -> datetime:
        parsed = datetime.fromisoformat(raw_time)
        if parsed.tzinfo is None:
            return parsed.replace(tzinfo=timezone.utc)
        return parsed.astimezone(timezone.utc)

    def _at(self, values: list[Any], index: int) -> float | None:
        if index >= len(values):
            return None

        value = values[index]
        if value is None:
            return None

        return float(value)


class OpenMeteoArchiveParser:
    """Converts Open-Meteo archive JSON into resolved truth records."""

    def parse_resolved_truth(self, payload: dict[str, Any]) -> list[WeatherResolvedTruth]:
        hourly = payload.get("hourly", {})
        times = hourly.get("time", [])
        temperatures = hourly.get("temperature_2m", [])
        radiation = hourly.get("shortwave_radiation", [])
        cloud_cover = hourly.get("cloud_cover", [])

        truth: list[WeatherResolvedTruth] = []
        for index, raw_time in enumerate(times):
            truth.append(
                WeatherResolvedTruth(
                    resolved_at=self._parse_time(raw_time),
                    temperature_c=self._at(temperatures, index),
                    shortwave_radiation_w_m2=self._at(radiation, index),
                    cloud_cover_pct=self._at(cloud_cover, index),
                    source="open_meteo_archive",
                )
            )

        return truth

    def _parse_time(self, raw_time: str) -> datetime:
        parsed = datetime.fromisoformat(raw_time)
        if parsed.tzinfo is None:
            return parsed.replace(tzinfo=timezone.utc)
        return parsed.astimezone(timezone.utc)

    def _at(self, values: list[Any], index: int) -> float | None:
        if index >= len(values):
            return None

        value = values[index]
        if value is None:
            return None

        return float(value)


class WeatherBuilder:
    """Builds a clean database-ready set of external weather forecast records."""

    def build_forecast_run(
        self,
        source: str,
        latitude: float,
        longitude: float,
        points: list[WeatherForecastPoint],
        issued_at: datetime | None = None,
    ) -> WeatherForecastRun:
        if issued_at is None:
            issued_at = datetime.now(timezone.utc)

        clean_points = [
            WeatherForecastPoint(
                issued_at=issued_at,
                target_at=point.target_at,
                horizon_hours=max(
                    0, round((point.target_at - issued_at).total_seconds() / 3600)
                ),
                temperature_c=point.temperature_c,
                shortwave_radiation_w_m2=point.shortwave_radiation_w_m2,
                cloud_cover_pct=point.cloud_cover_pct,
                source=source,
            )
            for point in sorted(points, key=lambda item: item.target_at)
        ]

        return WeatherForecastRun(
            issued_at=issued_at,
            source=source,
            latitude=latitude,
            longitude=longitude,
            points=clean_points,
        )

    def points_for_horizon(
        self,
        forecast_runs: list[WeatherForecastRun],
        horizon_hours: int,
    ) -> list[WeatherForecastPoint]:
        points: list[WeatherForecastPoint] = []
        for run in forecast_runs:
            points.extend(
                point
                for point in run.points
                if point.horizon_hours == horizon_hours
            )

        return sorted(points, key=lambda point: point.target_at)