# ============================================================
# Project: EDGAR Research Database
# Description: SEC EDGAR Research Infrastructure
#
# Authors:
# - Manel Kammoun — manel.kammoun@uqo.ca
# - Djerrycharli Tandjambianda — djerrycharli.tandjambianda@uqo.ca
# - Simon-Pierre Boucher — simon-pierre.boucher@uqo.ca
#
# Institution:
# Université du Québec en Outaouais (UQO)
#
# License:
# Research / Academic Use
# ============================================================

from __future__ import annotations

from abc import ABC, abstractmethod
from datetime import datetime
from pathlib import Path
from typing import TYPE_CHECKING

import pandas as pd

from src.utils.constants import PROJECT_ROOT
from src.utils.logging import get_logger

if TYPE_CHECKING:
    from src.embeddings.manager import EmbeddingManager
    from src.search.semantic import SemanticSearch
    from src.storage.database import DatabaseManager

logger = get_logger("research.base")


class ResearchModule(ABC):

    def __init__(
        self,
        db: DatabaseManager,
        embedding_manager: EmbeddingManager | None = None,
        search: SemanticSearch | None = None,
    ) -> None:
        self.db = db
        self.emb = embedding_manager
        self.search = search

    @property
    @abstractmethod
    def name(self) -> str: ...

    @property
    @abstractmethod
    def description(self) -> str: ...

    @abstractmethod
    def compute(
        self,
        tickers: list[str] | None = None,
        start_year: int | None = None,
        end_year: int | None = None,
    ) -> pd.DataFrame: ...

    def save_results(
        self,
        results: pd.DataFrame,
        output_dir: Path | None = None,
    ) -> None:
        if output_dir is None:
            output_dir = PROJECT_ROOT / "outputs" / self.name

        output_dir.mkdir(parents=True, exist_ok=True)
        timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")

        parquet_path = output_dir / f"{timestamp}.parquet"
        csv_path = output_dir / f"{timestamp}.csv"

        results.to_parquet(parquet_path, index=False, compression="zstd")
        results.to_csv(csv_path, index=False)

        logger.info(
            "Saved %d rows for module '%s' to %s",
            len(results), self.name, output_dir,
        )

    def load_results(self, output_dir: Path | None = None) -> pd.DataFrame:
        if output_dir is None:
            output_dir = PROJECT_ROOT / "outputs" / self.name

        parquet_files = sorted(output_dir.glob("*.parquet"))
        if not parquet_files:
            raise FileNotFoundError(
                f"No results found for module '{self.name}' in {output_dir}"
            )

        latest = parquet_files[-1]
        logger.info("Loading results from %s", latest)
        return pd.read_parquet(latest)