"""Yahoo Finance client for market benchmark data."""

from __future__ import annotations

import pandas as pd
import yfinance as yf

from src.config import DATA_RAW_YAHOO, YAHOO_END, YAHOO_START, YAHOO_TICKERS
from src.utils import setup_logging

logger = setup_logging("yahoo")


def fetch_yahoo_data(
    tickers: list[str] | None = None,
    start: str | None = None,
    end: str | None = None,
) -> pd.DataFrame:
    """Fetch daily OHLCV data for all configured tickers. Save to CSV."""
    tickers = tickers or YAHOO_TICKERS
    start = start or YAHOO_START
    end = end or YAHOO_END

    DATA_RAW_YAHOO.mkdir(parents=True, exist_ok=True)

    all_frames: list[pd.DataFrame] = []

    for ticker in tickers:
        try:
            logger.info("Fetching %s from Yahoo Finance", ticker)
            tk = yf.Ticker(ticker)
            df = tk.history(start=start, end=end, auto_adjust=True)
            if df.empty:
                logger.warning("No data returned for %s", ticker)
                continue
            df.index.name = "date"
            # Clean ticker name for filename (replace ^ and others)
            safe_name = ticker.replace("^", "").replace("-", "_")
            path = DATA_RAW_YAHOO / f"{safe_name}.csv"
            df.to_csv(path)
            logger.info("Saved %s (%d rows) to %s", ticker, len(df), path)
            all_frames.append(df.assign(ticker=ticker))
        except Exception as exc:
            logger.error("Failed to fetch %s: %s", ticker, exc)

    if all_frames:
        combined = pd.concat(all_frames)
        combined.to_csv(DATA_RAW_YAHOO / "all_tickers.csv")
        logger.info("Saved combined dataset (%d rows)", len(combined))
        return combined

    return pd.DataFrame()


def fetch_all_yahoo_data() -> None:
    """Fetch all Yahoo data and save to data/raw/yahoo/."""
    logger.info("=== Starting Yahoo Finance data acquisition ===")
    fetch_yahoo_data()
    logger.info("=== Yahoo Finance data acquisition complete ===")