from __future__ import annotations
from typing import List, Dict
import pandas as pd
import yfinance as yf

DEFAULT_UNIVERSE = [
    "AAPL", "MSFT", "NVDA", "AMZN", "GOOGL", "META",
    "JPM", "XOM", "AVGO", "LLY", "AMD", "COST"
]

def sanitize_tickers(tickers: List[str]) -> List[str]:
    cleaned = []
    for t in tickers:
        t = (t or "").strip().upper().replace('"', "").replace("'", "")
        if t and t.isascii() and t.replace("-", "").replace(".", "").isalnum():
            cleaned.append(t)
    return list(dict.fromkeys(cleaned))[:20]

def fetch_price_history(tickers: List[str], lookback_days: int = 365) -> pd.DataFrame:
    tickers = sanitize_tickers(tickers)
    if len(tickers) < 2:
        raise ValueError("Need at least 2 valid tickers")

    period = "2y" if lookback_days > 365 else "1y"
    data = yf.download(
        tickers=tickers,
        period=period,
        interval="1d",
        auto_adjust=True,
        progress=False,
        threads=True,
        group_by="ticker",
    )

    rows = []

    if isinstance(data.columns, pd.MultiIndex):
        for ticker in tickers:
            try:
                block = data[ticker].copy()
            except Exception:
                continue

            if block.empty or "Close" not in block.columns:
                continue

            block = block.reset_index()
            date_col = "Date" if "Date" in block.columns else block.columns[0]

            for _, row in block.iterrows():
                close_val = row.get("Close")
                if pd.isna(close_val):
                    continue
                rows.append({
                    "date": pd.Timestamp(row[date_col]).normalize(),
                    "ticker": ticker,
                    "close": float(close_val),
                    "volume": float(row.get("Volume", 0.0) or 0.0),
                })
    else:
        if len(tickers) != 1:
            raise ValueError("Unexpected Yahoo Finance schema for multiple tickers")
        ticker = tickers[0]
        block = data.copy()
        if block.empty or "Close" not in block.columns:
            raise ValueError("No usable market data returned")
        block = block.reset_index()
        date_col = "Date" if "Date" in block.columns else block.columns[0]

        for _, row in block.iterrows():
            close_val = row.get("Close")
            if pd.isna(close_val):
                continue
            rows.append({
                "date": pd.Timestamp(row[date_col]).normalize(),
                "ticker": ticker,
                "close": float(close_val),
                "volume": float(row.get("Volume", 0.0) or 0.0),
            })

    out = pd.DataFrame(rows)
    if out.empty:
        raise ValueError("No market data returned")
    if "ticker" not in out.columns:
        raise ValueError(f"Ticker column missing from market data. Columns: {list(out.columns)}")
    out = out.sort_values(["ticker", "date"]).reset_index(drop=True)
    return out

def fetch_quotes(tickers: List[str]) -> List[Dict[str, float]]:
    tickers = sanitize_tickers(tickers)
    result = []
    for ticker in tickers:
        try:
            hist = yf.Ticker(ticker).history(period="5d", interval="1d", auto_adjust=True)
            if hist.empty:
                continue
            last = float(hist["Close"].iloc[-1])
            prev = float(hist["Close"].iloc[-2]) if len(hist) > 1 else last
            chg = 0.0 if prev == 0 else (last / prev - 1.0)
            result.append({
                "ticker": ticker,
                "price": last,
                "day_change_pct": chg,
            })
        except Exception:
            continue
    return result

def infer_sectors(tickers: List[str]) -> Dict[str, str]:
    return {ticker: "Unknown" for ticker in sanitize_tickers(tickers)}