stock_data.py

"""
stock_data.py — Stock data via Yahoo Finance (yfinance). No API key required.
Alpha Vantage retained only for symbol search fallback (optional).
"""
import os
import json
import time
import logging
from pathlib import Path

try:
    from dotenv import load_dotenv
    load_dotenv()
except ImportError:
    pass

import yfinance as yf
import requests

log = logging.getLogger(__name__)

CACHE_DIR = Path("cache")
CACHE_DIR.mkdir(exist_ok=True)

AV_KEY  = os.environ.get("ALPHA_VANTAGE_KEY", "")
AV_BASE = "https://www.alphavantage.co/query"

# ---------------------------------------------------------------------------
# Stock universe — 67 tickers across 10+ sectors
# Architecture: add/remove entries here only. No other code changes needed.
# ---------------------------------------------------------------------------
STOCK_META = {
    # ── Technology ───────────────────────────────────────────────────────
    "AAPL":  {"name": "Apple Inc.",                "sector": "Technology",        "desc": "Consumer electronics, software & services giant."},
    "MSFT":  {"name": "Microsoft Corporation",     "sector": "Technology",        "desc": "Software, cloud, and enterprise solutions."},
    "GOOGL": {"name": "Alphabet Inc.",             "sector": "Technology",        "desc": "Search, advertising, and cloud services."},
    "GOOG":  {"name": "Alphabet Inc. (C)",         "sector": "Technology",        "desc": "Search, advertising, and cloud services."},
    "META":  {"name": "Meta Platforms, Inc.",      "sector": "Technology",        "desc": "Social media and virtual reality platforms."},
    "NVDA":  {"name": "NVIDIA Corporation",        "sector": "Semiconductors",    "desc": "GPU and AI chip manufacturer."},
    "CRM":   {"name": "Salesforce Inc.",           "sector": "Technology",        "desc": "Cloud-based CRM and enterprise software."},
    "ORCL":  {"name": "Oracle Corporation",        "sector": "Technology",        "desc": "Enterprise database and cloud infrastructure."},
    "ADBE":  {"name": "Adobe Inc.",                "sector": "Technology",        "desc": "Creative, marketing, and document software."},
    "SAP":   {"name": "SAP SE",                    "sector": "Technology",        "desc": "Enterprise resource planning and business software."},
    "PLTR":  {"name": "Palantir Technologies",     "sector": "Technology",        "desc": "Big data analytics and AI platform."},
    "SNOW":  {"name": "Snowflake Inc.",            "sector": "Technology",        "desc": "Cloud data warehousing and analytics."},
    "MSTR":  {"name": "MicroStrategy Inc.",        "sector": "Technology",        "desc": "Business intelligence and Bitcoin holdings."},
    "SMCI":  {"name": "Super Micro Computer",      "sector": "Technology",        "desc": "Server and storage solutions manufacturer."},

    # ── Semiconductors ───────────────────────────────────────────────────
    "AMD":   {"name": "Advanced Micro Devices",    "sector": "Semiconductors",    "desc": "CPU, GPU, and semi-custom chips."},
    "INTC":  {"name": "Intel Corporation",         "sector": "Semiconductors",    "desc": "Microprocessors, chips, and computing solutions."},
    "QCOM":  {"name": "QUALCOMM Inc.",             "sector": "Semiconductors",    "desc": "Mobile chipsets and wireless technology."},
    "TSM":   {"name": "Taiwan Semiconductor",      "sector": "Semiconductors",    "desc": "World's largest contract chipmaker."},
    "ASML":  {"name": "ASML Holding",              "sector": "Semiconductors",    "desc": "Semiconductor lithography equipment maker."},
    "ARM":   {"name": "Arm Holdings",              "sector": "Semiconductors",    "desc": "Chip architecture and IP licensing."},

    # ── Finance ──────────────────────────────────────────────────────────
    "JPM":   {"name": "JPMorgan Chase",            "sector": "Finance",           "desc": "Largest U.S. bank by assets."},
    "GS":    {"name": "Goldman Sachs",             "sector": "Finance",           "desc": "Global investment banking and securities."},
    "BAC":   {"name": "Bank of America",           "sector": "Finance",           "desc": "Second-largest U.S. bank by assets."},
    "V":     {"name": "Visa Inc.",                 "sector": "Finance",           "desc": "Global digital payments network."},
    "MA":    {"name": "Mastercard Inc.",           "sector": "Finance",           "desc": "Global payment processing network."},
    "PYPL":  {"name": "PayPal Holdings",           "sector": "Fintech",           "desc": "Digital payments and financial services."},
    "BRK-B": {"name": "Berkshire Hathaway",        "sector": "Finance",           "desc": "Diversified holding company run by Warren Buffett."},
    "BLK":   {"name": "BlackRock Inc.",            "sector": "Finance",           "desc": "World's largest asset management firm."},
    "SQ":    {"name": "Block, Inc.",               "sector": "Fintech",           "desc": "Payment and financial services ecosystem."},
    "HOOD":  {"name": "Robinhood Markets",         "sector": "Fintech",           "desc": "Commission-free investing platform."},
    "COIN":  {"name": "Coinbase Global",           "sector": "Finance/Crypto",    "desc": "Cryptocurrency exchange platform."},

    # ── Healthcare ───────────────────────────────────────────────────────
    "JNJ":   {"name": "Johnson & Johnson",         "sector": "Healthcare",        "desc": "Pharmaceuticals, medical devices, and consumer health."},
    "PFE":   {"name": "Pfizer Inc.",               "sector": "Healthcare",        "desc": "Global pharmaceutical and vaccine manufacturer."},
    "UNH":   {"name": "UnitedHealth Group",        "sector": "Healthcare",        "desc": "Largest U.S. health insurance conglomerate."},

    # ── Consumer / Retail ────────────────────────────────────────────────
    "AMZN":  {"name": "Amazon.com, Inc.",          "sector": "Consumer/Cloud",    "desc": "E-commerce and cloud computing behemoth."},
    "WMT":   {"name": "Walmart Inc.",              "sector": "Retail",            "desc": "World's largest retailer by revenue."},
    "TGT":   {"name": "Target Corporation",        "sector": "Retail",            "desc": "U.S. discount retailer and big-box stores."},
    "COST":  {"name": "Costco Wholesale",          "sector": "Retail",            "desc": "Membership warehouse club and retailer."},
    "HD":    {"name": "Home Depot",                "sector": "Retail",            "desc": "Largest U.S. home improvement retailer."},
    "LOW":   {"name": "Lowe's Companies",          "sector": "Retail",            "desc": "Second-largest U.S. home improvement retailer."},
    "SBUX":  {"name": "Starbucks Corporation",     "sector": "Consumer",          "desc": "Global coffeehouse chain and coffee brand."},
    "MCD":   {"name": "McDonald's Corporation",    "sector": "Consumer",          "desc": "World's largest fast food restaurant chain."},
    "KO":    {"name": "Coca-Cola Company",         "sector": "Consumer",          "desc": "World's largest non-alcoholic beverage company."},
    "PEP":   {"name": "PepsiCo Inc.",              "sector": "Consumer",          "desc": "Beverages and snacks conglomerate."},
    "NKE":   {"name": "Nike Inc.",                 "sector": "Consumer",          "desc": "World's largest athletic footwear and apparel maker."},
    "BABA":  {"name": "Alibaba Group",             "sector": "E-Commerce",        "desc": "China's largest e-commerce conglomerate."},
    "SHOP":  {"name": "Shopify Inc.",              "sector": "E-Commerce",        "desc": "E-commerce platform for businesses."},
    "GME":   {"name": "GameStop Corp.",            "sector": "Retail",            "desc": "Video game and consumer electronics retailer."},

    # ── Energy ───────────────────────────────────────────────────────────
    "XOM":   {"name": "Exxon Mobil Corporation",   "sector": "Energy",            "desc": "Largest U.S. oil and gas company."},
    "CVX":   {"name": "Chevron Corporation",       "sector": "Energy",            "desc": "Integrated energy and chemicals company."},

    # ── Automotive ───────────────────────────────────────────────────────
    "TSLA":  {"name": "Tesla, Inc.",               "sector": "Automotive/Energy", "desc": "Electric vehicles and clean energy pioneer."},
    "F":     {"name": "Ford Motor Company",        "sector": "Automotive",        "desc": "American automaker — trucks, EVs, and ICE vehicles."},
    "GM":    {"name": "General Motors",            "sector": "Automotive",        "desc": "American automaker and EV transition leader."},
    "RIVN":  {"name": "Rivian Automotive",         "sector": "Automotive",        "desc": "Electric vehicle manufacturer."},

    # ── Industrial ───────────────────────────────────────────────────────
    "BA":    {"name": "Boeing Company",            "sector": "Aerospace",         "desc": "Commercial jets, defense, and space systems."},
    "CAT":   {"name": "Caterpillar Inc.",          "sector": "Industrial",        "desc": "Heavy equipment, machinery, and diesel engines."},
    "DE":    {"name": "Deere & Company",           "sector": "Industrial",        "desc": "Agricultural and construction equipment maker."},

    # ── Entertainment / Media ────────────────────────────────────────────
    "NFLX":  {"name": "Netflix, Inc.",             "sector": "Entertainment",     "desc": "Global streaming entertainment service."},
    "DIS":   {"name": "The Walt Disney Company",   "sector": "Entertainment",     "desc": "Media, parks, and streaming entertainment."},
    "SPOT":  {"name": "Spotify Technology",        "sector": "Entertainment",     "desc": "Audio streaming and podcast platform."},
    "AMC":   {"name": "AMC Entertainment",         "sector": "Entertainment",     "desc": "Movie theater chain operator."},

    # ── Telecom ──────────────────────────────────────────────────────────
    "T":     {"name": "AT&T Inc.",                 "sector": "Telecom",           "desc": "U.S. telecommunications and media conglomerate."},
    "VZ":    {"name": "Verizon Communications",    "sector": "Telecom",           "desc": "U.S. telecom giant — wireless and broadband."},

    # ── ETFs ─────────────────────────────────────────────────────────────
    "SPY":   {"name": "SPDR S&P 500 ETF",          "sector": "ETF",               "desc": "Tracks the S&P 500 index."},
    "QQQ":   {"name": "Invesco QQQ ETF",           "sector": "ETF",               "desc": "Tracks the Nasdaq-100 index."},

    # ── Other ────────────────────────────────────────────────────────────
    "UBER":  {"name": "Uber Technologies",         "sector": "Transportation",    "desc": "Ride-sharing and food delivery platform."},
    "SNAP":  {"name": "Snap Inc.",                 "sector": "Technology",        "desc": "Camera and messaging app platform."},
}

LOGO_MAP = {
    "AAPL":  "https://logo.clearbit.com/apple.com",
    "MSFT":  "https://logo.clearbit.com/microsoft.com",
    "GOOGL": "https://logo.clearbit.com/google.com",
    "GOOG":  "https://logo.clearbit.com/google.com",
    "META":  "https://logo.clearbit.com/meta.com",
    "NVDA":  "https://logo.clearbit.com/nvidia.com",
    "CRM":   "https://logo.clearbit.com/salesforce.com",
    "ORCL":  "https://logo.clearbit.com/oracle.com",
    "ADBE":  "https://logo.clearbit.com/adobe.com",
    "SAP":   "https://logo.clearbit.com/sap.com",
    "PLTR":  "https://logo.clearbit.com/palantir.com",
    "SNOW":  "https://logo.clearbit.com/snowflake.com",
    "AMD":   "https://logo.clearbit.com/amd.com",
    "INTC":  "https://logo.clearbit.com/intel.com",
    "QCOM":  "https://logo.clearbit.com/qualcomm.com",
    "TSM":   "https://logo.clearbit.com/tsmc.com",
    "ASML":  "https://logo.clearbit.com/asml.com",
    "ARM":   "https://logo.clearbit.com/arm.com",
    "JPM":   "https://logo.clearbit.com/jpmorganchase.com",
    "GS":    "https://logo.clearbit.com/goldmansachs.com",
    "BAC":   "https://logo.clearbit.com/bankofamerica.com",
    "V":     "https://logo.clearbit.com/visa.com",
    "MA":    "https://logo.clearbit.com/mastercard.com",
    "PYPL":  "https://logo.clearbit.com/paypal.com",
    "BRK-B": "https://logo.clearbit.com/berkshirehathaway.com",
    "BLK":   "https://logo.clearbit.com/blackrock.com",
    "SQ":    "https://logo.clearbit.com/block.xyz",
    "HOOD":  "https://logo.clearbit.com/robinhood.com",
    "COIN":  "https://logo.clearbit.com/coinbase.com",
    "JNJ":   "https://logo.clearbit.com/jnj.com",
    "PFE":   "https://logo.clearbit.com/pfizer.com",
    "UNH":   "https://logo.clearbit.com/unitedhealthgroup.com",
    "AMZN":  "https://logo.clearbit.com/amazon.com",
    "WMT":   "https://logo.clearbit.com/walmart.com",
    "TGT":   "https://logo.clearbit.com/target.com",
    "COST":  "https://logo.clearbit.com/costco.com",
    "HD":    "https://logo.clearbit.com/homedepot.com",
    "LOW":   "https://logo.clearbit.com/lowes.com",
    "SBUX":  "https://logo.clearbit.com/starbucks.com",
    "MCD":   "https://logo.clearbit.com/mcdonalds.com",
    "KO":    "https://logo.clearbit.com/coca-cola.com",
    "PEP":   "https://logo.clearbit.com/pepsico.com",
    "NKE":   "https://logo.clearbit.com/nike.com",
    "BABA":  "https://logo.clearbit.com/alibaba.com",
    "SHOP":  "https://logo.clearbit.com/shopify.com",
    "GME":   "https://logo.clearbit.com/gamestop.com",
    "XOM":   "https://logo.clearbit.com/exxonmobil.com",
    "CVX":   "https://logo.clearbit.com/chevron.com",
    "TSLA":  "https://logo.clearbit.com/tesla.com",
    "F":     "https://logo.clearbit.com/ford.com",
    "GM":    "https://logo.clearbit.com/gm.com",
    "RIVN":  "https://logo.clearbit.com/rivian.com",
    "BA":    "https://logo.clearbit.com/boeing.com",
    "CAT":   "https://logo.clearbit.com/caterpillar.com",
    "DE":    "https://logo.clearbit.com/deere.com",
    "NFLX":  "https://logo.clearbit.com/netflix.com",
    "DIS":   "https://logo.clearbit.com/disney.com",
    "SPOT":  "https://logo.clearbit.com/spotify.com",
    "AMC":   "https://logo.clearbit.com/amctheatres.com",
    "T":     "https://logo.clearbit.com/att.com",
    "VZ":    "https://logo.clearbit.com/verizon.com",
    "UBER":  "https://logo.clearbit.com/uber.com",
    "SNAP":  "https://logo.clearbit.com/snap.com",
}

# Issue #8 — pre-built search index at module load (O(1) lookup instead of O(n) scan)
_SEARCH_INDEX: dict[str, list[str]] = {}

def _build_index():
    for ticker, meta in STOCK_META.items():
        tl = ticker.lower()
        words = [tl] + meta["name"].lower().replace(",", "").replace(".", "").replace("-", " ").split()
        for word in set(words):
            for length in range(1, len(word) + 1):
                prefix = word[:length]
                bucket = _SEARCH_INDEX.setdefault(prefix, [])
                if ticker not in bucket:
                    bucket.append(ticker)

_build_index()


# ---------------------------------------------------------------------------
# Data fetching
# ---------------------------------------------------------------------------

def _cache_path(ticker: str) -> Path:
    # Sanitize ticker for filename (BRK-B → BRK-B_yf.json, safe on all OS)
    safe = ticker.upper().replace("/", "_")
    return CACHE_DIR / f"{safe}_yf.json"


def _is_fresh(path: Path, hours: int = 12) -> bool:
    return path.exists() and (time.time() - path.stat().st_mtime) < hours * 3600


def fetch_daily_ohlcv(ticker: str):
    """
    Fetch full daily OHLCV via yfinance. Results cached to disk.
    Cache is always preferred if it exists — historical data doesn't change.
    yfinance is only called when no cache file is present.
    Returns dict keyed by 'YYYY-MM-DD', or None on failure.
    """
    ticker = ticker.upper()
    cache_file = _cache_path(ticker)

    # Always use cache if it exists and has valid data — no freshness check.
    # Historical OHLCV never changes; this also makes Railway deployments work
    # without hitting Yahoo Finance (which blocks datacenter IPs).
    if cache_file.exists():
        try:
            with open(cache_file, encoding="utf-8") as f:
                data = json.load(f)
            if data and len(data) >= 30:
                return data
        except (json.JSONDecodeError, IOError):
            pass

    try:
        t    = yf.Ticker(ticker)
        hist = t.history(period="max")
        if hist is None or hist.empty:
            hist = t.history(period="5y")
        if hist is None or hist.empty:
            return None

        result = {}
        for ts, row in hist.iterrows():
            result[str(ts.date())] = {
                "open":   round(float(row["Open"]),   4),
                "high":   round(float(row["High"]),   4),
                "low":    round(float(row["Low"]),    4),
                "close":  round(float(row["Close"]),  4),
                "volume": int(row["Volume"]),
            }

        if not result:
            return None

        with open(cache_file, "w", encoding="utf-8") as f:
            json.dump(result, f)
        return result

    except Exception as e:
        log.error("yfinance fetch failed for %s: %s", ticker, e)
        # Last-resort: return stale cache rather than failing entirely
        if cache_file.exists():
            try:
                with open(cache_file, encoding="utf-8") as f:
                    return json.load(f)
            except Exception:
                pass
        return None


def get_current_price(ticker: str):
    """
    Issue #4 — use yfinance fast_info for a lightweight price lookup.
    Falls back to cached OHLCV data if fast_info fails.
    """
    ticker = ticker.upper()
    try:
        fi = yf.Ticker(ticker).fast_info
        price = getattr(fi, "last_price", None)
        if price and float(price) > 0:
            return round(float(price), 2)
    except Exception:
        pass

    # Fallback: use last close from cached data (no new network call)
    cache_file = _cache_path(ticker)
    if cache_file.exists():
        try:
            with open(cache_file, encoding="utf-8") as f:
                data = json.load(f)
            if data:
                return data[sorted(data.keys())[-1]]["close"]
        except Exception:
            pass
    return None


def search_ticker(query: str):
    """O(1) prefix lookup via pre-built index. Only returns curated STOCK_META tickers."""
    key     = query.lower().strip()
    results = []
    seen    = set()

    for ticker in _SEARCH_INDEX.get(key, []):
        if ticker not in seen:
            seen.add(ticker)
            meta = STOCK_META[ticker]
            results.append({
                "ticker": ticker,
                "name":   meta["name"],
                "sector": meta["sector"],
                "desc":   meta["desc"],
                "logo":   LOGO_MAP.get(ticker, ""),
            })

    return results[:8]


def get_stock_info(ticker: str) -> dict:
    ticker = ticker.upper()
    meta   = STOCK_META.get(ticker, {"name": ticker, "sector": "Unknown", "desc": ""})
    return {
        "ticker":        ticker,
        "name":          meta["name"],
        "sector":        meta["sector"],
        "desc":          meta["desc"],
        "logo":          LOGO_MAP.get(ticker, ""),
        "current_price": get_current_price(ticker),
    }