"""
Forex Signal Intelligence Platform - News & Sentiment Engine
=============================================================
Monitors economic calendar events and news sentiment to provide
fundamental context for technical signals.

Key principle: High-impact news events override technical signals.
A perfect technical setup can be destroyed by an unexpected NFP print.
"""

import logging
import re
import threading
import time
import xml.etree.ElementTree as ET
from dataclasses import dataclass, field
from datetime import datetime, timezone
from email.utils import parsedate_to_datetime
from typing import Dict, List, Optional, Tuple

import requests

from config import NewsConfig

logger = logging.getLogger(__name__)


_RELEASE_VALUE_RE = re.compile(r"(-?\d+(?:\.\d+)?)\s*([kmbt])?", re.IGNORECASE)
_RELEASE_MULTIPLIERS = {"k": 1e3, "m": 1e6, "b": 1e9, "t": 1e12}


def _parse_release_value(raw: Optional[str]) -> Optional[float]:
    """Parse a calendar release value like '0.3%', '-1.7%', '228K', '1.1M'."""
    if not raw:
        return None
    match = _RELEASE_VALUE_RE.search(raw.replace(",", ""))
    if not match:
        return None
    multiplier = _RELEASE_MULTIPLIERS.get((match.group(2) or "").lower(), 1.0)
    return float(match.group(1)) * multiplier


@dataclass
class EconomicEvent:
    """Single economic calendar event."""
    time: datetime
    currency: str
    impact: str  # "low", "medium", "high"
    event: str
    forecast: Optional[str] = None
    previous: Optional[str] = None
    actual: Optional[str] = None

    @property
    def surprise(self) -> Optional[str]:
        """Actual vs forecast: "positive"/"negative"/"inline", or None when
        either value is missing or non-numeric. Direction is numeric only —
        it does not know whether higher is market-bullish for this event."""
        actual = _parse_release_value(self.actual)
        forecast = _parse_release_value(self.forecast)
        if actual is None or forecast is None:
            return None
        if actual > forecast:
            return "positive"
        if actual < forecast:
            return "negative"
        return "inline"

    @property
    def is_upcoming(self) -> bool:
        return self.time > datetime.now(timezone.utc)

    @property
    def minutes_until(self) -> float:
        delta = self.time - datetime.now(timezone.utc)
        return delta.total_seconds() / 60

    @property
    def is_high_impact(self) -> bool:
        return self.impact == "high"


@dataclass
class NewsSentiment:
    """News sentiment analysis result."""
    headline: str
    source: str
    timestamp: datetime
    currencies_mentioned: List[str]
    sentiment_score: float  # -1.0 (bearish) to +1.0 (bullish)
    keywords: List[str]
    # Per-currency score: monetary-policy keywords flip sign for XAU
    # (hawkish is dollar-bullish but gold-bearish).
    sentiment_by_currency: Dict[str, float] = field(default_factory=dict)


@dataclass
class FundamentalContext:
    """Complete fundamental/news context for signal decisions."""
    events_today: List[EconomicEvent] = field(default_factory=list)
    events_upcoming_1h: List[EconomicEvent] = field(default_factory=list)
    high_impact_warning: bool = False
    warning_message: str = ""
    news_sentiment: Dict[str, float] = field(default_factory=dict)  # currency -> sentiment
    news_headlines: List[NewsSentiment] = field(default_factory=list)
    event_impact_on_pairs: Dict[str, str] = field(default_factory=dict)
    calendar_available: bool = False  # True if live calendar data was fetched


class NewsEngine:
    """
    Economic calendar and news sentiment analyzer.

    Provides fundamental context that modifies technical signal confidence.
    """

    # Keywords that indicate directional sentiment
    BULLISH_KEYWORDS = {
        "rate hike", "hawkish", "strong growth", "beat expectations",
        "above forecast", "above estimate", "above expectation",
        "surplus", "expansion", "employment gains",
        "strong jobs", "gdp growth", "inflation rising", "tightening",
        "positive surprise", "record high", "bullish", "rally",
        "stronger than expected", "upbeat",
        "beats", "surges", "soars", "jumps", "climbs", "rises",
        "higher than expected", "better than expected",
        "strong data", "robust", "resilient", "accelerates",
    }

    BEARISH_KEYWORDS = {
        "rate cut", "dovish", "recession", "slowdown", "contraction",
        "below forecast", "below estimate", "below expectation",
        "deficit", "miss expectations", "weak data",
        "unemployment rise", "negative surprise", "bearish", "selloff",
        "weaker than expected", "downbeat", "easing", "stimulus",
        "misses", "slides", "drops", "falls", "plunges", "tumbles",
        "weakens", "slumps", "declines", "retreats",
        "lower than expected", "worse than expected",
        "disappointing", "soft data",
    }

    # Monetary-policy keywords whose direction inverts for gold: tighter
    # policy lifts the dollar and yields, weighing on non-yielding gold;
    # easing does the opposite. Only unambiguous policy words — economic
    # data words (beats/misses) keep their normal direction.
    GOLD_INVERSE_KEYWORDS = {
        "rate hike", "hawkish", "tightening",
        "rate cut", "dovish", "easing", "stimulus",
    }

    # Currency-specific keywords for headline parsing. Matched with word
    # boundaries — bare "us"/"eu"/"uk" are deliberately excluded because as
    # substrings they false-positive constantly ("versus" → USD).
    CURRENCY_KEYWORDS = {
        "USD": ["dollar", "fed", "federal reserve", "fomc", "treasury", "american", "nonfarm", "nfp"],
        "EUR": ["euro", "ecb", "eurozone", "german", "french"],
        "GBP": ["pound", "sterling", "boe", "bank of england", "british"],
        "JPY": ["yen", "boj", "bank of japan", "japanese"],
        "CHF": ["franc", "snb", "swiss"],
        "AUD": ["aussie", "rba", "australian", "australia"],
        "CAD": ["loonie", "boc", "canadian", "canada"],
        "NZD": ["kiwi", "rbnz", "new zealand"],
        "XAU": ["gold", "precious metal", "safe haven", "bullion"],
    }

    # One compiled alternation per currency (code + keywords). (?<![a-z]) /
    # (?![a-z]) instead of \b so "0.3%fed" still matches but "versus",
    # "audit", "cascade" don't.
    _CURRENCY_PATTERNS = {
        cur: re.compile(
            r"(?<![a-z])(?:"
            + "|".join(re.escape(kw) for kw in [cur.lower()] + kws)
            + r")(?![a-z])"
        )
        for cur, kws in CURRENCY_KEYWORDS.items()
    }

    _calendar_backoff_until: float = 0.0

    # Fetched-data cache, class-level: a fresh NewsEngine is built per scan,
    # so instance state would never be reused. Guarded by _cache_lock since
    # scans run concurrently in a thread pool.
    _cache_lock = threading.Lock()
    _calendar_cache: Tuple[float, List[EconomicEvent]] = (0.0, [])
    _headlines_cache: Tuple[float, List[NewsSentiment]] = (0.0, [])
    _EMPTY_RESULT_TTL = 60.0  # retry sooner after a failed/empty fetch

    def __init__(self, config: NewsConfig):
        self.config = config
        self._session = requests.Session()
        self._session.headers.update({
            "User-Agent": "Mozilla/5.0 (compatible; ForexIntel/1.0)"
        })

    def get_fundamental_context(
        self, currencies: Optional[List[str]] = None
    ) -> FundamentalContext:
        """
        Get complete fundamental context for signal decisions.

        Combines economic calendar + news sentiment into actionable context.
        """
        if currencies is None:
            currencies = self.config.tracked_currencies

        context = FundamentalContext()

        # 1. Economic calendar events
        try:
            events = self._fetch_economic_calendar(currencies)
            now = datetime.now(timezone.utc)

            # Compare dates in UTC — feed timestamps carry their own offset
            # (FF sends US-Eastern), so a late-evening ET event would
            # otherwise land on the wrong day.
            context.events_today = [
                e for e in events
                if e.time.astimezone(timezone.utc).date() == now.date()
            ]
            context.events_upcoming_1h = [
                e for e in events
                if 0 < e.minutes_until <= 60
            ]
            context.calendar_available = bool(events)

            # Check for high-impact warnings
            for event in events:
                if event.is_high_impact and 0 < event.minutes_until <= self.config.pre_event_buffer_minutes:
                    context.high_impact_warning = True
                    context.warning_message = (
                        f"HIGH IMPACT: {event.currency} {event.event} "
                        f"in {event.minutes_until:.0f} min — signals may be unreliable"
                    )
                    break

            # Map upcoming high-impact events to affected pairs
            for event in context.events_upcoming_1h:
                if event.is_high_impact:
                    affected = self._get_affected_pairs(event.currency)
                    for pair in affected:
                        context.event_impact_on_pairs[pair] = (
                            f"{event.currency} {event.event} in {event.minutes_until:.0f}min"
                        )

        except Exception as e:
            logger.warning(f"Economic calendar fetch failed: {e}")

        # 2. News sentiment
        try:
            headlines = self._fetch_news_sentiment()
            context.news_headlines = headlines

            # Aggregate sentiment per currency (per-currency score where
            # available, so gold-inverted policy keywords are respected)
            for currency in currencies:
                scores = [
                    h.sentiment_by_currency.get(currency, h.sentiment_score)
                    for h in headlines
                    if currency in h.currencies_mentioned
                ]
                if scores:
                    context.news_sentiment[currency] = sum(scores) / len(scores)

        except Exception as e:
            logger.warning(f"News sentiment fetch failed: {e}")

        return context

    @staticmethod
    def _parse_pair(pair_symbol: str) -> Tuple[str, str]:
        if "/" in pair_symbol:
            parts = pair_symbol.split("/")
            return parts[0], parts[1]
        clean = pair_symbol.replace("=X", "")
        return clean[:3], clean[3:]

    def get_event_risk_level(self, pair_symbol: str, context: FundamentalContext) -> Tuple[str, str]:
        """
        Get event risk level for a specific pair.
        Returns (risk_level, description).
        risk_level: "clear", "caution", "danger"
        """
        base, quote = self._parse_pair(pair_symbol)

        # Check upcoming high-impact events. Grade from the SOONEST
        # matching event, not the first listed — an unsorted feed could
        # otherwise report "caution" for a far event while a nearer one
        # warrants "danger".
        soonest = None
        for event in context.events_upcoming_1h:
            if event.is_high_impact and event.currency in (base, quote):
                if soonest is None or event.minutes_until < soonest.minutes_until:
                    soonest = event
        if soonest is not None:
            mins = soonest.minutes_until
            if mins <= self.config.pre_event_buffer_minutes:
                return "danger", f"{soonest.currency} {soonest.event} in {mins:.0f}min"
            return "caution", f"{soonest.currency} {soonest.event} in {mins:.0f}min"

        # Check for recent high-impact releases. A surprise print (actual
        # away from forecast) keeps the market unstable longer than an
        # inline release, so it gets a wider post-event window.
        for event in context.events_today:
            if event.is_high_impact and event.currency in (base, quote) and not event.is_upcoming:
                surprise = event.surprise
                surprised = surprise in ("positive", "negative")
                window = (
                    self.config.post_event_surprise_buffer_minutes
                    if surprised
                    else self.config.post_event_buffer_minutes
                )
                if event.minutes_until > -window:
                    if surprised:
                        return "caution", (
                            f"{event.currency} {event.event} released — {surprise} surprise "
                            f"(actual {event.actual} vs forecast {event.forecast})"
                        )
                    return "caution", f"{event.currency} {event.event} just released"

        return "clear", "No significant events"

    def get_pair_sentiment(
        self, pair_symbol: str, context: FundamentalContext
    ) -> Tuple[float, str]:
        """
        Get net sentiment for a pair based on news.
        Returns (score, description) where score is -1 to +1.
        Positive = bullish for the pair, negative = bearish.
        """
        base, quote = self._parse_pair(pair_symbol)

        base_sent = context.news_sentiment.get(base, 0.0)
        quote_sent = context.news_sentiment.get(quote, 0.0)

        # Net sentiment: positive base or negative quote = bullish for pair
        net = base_sent - quote_sent

        if abs(net) < 0.1:
            desc = "Neutral news sentiment"
        elif net > 0.3:
            desc = f"Bullish sentiment ({base} positive / {quote} negative)"
        elif net > 0:
            desc = "Slightly bullish sentiment"
        elif net < -0.3:
            desc = f"Bearish sentiment ({base} negative / {quote} positive)"
        else:
            desc = "Slightly bearish sentiment"

        return net, desc

    # ── Private Methods ────────────────────────────────────────────

    # Maps country names in MyFXBook titles to currency codes
    _COUNTRY_TO_CURRENCY = {
        "united states": "USD", "euro area": "EUR", "united kingdom": "GBP",
        "japan": "JPY", "switzerland": "CHF", "australia": "AUD",
        "canada": "CAD", "new zealand": "NZD",
    }

    def _cached_fetch(self, cache_attr: str, fetch_fn) -> list:
        """Return cached data for `cache_attr` or refetch when the TTL
        expired. Successful results live for context_cache_ttl_seconds;
        empty results only _EMPTY_RESULT_TTL so outages retry quickly.
        The lock is held across the fetch so concurrent scans share one
        request instead of stampeding the source."""
        ts, data = getattr(NewsEngine, cache_attr)
        ttl = self.config.context_cache_ttl_seconds if data else self._EMPTY_RESULT_TTL
        if time.time() - ts < ttl:
            return data

        with NewsEngine._cache_lock:
            ts, data = getattr(NewsEngine, cache_attr)  # re-check under lock
            ttl = self.config.context_cache_ttl_seconds if data else self._EMPTY_RESULT_TTL
            if time.time() - ts < ttl:
                return data
            data = fetch_fn()
            setattr(NewsEngine, cache_attr, (time.time(), data))
            return data

    def _fetch_economic_calendar(self, currencies: List[str]) -> List[EconomicEvent]:
        """Cached calendar fetch, filtered to the tracked currencies."""
        events = self._cached_fetch("_calendar_cache", self._fetch_calendar_raw)
        return [e for e in events if e.currency in currencies]

    def _fetch_calendar_raw(self) -> List[EconomicEvent]:
        """
        Fetch economic calendar events from a free API.
        Tries Forex Factory first, falls back to MyFXBook RSS.
        Returns an empty list (with a log warning) if unavailable —
        we never generate fake events since that causes constant false alarms.
        """
        for fetcher in (self._try_fetch_calendar_api, self._try_fetch_myfxbook_rss):
            try:
                events = fetcher()
                if events:
                    return events
            except Exception as e:
                logger.debug(f"Calendar fetch exception ({fetcher.__name__}): {e}")

        logger.info(
            "Economic calendar data unavailable. "
            "Event risk checks will be skipped for this cycle."
        )
        return []

    def _try_fetch_calendar_api(self) -> List[EconomicEvent]:
        """Attempt to fetch from the Forex Factory free JSON calendar."""
        now = time.time()
        if now < NewsEngine._calendar_backoff_until:
            wait = NewsEngine._calendar_backoff_until - now
            logger.debug(f"Calendar API in backoff for {wait:.0f}s more")
            return []

        url = "https://nfs.faireconomy.media/ff_calendar_thisweek.json"

        for attempt in range(3):
            try:
                resp = self._session.get(url, timeout=10)
            except requests.RequestException as e:
                logger.debug(f"Calendar request failed (attempt {attempt + 1}): {e}")
                if attempt < 2:
                    time.sleep(2 ** attempt)
                continue

            if resp.status_code == 429:
                retry_after = int(resp.headers.get("Retry-After", 300))
                retry_after = min(retry_after, 600)
                NewsEngine._calendar_backoff_until = time.time() + retry_after
                logger.warning(
                    f"Calendar API rate-limited (429), backing off {retry_after}s"
                )
                return []

            if resp.status_code != 200:
                logger.debug(f"Calendar API returned {resp.status_code}")
                return []

            data = resp.json()
            events = []
            impact_map = {"High": "high", "Medium": "medium", "Low": "low"}

            for item in data:
                try:
                    impact = impact_map.get(item.get("impact", ""), "low")

                    date_str = item.get("date", "")
                    if not date_str:
                        continue
                    event_time = datetime.fromisoformat(date_str.replace("Z", "+00:00"))

                    events.append(EconomicEvent(
                        time=event_time,
                        currency=item.get("country", ""),
                        impact=impact,
                        event=item.get("title", ""),
                        forecast=item.get("forecast") or None,
                        previous=item.get("previous") or None,
                        actual=item.get("actual") or None,
                    ))
                except Exception:
                    continue

            return events

        return []

    def _try_fetch_myfxbook_rss(self) -> List[EconomicEvent]:
        """Fallback calendar source: MyFXBook economic calendar RSS."""
        url = "https://www.myfxbook.com/rss/forex-economic-calendar-events"
        try:
            resp = self._session.get(url, timeout=10)
        except requests.RequestException as e:
            logger.debug(f"MyFXBook calendar request failed: {e}")
            return []

        if resp.status_code != 200:
            return []

        try:
            root = ET.fromstring(resp.content)
        except ET.ParseError:
            return []

        events = []
        for item in root.iter("item"):
            try:
                title_el = item.find("title")
                pub_el = item.find("pubDate")
                desc_el = item.find("description")
                if title_el is None or title_el.text is None:
                    continue

                title = title_el.text.strip()

                currency = ""
                title_lower = title.lower()
                for country, cur in self._COUNTRY_TO_CURRENCY.items():
                    if title_lower.startswith(country):
                        currency = cur
                        title = title[len(country):].strip()
                        break
                if not currency:
                    continue

                event_time = self._parse_rss_date(
                    pub_el.text if pub_el is not None else None
                )
                if event_time is None:
                    continue

                impact = "low"
                desc_text = desc_el.text if desc_el is not None and desc_el.text else ""
                impact_match = re.search(r"sprite-(high|medium|low)-impact", desc_text)
                if impact_match:
                    impact = impact_match.group(1)

                cells = re.findall(r"<td[^>]*>(.*?)</td>", desc_text, re.DOTALL)
                cells = [re.sub(r"<[^>]+>", "", c).strip() for c in cells]
                previous = cells[2] if len(cells) > 2 and cells[2] else None
                forecast = cells[3] if len(cells) > 3 and cells[3] else None
                actual = cells[4] if len(cells) > 4 and cells[4] else None

                events.append(EconomicEvent(
                    time=event_time,
                    currency=currency,
                    impact=impact,
                    event=title,
                    forecast=forecast,
                    previous=previous,
                    actual=actual,
                ))
            except Exception:
                continue

        logger.debug(f"MyFXBook calendar: parsed {len(events)} events")
        return events

    def _fetch_news_sentiment(self) -> List[NewsSentiment]:
        """Cached headline fetch + sentiment analysis."""
        return self._cached_fetch("_headlines_cache", self._fetch_news_sentiment_raw)

    def _fetch_news_sentiment_raw(self) -> List[NewsSentiment]:
        """Fetch and analyze news headlines for sentiment."""
        headlines = []
        seen_titles = set()

        for feed_url in self.config.rss_feeds:
            try:
                resp = self._session.get(feed_url, timeout=10)
                if resp.status_code != 200:
                    continue

                root = ET.fromstring(resp.content)

                for item in root.iter("item"):
                    title_el = item.find("title")
                    pub_date_el = item.find("pubDate")

                    if title_el is None:
                        continue

                    title = title_el.text or ""
                    pub_date = self._parse_rss_date(
                        pub_date_el.text if pub_date_el is not None else None
                    )

                    # Only recent headlines (last 24h)
                    if pub_date and (datetime.now(timezone.utc) - pub_date).total_seconds() > 86400:
                        continue

                    # Dedup within and across feeds so a syndicated story
                    # doesn't count twice in the sentiment average. Google
                    # News appends " - Publisher", so compare without it.
                    title_key = title.lower().rsplit(" - ", 1)[0].strip()
                    if title_key in seen_titles:
                        continue
                    seen_titles.add(title_key)

                    sentiment = self._analyze_headline_sentiment(title)
                    currencies = self._extract_currencies(title)

                    if currencies:
                        headlines.append(NewsSentiment(
                            headline=title,
                            source=feed_url,
                            timestamp=pub_date or datetime.now(timezone.utc),
                            currencies_mentioned=currencies,
                            sentiment_score=sentiment,
                            keywords=self._extract_keywords(title),
                            sentiment_by_currency={
                                cur: self._analyze_headline_sentiment(title, cur)
                                for cur in currencies
                            },
                        ))

            except Exception as e:
                logger.debug(f"Failed to fetch RSS from {feed_url}: {e}")

        return headlines

    def _analyze_headline_sentiment(
        self, headline: str, for_currency: Optional[str] = None
    ) -> float:
        """
        Simple keyword-based sentiment analysis.

        Returns -1.0 (very bearish) to +1.0 (very bullish).

        When for_currency is "XAU", monetary-policy keywords contribute
        with inverted sign (see GOLD_INVERSE_KEYWORDS).

        Note: This is intentionally simple. NLP models like FinBERT
        would be more accurate but require large dependencies. This catches
        the most impactful sentiment signals from headlines.
        """
        headline_lower = headline.lower()
        invert_policy = for_currency == "XAU"

        bullish_score = 0
        bearish_score = 0
        for kw in self.BULLISH_KEYWORDS:
            if kw in headline_lower:
                if invert_policy and kw in self.GOLD_INVERSE_KEYWORDS:
                    bearish_score += 1
                else:
                    bullish_score += 1
        for kw in self.BEARISH_KEYWORDS:
            if kw in headline_lower:
                if invert_policy and kw in self.GOLD_INVERSE_KEYWORDS:
                    bullish_score += 1
                else:
                    bearish_score += 1

        total = bullish_score + bearish_score
        if total == 0:
            return 0.0

        return (bullish_score - bearish_score) / total

    def _extract_currencies(self, headline: str) -> List[str]:
        """Extract mentioned currencies from a headline."""
        headline_lower = headline.lower()
        return [
            currency
            for currency, pattern in self._CURRENCY_PATTERNS.items()
            if pattern.search(headline_lower)
        ]

    def _extract_keywords(self, headline: str) -> List[str]:
        """Extract relevant trading keywords from headline."""
        headline_lower = headline.lower()
        return [kw for kw in self.BULLISH_KEYWORDS | self.BEARISH_KEYWORDS if kw in headline_lower]

    @staticmethod
    def _parse_rss_date(date_str: Optional[str]) -> Optional[datetime]:
        """Parse various RSS date formats into a timezone-aware datetime."""
        if not date_str:
            return None

        # RFC 822/2822 forms, with or without seconds, numeric offsets AND
        # named zones (GMT, EST/EDT, PST…). The old strptime "%Z" path
        # accepted ANY abbreviation but attached no offset, so e.g. an EST
        # pubDate was silently stamped UTC — a 5-hour error.
        try:
            dt = parsedate_to_datetime(date_str.strip())
            if dt is not None:
                if dt.tzinfo is None:   # unknown zone name — assume UTC
                    return dt.replace(tzinfo=timezone.utc)
                return dt.astimezone(timezone.utc)
        except (TypeError, ValueError):
            pass

        formats = [
            "%Y-%m-%dT%H:%M:%S%z",         # ISO 8601 with offset
            "%Y-%m-%d %H:%M:%S",           # ISO 8601 naive (assume UTC)
        ]
        for fmt in formats:
            try:
                dt = datetime.strptime(date_str.strip(), fmt)
                # If strptime already attached tzinfo (from %z), keep it.
                # Otherwise the string had no timezone info — assume UTC.
                if dt.tzinfo is not None:
                    return dt
                return dt.replace(tzinfo=timezone.utc)
            except ValueError:
                continue
        return None

    @staticmethod
    def _get_affected_pairs(currency: str) -> List[str]:
        _MAP = {
            "USD": ["XAU/USD"],
            "XAU": ["XAU/USD"],
        }
        return _MAP.get(currency, [])