"""Loughran-McDonald text sentiment features for SEC filings.

Computes word-frequency-based sentiment scores using the Loughran-McDonald
financial sentiment dictionary. Features:
  - lm_positive_pct: fraction of words in positive word list
  - lm_negative_pct: fraction of words in negative word list
  - lm_net_sentiment: (positive - negative) / total_words
  - lm_uncertainty_pct: fraction of words in uncertainty word list
"""
from __future__ import annotations

import csv
import re
from functools import lru_cache
from pathlib import Path
from typing import Any

from libs.common.logging import get_logger

logger = get_logger(__name__)

_DICT_PATH = Path("data/dictionaries/lm_master_dictionary.csv")

# Fallback minimal word lists if the full dictionary is not available.
# These are the most common Loughran-McDonald words by category.
_FALLBACK_POSITIVE = {
    "achieve", "achieved", "achieves", "achieving", "advantage", "advantages",
    "benefit", "beneficial", "benefits", "better", "boost", "boosted",
    "create", "created", "creative", "effective", "efficiency", "enable",
    "enabled", "enhance", "enhanced", "exceed", "exceeded", "exceeding",
    "excellent", "favorable", "gain", "gained", "gains", "good", "great",
    "greater", "grew", "growth", "highest", "improve", "improved",
    "improvement", "improvements", "improving", "increase", "increased",
    "increases", "increasing", "innovative", "leading", "opportunity",
    "opportunities", "optimal", "outperform", "outperformed", "positive",
    "profitability", "profitable", "progress", "prosper", "record",
    "reward", "rewarding", "strong", "stronger", "strongest", "succeed",
    "succeeded", "success", "successful", "superior", "surpass", "surpassed",
    "upturn", "win", "winning",
}

_FALLBACK_NEGATIVE = {
    "abandon", "abandoned", "adversarial", "adverse", "adversely",
    "challenge", "challenged", "challenges", "challenging", "close",
    "closed", "closing", "concern", "concerned", "concerns", "decline",
    "declined", "declines", "declining", "default", "defaults", "deficit",
    "deficient", "delay", "delayed", "delays", "deteriorate", "deteriorated",
    "deteriorating", "difficult", "difficulties", "difficulty", "diminish",
    "disappointed", "disappointing", "discontinue", "disruption", "doubt",
    "downturn", "downturns", "drop", "dropped", "drops", "fail", "failed",
    "failing", "failure", "failures", "fell", "impair", "impaired",
    "impairment", "impairments", "inability", "inadequate", "investigation",
    "investigations", "lawsuit", "lawsuits", "liability", "liabilities",
    "liquidate", "liquidation", "litigation", "loss", "losses", "lost",
    "negative", "negatively", "penalty", "penalties", "problem", "problems",
    "recession", "recessions", "restructure", "restructured", "restructuring",
    "risk", "risks", "risky", "shortfall", "shutdown", "slump", "slowdown",
    "suffer", "suffered", "suffering", "suspend", "suspended", "terminate",
    "terminated", "termination", "threat", "threaten", "uncertain",
    "unfavorable", "unforeseen", "unprofitable", "volatile", "volatility",
    "weakness", "weaknesses", "worsen", "worsened", "worsening", "writedown",
    "writeoff",
}

_FALLBACK_UNCERTAINTY = {
    "almost", "ambiguity", "ambiguous", "approximate", "approximately",
    "assume", "assumed", "assumes", "assuming", "assumption", "assumptions",
    "believe", "believed", "believes", "cautious", "conceivable",
    "conditional", "could", "depend", "dependent", "depending", "depends",
    "doubt", "doubtful", "estimate", "estimated", "estimates", "estimating",
    "estimation", "expect", "expected", "expecting", "expects", "fluctuate",
    "fluctuated", "fluctuates", "fluctuating", "fluctuation", "fluctuations",
    "indefinite", "indefinitely", "indicate", "indicated", "indicates",
    "indication", "likely", "may", "maybe", "might", "nearly", "pending",
    "perhaps", "possible", "possibly", "potential", "potentially",
    "predict", "predicted", "prediction", "predicting", "preliminary",
    "presumably", "probable", "probably", "project", "projected",
    "projecting", "projection", "projections", "risk", "risky",
    "roughly", "seem", "seemed", "seems", "sometimes", "somewhat",
    "suggest", "suggested", "suggesting", "suggests", "suppose", "tend",
    "tended", "tends", "uncertain", "uncertainty", "unclear", "undetermined",
    "unlikely", "unpredictable", "unsettled", "unsure", "variable",
    "variability",
}

_WORD_RE = re.compile(r"[a-z]+", re.IGNORECASE)


@lru_cache(maxsize=1)
def _load_dictionary() -> tuple[set[str], set[str], set[str]]:
    """Load Loughran-McDonald dictionary. Returns (positive, negative, uncertainty) word sets."""
    if not _DICT_PATH.exists():
        logger.info("lm_dict_using_fallback", path=str(_DICT_PATH))
        return _FALLBACK_POSITIVE, _FALLBACK_NEGATIVE, _FALLBACK_UNCERTAINTY

    positive: set[str] = set()
    negative: set[str] = set()
    uncertainty: set[str] = set()

    try:
        with open(_DICT_PATH, encoding="utf-8") as f:
            reader = csv.DictReader(f)
            for row in reader:
                word = row.get("Word", row.get("word", "")).lower().strip()
                if not word:
                    continue
                # LM dictionary uses non-zero year values to indicate category membership
                if _is_positive_value(row):
                    positive.add(word)
                if _is_negative_value(row):
                    negative.add(word)
                if _is_uncertainty_value(row):
                    uncertainty.add(word)

        logger.info(
            "lm_dict_loaded",
            positive=len(positive),
            negative=len(negative),
            uncertainty=len(uncertainty),
        )
    except Exception as exc:
        logger.warning("lm_dict_load_failed", error=str(exc))
        return _FALLBACK_POSITIVE, _FALLBACK_NEGATIVE, _FALLBACK_UNCERTAINTY

    # Fall back if dictionary seems empty
    if not positive and not negative:
        return _FALLBACK_POSITIVE, _FALLBACK_NEGATIVE, _FALLBACK_UNCERTAINTY

    return positive, negative, uncertainty


def _is_positive_value(row: dict[str, str]) -> bool:
    val = row.get("Positive", row.get("positive", "0"))
    try:
        return int(val) != 0
    except (ValueError, TypeError):
        return False


def _is_negative_value(row: dict[str, str]) -> bool:
    val = row.get("Negative", row.get("negative", "0"))
    try:
        return int(val) != 0
    except (ValueError, TypeError):
        return False


def _is_uncertainty_value(row: dict[str, str]) -> bool:
    val = row.get("Uncertainty", row.get("uncertainty", "0"))
    try:
        return int(val) != 0
    except (ValueError, TypeError):
        return False


def compute_text_features(text: str) -> dict[str, Any]:
    """Compute Loughran-McDonald text sentiment features from filing text.

    Args:
        text: Raw or normalized filing/exhibit text.

    Returns:
        Dict with keys: lm_positive_pct, lm_negative_pct, lm_net_sentiment,
        lm_uncertainty_pct, lm_word_count.
    """
    positive_words, negative_words, uncertainty_words = _load_dictionary()

    words = _WORD_RE.findall(text.lower())
    total = len(words)

    if total == 0:
        return {
            "lm_positive_pct": 0.0,
            "lm_negative_pct": 0.0,
            "lm_net_sentiment": 0.0,
            "lm_uncertainty_pct": 0.0,
            "lm_word_count": 0,
        }

    pos_count = sum(1 for w in words if w in positive_words)
    neg_count = sum(1 for w in words if w in negative_words)
    unc_count = sum(1 for w in words if w in uncertainty_words)

    return {
        "lm_positive_pct": round(pos_count / total, 6),
        "lm_negative_pct": round(neg_count / total, 6),
        "lm_net_sentiment": round((pos_count - neg_count) / total, 6),
        "lm_uncertainty_pct": round(unc_count / total, 6),
        "lm_word_count": total,
    }