from __future__ import annotations

SYMPTOM_KEYWORDS: dict[str, list[str]] = {

    # ── VATA SYMPTOMS ───────────────────────────────────────────────────
    "trunk_bent": [
        "trunk bent", "bent trunk", "curved trunk", "twisted stem",
        "crooked trunk", "leaning trunk",
    ],
    "knots_on_trunk": [
        "knots", "knotted", "knots on trunk", "knots on leaves",
        "nodules", "galls", "swellings on bark",
    ],
    "hard_fruits": [
        "hard fruit", "hard fruits", "less juicy", "dry fruit",
        "no juice", "tasteless fruit", "woody fruit",
    ],
    "slow_defoliation": [
        "slow defoliation", "leaves not falling", "leaves clinging",
        "slow leaf drop", "delayed leaf shed",
    ],
    "flower_fruit_loss": [
        "loss of flowers", "loss of fruits", "fruit drop", "flower drop",
        "dropping fruit", "flowers falling", "fruits falling",
        "premature fruit drop", "fruit loss", "flower loss",
    ],
    "general_yellowing": [
        "yellowing", "yellow leaves", "yellowing of leaves",
        "yellowing of fruits", "pale leaves", "chlorosis",
        "leaves turning yellow", "yellow fruit",
    ],

    # ── KAPHA SYMPTOMS ──────────────────────────────────────────────────
    "delayed_fruiting": [
        "delayed fruiting", "fruit bearing delayed", "no fruit",
        "not fruiting", "late fruiting", "delayed bearing",
        "tree not producing",
    ],
    "bland_overripe_fruits": [
        "bland fruit", "bland and overripe", "overripe", "tasteless",
        "flat taste", "no flavour", "watery fruit",
    ],
    "oozing_without_injury": [
        "oozing", "oozing without injury", "seeping", "gummosis",
        "sap oozing", "resin oozing", "spontaneous discharge",
        "leaking sap",
    ],

    # ── PITTA SYMPTOMS ──────────────────────────────────────────────────
    "early_leaf_withering": [
        "early withering", "withering early", "leaf withering",
        "premature withering", "withering", "wilting",
        "early wilting", "leaves dying early", "withered leaves",
    ],
    "early_fruit_flower_decay": [
        "early decay", "fruit decay", "flower decay", "blossom blight",
        "rotting flowers", "rotting fruits", "premature decay",
        "fruit rot", "flower rot", "decaying", "decay",
        "decaying prematurely",
    ],

    # ── EXTERNAL HEAT / FROST SYMPTOMS ──────────────────────────────────
    "vata_like_symptoms": [
        "vata-like", "vata like symptoms", "vata symptoms",
        "yellowing and drying", "general decline", "drying and yellowing",
    ],

    # ── WIND DAMAGE SYMPTOMS ─────────────────────────────────────────────
    "tree_uprooting": [
        "uprooted", "tree uprooting", "fell", "fallen tree",
        "roots exposed", "tree fell over", "uprooted tree",
    ],
    "branch_breaking": [
        "branch breaking", "broken branch", "branches broken",
        "limbs broken", "snapped branch", "broken limb",
    ],
    "tree_twisting": [
        "tree twisting", "twisted tree", "twisted trunk",
        "trunk twisted", "torqued",
    ],

    # ── FIRE / DROUGHT / LIGHTNING SYMPTOMS ──────────────────────────────
    "tree_drying": [
        "drying", "tree drying", "drying up", "dried out",
        "desiccation", "tree dried", "branches drying",
        "completely dry",
    ],
    "lightning_strike": [
        "lightning", "struck by lightning", "lightning strike",
        "thunder damage", "lightning damage",
    ],

    # ── MECHANICAL WOUND SYMPTOMS ─────────────────────────────────────────
    "tree_wounds": [
        "wound", "wounded", "axe wound", "cut", "gash",
        "mechanical damage", "tool damage", "injured bark",
        "cut with axe", "bark cut",
    ],

    # ── FAULTY SEED SYMPTOMS ──────────────────────────────────────────────
    "tree_unproductive": [
        "unproductive", "not bearing", "no yield", "barren tree",
        "tree not growing", "no produce", "stunted from seed",
        "failed to grow",
    ],

    # ── INSECT / ANT INFESTATION SYMPTOMS ─────────────────────────────────
    "foul_smell": [
        "foul smell", "bad smell", "smell", "odour",
        "unpleasant odour", "rotten smell",
    ],
    "fragrance_loss": [
        "fragrance missing", "fragrance lost", "no fragrance",
        "original fragrance missing", "lost scent", "fragrance is missing",
        "fragrance",
    ],
    "reduced_leaf_size": [
        "reduced leaf size", "smaller leaves", "small leaves",
        "leaf size reduction", "tiny leaves", "reduced in size",
        "leaves are reduced",
    ],
    "stunted_seedlings": [
        "stunted seedlings", "seedling stunted", "seedling not growing",
        "slow seedling", "weak seedling",
    ],

    # ── EXCESSIVE WATERING SYMPTOMS ───────────────────────────────────────
    "tree_indigestion": [
        "indigestion", "tree indigestion", "waterlogged",
        "soggy roots", "root suffocation", "over watered",
        "overwatered", "root rot from water",
    ],
    "tree_destruction": [
        "destruction", "tree destruction", "deteriorating",
        "collapsing", "decaying rapidly", "dying from water",
    ],

    # ── SEASONAL CONTEXT ──────────────────────────────────────────────────
    "winter_spring_season": [
        "winter", "spring", "cold season", "cool season",
        "winter season", "spring season",
    ],
    "end_of_summer": [
        "end of summer", "late summer", "summer end",
        "post summer", "end of hot season",
    ],
}


def extract_facts(
    user_query: str,
    expanded_queries: list[str],
    retrieved_chunks: list[str],
) -> set[str]:
    """
    Extract atomic Vrikshayurveda facts from all text sources.

    Steps:
    1. Combine user_query + expanded_queries + retrieved_chunks
       into a single lowercase string.
    2. For each (fact, keywords) entry in SYMPTOM_KEYWORDS, check if
       ANY keyword appears in the combined text.
    3. Return the set of matched fact strings.
    """
    combined = " ".join(
        [user_query] + expanded_queries + retrieved_chunks
    ).lower()

    facts: set[str] = set()
    for fact, keywords in SYMPTOM_KEYWORDS.items():
        if any(kw in combined for kw in keywords):
            facts.add(fact)

    return facts