from __future__ import annotations

from typing import Any, Dict, Mapping

from .explanation import explain_results
from .features import extract_features
from .normalization import normalize_text
from .scoring import DIALECTS, score_dialects
from .tokenization import tokenize


def classify_text(text: str, *, strip_diacritics: bool = False) -> Dict[str, Any]:
    """End-to-end dialect classification pipeline."""

    normalized = normalize_text(text, strip_diacritics=strip_diacritics)
    tokens = tokenize(normalized)
    features = extract_features(tokens)
    scores = score_dialects(features)

    dialect = max(scores.items(), key=lambda kv: kv[1])[0] if scores else "Unknown"
    confidence = (float(scores.get(dialect, 0.0)) / 100.0) if scores else 0.0

    top_features: Dict[str, Any] = {}
    contrib_map: Mapping[str, float] = (features.get("_contributions", {}) or {}).get(dialect, {})  # type: ignore[assignment]
    for name, delta in sorted(contrib_map.items(), key=lambda kv: abs(kv[1]), reverse=True)[:6]:
        top_features[name] = {"contribution": float(delta)}

    explanation = explain_results(features, scores)
    return {
        "dialect": dialect,
        "confidence": confidence,
        "scores": scores,
        "top_features": top_features,
        "explanation": explanation,
    }