"""Utility helpers for Urdu classification tasks (generative mode).

Each process_docs function adds a ``target`` field with the expected
Urdu label. process_results + macro_f1_agg compute macro-averaged F1.
"""

import os as _os, sys as _sys  # noqa: E401
_sys.path.insert(0, _os.path.normpath(_os.path.join(_os.path.dirname(__file__), "..","..",)))


from f1_utils import macro_f1_agg, process_results_f1  # noqa: F401


# ── Document pre-processing ─────────────────────────────────────────


def process_fake_news_docs(dataset):
    """Map Real/Fake → حقیقی/جعلی."""
    label_map = {"Real": "حقیقی", "Fake": "جعلی"}

    def _map(doc):
        doc["target"] = label_map.get(doc["label"], doc["label"])
        return doc

    return dataset.map(_map)


def process_emotion_docs(dataset):
    """Map English emotion labels → Urdu."""
    label_map = {
        "sadness": "غم",
        "neutral": "غیر جانبدار",
        "fear": "خوف",
        "anger": "غصہ",
        "happiness": "خوشی",
        "surprise": "حیرت",
        "disgust": "نفرت",
    }

    def _map(doc):
        doc["target"] = label_map.get(doc["label"], doc["label"])
        return doc

    return dataset.map(_map)


# ── Result processing ────────────────────────────────────────────────


def process_results(doc, results):
    """Return (pred, gold) tuple for macro-F1 aggregation."""
    return process_results_f1(doc, results)