from __future__ import annotations

import difflib
import re
from typing import Dict, Tuple

COCO_CLASSES: Tuple[str, ...] = (
    "person",
    "bicycle",
    "car",
    "motorcycle",
    "airplane",
    "bus",
    "train",
    "truck",
    "boat",
    "traffic light",
    "fire hydrant",
    "stop sign",
    "parking meter",
    "bench",
    "bird",
    "cat",
    "dog",
    "horse",
    "sheep",
    "cow",
    "elephant",
    "bear",
    "zebra",
    "giraffe",
    "backpack",
    "umbrella",
    "handbag",
    "tie",
    "suitcase",
    "frisbee",
    "skis",
    "snowboard",
    "sports ball",
    "kite",
    "baseball bat",
    "baseball glove",
    "skateboard",
    "surfboard",
    "tennis racket",
    "bottle",
    "wine glass",
    "cup",
    "fork",
    "knife",
    "spoon",
    "bowl",
    "banana",
    "apple",
    "sandwich",
    "orange",
    "broccoli",
    "carrot",
    "hot dog",
    "pizza",
    "donut",
    "cake",
    "chair",
    "couch",
    "potted plant",
    "bed",
    "dining table",
    "toilet",
    "tv",
    "laptop",
    "mouse",
    "remote",
    "keyboard",
    "cell phone",
    "microwave",
    "oven",
    "toaster",
    "sink",
    "refrigerator",
    "book",
    "clock",
    "vase",
    "scissors",
    "teddy bear",
    "hair drier",
    "toothbrush",
)


def coco_class_catalog() -> str:
    """Return the COCO classes in a comma-separated catalog for prompts."""

    return ", ".join(COCO_CLASSES)


def _normalize(label: str) -> str:
    return re.sub(r"[^a-z0-9]+", " ", label.lower()).strip()


_CANONICAL_LOOKUP: Dict[str, str] = {_normalize(name): name for name in COCO_CLASSES}
_COCO_SYNONYMS: Dict[str, str] = {
    "people": "person",
    "man": "person",
    "woman": "person",
    "men": "person",
    "women": "person",
    "motorbike": "motorcycle",
    "motor bike": "motorcycle",
    "bike": "bicycle",
    "aircraft": "airplane",
    "plane": "airplane",
    "jet": "airplane",
    "aeroplane": "airplane",
    "pickup": "truck",
    "pickup truck": "truck",
    "semi": "truck",
    "lorry": "truck",
    "tractor trailer": "truck",
    "coach": "bus",
    "television": "tv",
    "tv monitor": "tv",
    "mobile phone": "cell phone",
    "smartphone": "cell phone",
    "cellphone": "cell phone",
    "dinner table": "dining table",
    "sofa": "couch",
    "cooker": "oven",
}
_ALIAS_LOOKUP: Dict[str, str] = {_normalize(alias): canonical for alias, canonical in _COCO_SYNONYMS.items()}


def canonicalize_coco_name(value: str | None) -> str | None:
    """Map an arbitrary string to the closest COCO class name if possible."""

    if not value:
        return None
    normalized = _normalize(value)
    if not normalized:
        return None
    if normalized in _CANONICAL_LOOKUP:
        return _CANONICAL_LOOKUP[normalized]
    if normalized in _ALIAS_LOOKUP:
        return _ALIAS_LOOKUP[normalized]

    for alias_norm, canonical in _ALIAS_LOOKUP.items():
        if alias_norm and alias_norm in normalized:
            return canonical
    for canonical_norm, canonical in _CANONICAL_LOOKUP.items():
        if canonical_norm and canonical_norm in normalized:
            return canonical

    tokens = normalized.split()
    for token in tokens:
        if token in _CANONICAL_LOOKUP:
            return _CANONICAL_LOOKUP[token]
        if token in _ALIAS_LOOKUP:
            return _ALIAS_LOOKUP[token]

    close = difflib.get_close_matches(normalized, list(_CANONICAL_LOOKUP.keys()), n=1, cutoff=0.82)
    if close:
        return _CANONICAL_LOOKUP[close[0]]
    return None