"""
OCR engine using rapidocr-onnxruntime (PP-OCRv4 weights).

No PaddlePaddle dependency — pure ONNX Runtime. Language packs are
downloaded automatically by rapidocr on first use.
"""
import logging

import numpy as np

from app.config import VisionSettings
from app.services.vision.base import OCREngine, OCRResult

logger = logging.getLogger(__name__)


class RapidOCREngine(OCREngine):
    def __init__(self, settings: VisionSettings):
        from rapidocr_onnxruntime import RapidOCR

        self._min_confidence = settings.ocr.min_confidence
        self._engine = RapidOCR()
        logger.info("RapidOCR engine initialized")

    def run(self, image: np.ndarray) -> list[OCRResult]:
        result, _ = self._engine(image)
        if not result:
            return []

        out = []
        for box, text, score in result:
            if score < self._min_confidence:
                continue
            # box is [[x1,y1],[x2,y2],[x3,y3],[x4,y4]] — take bounding rect
            xs = [p[0] for p in box]
            ys = [p[1] for p in box]
            h, w = image.shape[:2]
            bbox = [
                min(xs) / w,
                min(ys) / h,
                max(xs) / w,
                max(ys) / h,
            ]
            out.append(OCRResult(text=text, confidence=float(score), bbox=bbox))
        return out