"""Surya OCR engine wrapper — transformer-based, handles typewritten and modern Latin handwriting."""

import logging

logger = logging.getLogger(__name__)

_recognition_predictor = None
_detection_predictor = None


def load_models():
    """Eagerly load Surya models into memory. Called once at container startup."""
    global _recognition_predictor, _detection_predictor

    logger.info("Loading Surya models...")

    from surya.foundation import FoundationPredictor
    from surya.recognition import RecognitionPredictor
    from surya.detection import DetectionPredictor

    foundation_predictor = FoundationPredictor()
    _recognition_predictor = RecognitionPredictor(foundation_predictor)
    _detection_predictor = DetectionPredictor()

    logger.info("Surya models loaded successfully")


def extract_blocks(images: list, language: str = "de") -> list[dict]:
    """Run Surya OCR on a list of PIL images (one per page).

    Returns a flat list of block dicts with pageNumber, x, y, width, height,
    polygon, text. Coordinates are normalized to [0, 1] relative to page dimensions.
    Surya 0.17+ returns polygon (4-point) natively on each text line.
    """
    all_blocks = []

    predictions = _recognition_predictor(images, det_predictor=_detection_predictor)

    for page_idx, page_pred in enumerate(predictions):
        page_w, page_h = images[page_idx].size

        for line in page_pred.text_lines:
            bbox = line.bbox  # [x1, y1, x2, y2] in pixel coordinates
            x1, y1, x2, y2 = bbox

            # Surya 0.17 provides polygon as list of (x, y) tuples (4 points, clockwise)
            polygon = None
            if hasattr(line, "polygon") and line.polygon and len(line.polygon) == 4:
                polygon = [
                    [p[0] / page_w, p[1] / page_h]
                    for p in line.polygon
                ]

            # Extract word-level confidence for [unleserlich] marking
            words = []
            if hasattr(line, "words") and line.words:
                for word in line.words:
                    words.append({
                        "text": word.text,
                        "confidence": word.confidence,
                    })
            else:
                words = [{"text": line.text, "confidence": getattr(line, "confidence", 1.0)}]

            all_blocks.append({
                "pageNumber": page_idx,
                "x": x1 / page_w,
                "y": y1 / page_h,
                "width": (x2 - x1) / page_w,
                "height": (y2 - y1) / page_h,
                "polygon": polygon,
                "text": line.text,
                "words": words,
            })

    return all_blocks