doc_processer/app/core/dependencies.py

"""Application dependencies."""

from app.services.image_processor import ImageProcessor
from app.services.layout_detector import LayoutDetector
from app.services.ocr_service import OCRService, MineruOCRService
from app.services.converter import Converter
from app.core.config import get_settings

# Global instances (initialized on startup)
_layout_detector: LayoutDetector | None = None


def init_layout_detector() -> None:
    """Initialize the global layout detector.

    Called during application startup.
    """
    global _layout_detector
    _layout_detector = LayoutDetector()


def get_layout_detector() -> LayoutDetector:
    """Get the global layout detector instance."""
    if _layout_detector is None:
        raise RuntimeError("Layout detector not initialized. Call init_layout_detector() first.")
    return _layout_detector


def get_image_processor() -> ImageProcessor:
    """Get an image processor instance."""
    return ImageProcessor()


def get_ocr_service() -> OCRService:
    """Get an OCR service instance."""
    return OCRService(
        vl_server_url=get_settings().paddleocr_vl_url,
        layout_detector=get_layout_detector(),
        image_processor=get_image_processor(),
        converter=get_converter(),
    )


def get_converter() -> Converter:
    """Get a DOCX converter instance."""
    return Converter()


def get_mineru_ocr_service() -> MineruOCRService:
    """Get a MinerOCR service instance."""
    settings = get_settings()
    api_url = getattr(settings, 'miner_ocr_api_url', 'http://127.0.0.1:8000/file_parse')
    return MineruOCRService(
        api_url=api_url,
        converter=get_converter(),
        image_processor=get_image_processor(),
    )