ebc633fb36
Introduce pluggable OcrEngine ABC with PaddleOCR PP-OCRv4 as primary engine and Tesseract wrapper for backward compatibility. Engine factory reads OCR_PRIMARY_ENGINE config to instantiate the correct engine. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
53 lines
1.6 KiB
Python
53 lines
1.6 KiB
Python
"""Factory function for creating OCR engine instances from configuration."""
|
|
|
|
import logging
|
|
|
|
from app.config import settings
|
|
from app.engines.base_engine import EngineUnavailableError, OcrEngine
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
# Valid engine identifiers
|
|
_ENGINE_REGISTRY: dict[str, str] = {
|
|
"paddleocr": "app.engines.paddle_engine.PaddleOcrEngine",
|
|
"tesseract": "app.engines.tesseract_engine.TesseractEngine",
|
|
}
|
|
|
|
|
|
def create_engine(engine_name: str | None = None) -> OcrEngine:
|
|
"""Instantiate an OCR engine by name (defaults to config value).
|
|
|
|
Args:
|
|
engine_name: Engine identifier ("paddleocr", "tesseract").
|
|
Falls back to ``settings.ocr_primary_engine``.
|
|
|
|
Returns:
|
|
Initialized OcrEngine instance.
|
|
|
|
Raises:
|
|
EngineUnavailableError: If the engine cannot be loaded or initialized.
|
|
"""
|
|
name = (engine_name or settings.ocr_primary_engine).lower().strip()
|
|
|
|
if name not in _ENGINE_REGISTRY:
|
|
raise EngineUnavailableError(
|
|
f"Unknown engine '{name}'. Available: {list(_ENGINE_REGISTRY.keys())}"
|
|
)
|
|
|
|
module_path, class_name = _ENGINE_REGISTRY[name].rsplit(".", 1)
|
|
|
|
try:
|
|
import importlib
|
|
|
|
module = importlib.import_module(module_path)
|
|
engine_cls = getattr(module, class_name)
|
|
engine: OcrEngine = engine_cls()
|
|
logger.info("Created OCR engine: %s", name)
|
|
return engine
|
|
except EngineUnavailableError:
|
|
raise
|
|
except Exception as exc:
|
|
raise EngineUnavailableError(
|
|
f"Failed to create engine '{name}': {exc}"
|
|
) from exc
|