fix: improve OCR indexing and evidence review

backend/wisegrade/parsing.py

@@ -1,6 +1,7 @@
 import subprocess
 import tempfile
 from functools import lru_cache
+from importlib.metadata import version
 from pathlib import Path
 from threading import Lock
 
@@ -30,11 +31,21 @@ def _ocr_engine(model_dir: str):
         from paddleocr import PaddleOCR
     except ImportError as exc:
         raise RuntimeError("扫描PDF需要PaddleOCR；请安装OCR依赖或交由教师处理") from exc
-    try:
-        return PaddleOCR(lang="ch", text_detection_model_dir=str(detection), text_recognition_model_dir=str(recognition),
-                         use_textline_orientation=False, use_doc_orientation_classify=False, use_doc_unwarping=False)
-    except TypeError:
-        return PaddleOCR(lang="ch", det_model_dir=str(detection), rec_model_dir=str(recognition), use_angle_cls=False, show_log=False)
+    if int(version("paddleocr").split(".")[0]) >= 3:
+        def model_name(directory):
+            config = directory / "inference.yml"
+            if not config.is_file():
+                raise RuntimeError(f"离线OCR模型缺少 inference.yml: {directory}")
+            for line in config.read_text(encoding="utf-8").splitlines():
+                if line.strip().startswith("model_name:"):
+                    return line.split(":", 1)[1].strip().strip("'\"")
+            raise RuntimeError(f"离线OCR模型未声明 model_name: {config}")
+
+        return PaddleOCR(text_detection_model_name=model_name(detection), text_detection_model_dir=str(detection),
+                         text_recognition_model_name=model_name(recognition), text_recognition_model_dir=str(recognition),
+                         use_textline_orientation=False, use_doc_orientation_classify=False, use_doc_unwarping=False,
+                         device="cpu", enable_mkldnn=False)
+    return PaddleOCR(lang="ch", det_model_dir=str(detection), rec_model_dir=str(recognition), use_angle_cls=False, show_log=False)
 
 
 def _ocr(image_path: str):