feat: 添加 PDF 类型检测功能，优化文档处理逻辑，支持文本和 OCR 页面的识别

ocr_tools/universal_doc_parser/core/element_processors.py

@@ -326,6 +326,7 @@ class ElementProcessors:
         layout_item: Dict[str, Any],
         scale: float,
         pre_matched_spans: Optional[List[Dict[str, Any]]] = None,
+        pdf_type: str = 'ocr', # 'ocr' 或 'txt'
         output_dir: Optional[str] = None,
         basename: Optional[str] = None
     ) -> Dict[str, Any]:
@@ -376,6 +377,7 @@ class ElementProcessors:
                 table_image=cropped_table,
                 # ocr_boxes=ocr_boxes_for_wired,
                 ocr_boxes=ocr_boxes,
+                pdf_type=pdf_type,
                 debug_options=debug_opts_override
             )