feat: 更新parse_mineru_data函数，添加对table_cells的解析，优化表格单元格数据处理

ocr_validator_utils.py

@@ -337,6 +337,21 @@ def parse_mineru_data(data: List, config: Dict, tool_name="mineru") -> List[Dict
                     'img_path': img_path,
                     'table_body': table_html
                 })
+            table_cells = item.get(tool_config.get('table_cells_field', 'table_cells'), [])
+            for cell in table_cells:
+                cell_text = cell.get('text', '')
+                cell_bbox = cell.get('bbox', [])
+                if cell_text and cell_bbox and len(cell_bbox) >= 4:
+                    parsed_data.append({
+                        'text': str(cell_text).strip(),
+                        'bbox': cell_bbox[:4],
+                        'row': cell.get('row', -1),
+                        'col': cell.get('col', -1),
+                        'category': 'table_cell',
+                        'confidence': cell.get('score', 0.0),
+                        'source_tool': tool_name,
+                    })
+        # 处理图片类型
         elif category == 'image':
             img_path = item.get(tool_config.get('img_path_field', 'img_path'), '')
             if bbox and len(bbox) >= 4:
@@ -348,17 +363,6 @@ def parse_mineru_data(data: List, config: Dict, tool_name="mineru") -> List[Dict
                     'source_tool': tool_name,
                     'img_path': img_path
                 })
-        elif category == 'table_cell':
-            if bbox and len(bbox) >= 4:
-                parsed_data.append({
-                    'text': str(text).strip(),
-                    'bbox': bbox[:4],
-                    'row': item.get('row', -1),
-                    'col': item.get('col', -1),
-                    'category': 'table_cell',
-                    'confidence': confidence,
-                    'source_tool': tool_name,
-                })
         else:
             # 其他类型，按文本处理,  header, table_cell, ...
             if text and bbox and len(bbox) >= 4: