Merge pull request #16 from myhloli/dev

Dev

README.md

@@ -44,6 +44,9 @@
 
 # Changelog
 
+- 2025/09/10 2.2.2 Released
+  - Fixed the issue where the new table recognition model would affect the overall parsing task when some table parsing failed
+
 - 2025/09/08 2.2.1 Released  
   - Fixed the issue where some newly added models were not downloaded when using the model download command.
 

README_zh-CN.md

@@ -44,6 +44,9 @@
 
 # 更新记录
 
+- 2025/09/10 2.2.2 发布
+  - 修复新的表格识别模型在部分表格解析失败时影响整体解析任务的问题
+
 - 2025/09/08 2.2.1 发布
   - 修复使用模型下载命令时，部分新增模型未下载的问题
 

mineru/backend/pipeline/batch_analyze.py

@@ -221,7 +221,7 @@ class BatchAnalyze:
 
             # 表格格式清理
             for table_res_dict in table_res_list_all_page:
-                html_code = table_res_dict["table_res"].get("html", "")
+                html_code = table_res_dict["table_res"].get("html", "") or ""
 
                 # 检查html_code是否包含'<table>'和'</table>'
                 if "<table>" in html_code and "</table>" in html_code:

mineru/model/table/rec/unet_table/main.py

@@ -337,5 +337,5 @@ class UnetTableModel:
 
             return html_code
         except Exception as e:
-            logger.exception(e)
-            return None
+            logger.warning(e)
+            return wireless_html_code

mineru/version.py

@@ -1 +1 @@
-__version__ = "2.2.1"
+__version__ = "2.2.2"