浏览代码

fix: add environment variable handling for table merging in JSON processing

myhloli 1 月之前
父节点
当前提交
43b51e78fc

+ 8 - 1
mineru/backend/pipeline/model_json_to_middle_json.py

@@ -231,7 +231,14 @@ def result_to_middle_json(model_list, images_list, pdf_doc, image_writer, lang=N
     para_split(middle_json["pdf_info"])
 
     """表格跨页合并"""
-    merge_table(middle_json["pdf_info"])
+    is_merge_table = os.getenv('MINERU_MERGE_TABLE', 'true')
+    if is_merge_table.lower() == 'true':
+        merge_table(middle_json["pdf_info"])
+    elif is_merge_table.lower() == 'false':
+        pass
+    else:
+        logger.warning(f'unknown MINERU_MERGE_TABLE config: {is_merge_table}, pass')
+        pass
 
     """llm优化"""
     llm_aided_config = get_llm_aided_config()

+ 8 - 1
mineru/backend/vlm/model_output_to_middle_json.py

@@ -110,7 +110,14 @@ def result_to_middle_json(model_output_blocks_list, images_list, pdf_doc, image_
     """表格跨页合并"""
     table_enable = get_table_enable(os.getenv('MINERU_VLM_TABLE_ENABLE', 'True').lower() == 'true')
     if table_enable:
-        merge_table(middle_json["pdf_info"])
+        is_merge_table = os.getenv('MINERU_MERGE_TABLE', 'true')
+        if is_merge_table.lower() == 'true':
+            merge_table(middle_json["pdf_info"])
+        elif is_merge_table.lower() == 'false':
+            pass
+        else:
+            logger.warning(f'unknown MINERU_MERGE_TABLE config: {is_merge_table}, pass')
+            pass
 
     """llm优化标题分级"""
     if heading_level_import_success: