更新 chunk_text.py

切片增加型号信息

chunk_text.py

@@ -898,8 +898,8 @@ def find_ship_info_by_hull(json_file_path, data):
     except json.JSONDecodeError:
         print("错误：JSON 文件格式不正确")
         return None
-def merge_short_slices(slices, min_length=30,filename="163-06A0014-B01001_发动机-维修手册.pdf"):
-    """
+def merge_short_slices(slices, min_length=30,filename="122-06A0014-B01003_雷达-使用说明书.pdf"):
+    """ 
     合并过短的切片：
     - 如果某切片 content 长度 <= min_length，则将其合并到下一个切片的开头
     - 若处于末尾无下一个切片，则反向合并到上一个切片末尾
@@ -908,6 +908,8 @@ def merge_short_slices(slices, min_length=30,filename="163-06A0014-B01001_发动
     Args:
         slices: [{"content": str, "positions": [...]}]
         min_length: 短切片的字符长度阈值（含）
+        filename: 用于实体提取的文件名
+    
     Returns:
         合并后的 slices 列表
     """
@@ -915,7 +917,7 @@ def merge_short_slices(slices, min_length=30,filename="163-06A0014-B01001_发动
         return slices
 
     result = []
-    pending_contents = []   # 缓存等待合并到"下一个"的短切片 content
+    pending_contents = []  # 缓存等待合并到"下一个"的短切片 content
     pending_positions = []  # 缓存对应的 positions
 
     for ins in slices:
@@ -934,6 +936,7 @@ def merge_short_slices(slices, min_length=30,filename="163-06A0014-B01001_发动
                 positions = pending_positions + positions
                 pending_contents = []
                 pending_positions = []
+            
             result.append({
                 "content": content,
                 "positions": positions
@@ -953,35 +956,43 @@ def merge_short_slices(slices, min_length=30,filename="163-06A0014-B01001_发动
                 "content": merged_suffix,
                 "positions": pending_positions
             })
+
     try:
         final_result = get_entity(filename)
-        print(final_result)
-        xinghao = find_ship_info_by_hull(SHIP_MODEL_NAME,final_result)
-        if xinghao.get('model_name'):
+        xinghao = find_ship_info_by_hull(SHIP_MODEL_NAME, final_result)
+        if xinghao is None:  # 确保 xinghao 为 None 时不会报错
+            xinghao = {"model_name": "", "ship_name": ""}
+            print("未找到匹配的舰船信息")
+
+        # 安全处理 xinghao 为 None 的情况
+        model_name = ""
+        if xinghao and 'model_name' in xinghao:
             model_name = xinghao['model_name']
-        else:
-            model_name = ""
-        # lower_entity = final_result.get("low_level")
-        otehr_data = format_entity_text(final_result)
-        logger.info(f"文件名实体提取成功: {otehr_data}")
+            
+        other_data = format_entity_text(final_result)
+        logger.info(f"文件名实体提取成功: {other_data}")
     except Exception as e:
         logger.warning(f"文件名实体提取失败: {e}")
-        otehr_data = ""  # 建议加个兜底,避免后面 NameError
+        other_data = ""
+        model_name = ""  # 确保异常时 model_name 有定义
 
+    # 将提取的信息（如舰艇名、型号）注入到每个切片的开头
     for ins in result:
         content = ins['content']
-        if not otehr_data:
-            continue
+        # 如果没有提取到有效数据，则跳过注入
+            
         newline_idx = content.find('\n')
-        # 拼接成一个括号：otehr_data + 型号为xxx
-        info = otehr_data
+        info = other_data
         if model_name:
             info += f'，型号为{model_name}'
         suffix = f'({info})'
+        
+        # 将信息插入到第一行末尾
         if newline_idx == -1:
             ins['content'] = content + suffix
         else:
             ins['content'] = content[:newline_idx] + suffix + content[newline_idx:]
+
     return result
 def find_and_read_content_list(directory, original_filename, encoding='utf-8'):
     """
@@ -1133,8 +1144,3 @@ if __name__ == "__main__":
 
     for ins in slices_2:
         print(ins)
-
-
-
-
-