12.4

flask_app/general/doubao.py

@@ -2,6 +2,8 @@ import os
 
 import PyPDF2
 import requests
+from ratelimit import sleep_and_retry, limits
+
 from flask_app.general.file2markdown import convert_pdf_to_markdown
 
 from flask_app.general.clean_pdf import extract_common_header, clean_page_content
@@ -58,7 +60,8 @@ def read_txt_to_string(file_path):
     except Exception as e:
         return f"错误：读取文件时发生错误。详细信息：{e}"
 
-
+@sleep_and_retry
+@limits(calls=10, period=1)  # 每秒最多调用4次
 def doubao_model(full_user_query):
     print("call doubao...")
     # 相关参数

flask_app/货物标/技术参数要求提取后处理函数.py

@@ -187,12 +187,25 @@ def restructure_data(data):
 def get_prefixes(s):
     prefixes = []
     for i in range(len(s)):
-        if s[i] == '：':
+        if s[i] in ['：', ':']:
             prefixes.append(s[:i+1])
     return prefixes
 
 # 定义删除公共前缀的函数
-def remove_common_prefixes(string_list):
+def remove_common_prefixes(string_list, min_occurrence=3):
+    """
+    删除列表中所有满足出现次数>= min_occurrence 的公共前缀。
+
+    Args:
+        string_list (list): 字符串列表。
+        min_occurrence (int): 前缀至少出现的次数。
+
+    Returns:
+        list: 删除公共前缀后的字符串列表。
+    """
+    if not string_list:
+        return string_list
+
     # 构建前缀到字符串集合的映射
     prefix_to_strings = {}
     for s in string_list:
@@ -202,20 +215,31 @@ def remove_common_prefixes(string_list):
             if prefix not in prefix_to_strings:
                 prefix_to_strings[prefix] = set()
             prefix_to_strings[prefix].add(s)
-    # 找出至少在两个字符串中出现的前缀
-    prefixes_occuring_in_multiple_strings = [prefix for prefix, strings in prefix_to_strings.items() if len(strings) >=2]
-    # 对每个字符串，找到其匹配的最长前缀并删除
+
+    # 找出所有出现次数 >= min_occurrence 的前缀
+    qualifying_prefixes = [prefix for prefix, strings in prefix_to_strings.items() if len(strings) >= min_occurrence]
+
+    if not qualifying_prefixes:
+        # 没有满足条件的公共前缀，返回原列表
+        return string_list
+
+    # 为了确保较长的前缀先被匹配，按长度降序排序
+    qualifying_prefixes.sort(key=len, reverse=True)
+
+    # 对每个字符串，循环删除所有匹配的前缀
     new_string_list = []
     for s in string_list:
-        applicable_prefixes = [prefix for prefix in prefixes_occuring_in_multiple_strings if s.startswith(prefix)]
-        if applicable_prefixes:
-            # 找到最长的前缀
-            longest_prefix = max(applicable_prefixes, key=len)
-            # 删除前缀
-            new_s = s[len(longest_prefix):]
-            new_string_list.append(new_s)
-        else:
-            new_string_list.append(s)
+        original_s = s
+        changed = True
+        while changed:
+            changed = False
+            for prefix in qualifying_prefixes:
+                if s.startswith(prefix):
+                    s = s[len(prefix):]
+                    changed = True
+                    # 一旦删除一个前缀，重新开始检查，以处理可能的多个前缀
+                    break
+        new_string_list.append(s)
     return new_string_list
 
 if __name__ == "__main__":