From c897a1722fcd98804b585dcd045c02a086225730 Mon Sep 17 00:00:00 2001
From: weiweiw <14335254+weiweiw22@user.noreply.gitee.com>
Date: Mon, 7 Apr 2025 07:55:31 +0800
Subject: [PATCH] =?UTF-8?q?=E5=B0=86=E7=9F=A5=E8=AF=86=E5=BA=93=E6=96=87?=
 =?UTF-8?q?=E4=BB=B6=E5=88=86=E5=9D=97=E6=96=87=E4=BB=B6=E4=BF=9D=E5=AD=98?=
 =?UTF-8?q?=EF=BC=8C=E4=BD=86=E6=98=AF=E4=B8=8D=E6=98=BE=E7=A4=BA?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 .../chatchat/server/knowledge_base/utils.py   | 21 +++++++++++--------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/libs/chatchat-server/chatchat/server/knowledge_base/utils.py b/libs/chatchat-server/chatchat/server/knowledge_base/utils.py
index 0d42a2b..84f1c24 100644
--- a/libs/chatchat-server/chatchat/server/knowledge_base/utils.py
+++ b/libs/chatchat-server/chatchat/server/knowledge_base/utils.py
@@ -70,6 +70,9 @@ def list_files_from_folder(kb_name: str):
         for x in ["temp", "tmp", ".", "~$"]:
             if tail.startswith(x):
                 return True
+        if "_source.txt" in tail.lower() or "_split.txt" in tail.lower():
+            return True
+
         return False
 
     def process_entry(entry):
@@ -422,15 +425,15 @@ class KnowledgeFile:
             docs = zh_first_title_enhance(docs)
             docs = customize_zh_title_enhance(docs)
 
-            # i = 1
-            # outputfile = file_name_without_extension + "_split.txt"
-            # # 打开文件以写入模式
-            # with open(outputfile, 'w') as file:
-            #     for doc in docs:
-            #         #print(f"**********切分段{i}：{doc}")
-            #         file.write(f"\n**********切分段{i}")
-            #         file.write(doc.page_content)
-            #         i = i+1
+            i = 1
+            outputfile = file_name_without_extension + "_split.txt"
+            # 打开文件以写入模式
+            with open(outputfile, 'w') as file:
+                for doc in docs:
+                    #print(f"**********切分段{i}：{doc}")
+                    file.write(f"\n**********切分段{i}")
+                    file.write(doc.page_content)
+                    i = i+1
 
         self.splited_docs = docs
         return self.splited_docs