From 416bd9ebc7564ea4b081906e0c3bcc37d965ef63 Mon Sep 17 00:00:00 2001
From: yuehuazhang <yuehuazhang@tencent.com>
Date: Tue, 7 Jan 2025 09:07:39 +0800
Subject: [PATCH] fix:SyntaxWarning: invalid escape sequence '\s'

---
 .../server/file_rag/text_splitter/ali_text_splitter.py    | 4 ++--
 .../text_splitter/chinese_recursive_text_splitter.py      | 8 ++++----
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/chatchat-server/chatchat/server/file_rag/text_splitter/ali_text_splitter.py b/chatchat-server/chatchat/server/file_rag/text_splitter/ali_text_splitter.py
index 9def31a..85d9526 100644
--- a/chatchat-server/chatchat/server/file_rag/text_splitter/ali_text_splitter.py
+++ b/chatchat-server/chatchat/server/file_rag/text_splitter/ali_text_splitter.py
@@ -15,8 +15,8 @@ def split_text(self, text: str) -> List[str]:
         # 考虑到使用了三个模型，可能对于低配置gpu不太友好，因此这里将模型load进cpu计算，有需要的话可以替换device为自己的显卡id
         if self.pdf:
             text = re.sub(r"\n{3,}", r"\n", text)
-            text = re.sub("\s", " ", text)
-            text = re.sub("\n\n", "", text)
+            text = re.sub(r"\s", " ", text)
+            text = re.sub(r"\n\n", "", text)
         try:
             from modelscope.pipelines import pipeline
         except ImportError:
diff --git a/chatchat-server/chatchat/server/file_rag/text_splitter/chinese_recursive_text_splitter.py b/chatchat-server/chatchat/server/file_rag/text_splitter/chinese_recursive_text_splitter.py
index 5445dd7..aabe19b 100644
--- a/chatchat-server/chatchat/server/file_rag/text_splitter/chinese_recursive_text_splitter.py
+++ b/chatchat-server/chatchat/server/file_rag/text_splitter/chinese_recursive_text_splitter.py
@@ -41,10 +41,10 @@ def __init__(
         self._separators = separators or [
             "\n\n",
             "\n",
-            "。|！|？",
-            "\.\s|\!\s|\?\s",
-            "；|;\s",
-            "，|,\s",
+            r"。|！|？",
+            r"\.\s|\!\s|\?\s",
+            r"；|;\s",
+            r"，|,\s",
         ]
         self._is_separator_regex = is_separator_regex