From 94f2956e3adf8de0e30d49bdf3f53645f204acf4 Mon Sep 17 00:00:00 2001
From: jyong <718720800@qq.com>
Date: Thu, 4 Sep 2025 14:52:23 +0800
Subject: [PATCH] fix file name

---
 api/models/dataset.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/api/models/dataset.py b/api/models/dataset.py
index 89da8ac8ce..e00b5ad00d 100644
--- a/api/models/dataset.py
+++ b/api/models/dataset.py
@@ -820,7 +820,8 @@ class DocumentSegment(Base):
             signed_urls.append((match.start(), match.end(), signed_url))
 
         # For tools directory - direct file formats (e.g., .png, .jpg, etc.)
-        pattern = r"/files/tools/([a-f0-9\-]+)\.([a-zA-Z0-9]+)(?:\?.*?)?"
+        # Match URL including any query parameters up to common URL boundaries (space, parenthesis, quotes)
+        pattern = r"/files/tools/([a-f0-9\-]+)\.([a-zA-Z0-9]+)(?:\?[^\s\)\"\']*)?"
         matches = re.finditer(pattern, text)
         for match in matches:
             upload_file_id = match.group(1)