fix: issue #11868 bring old logic back (#12100)

Signed-off-by: yihong0618 <[email protected]>
langgenius · Dec 26, 2024 · 8339d2c · 8339d2c
1 parent 811e4bd
commit 8339d2c
Showing 1 changed file with 2 additions and 1 deletion.
diff --git a/api/core/tools/utils/text_processing_utils.py b/api/core/tools/utils/text_processing_utils.py
@@ -12,5 +12,6 @@ def remove_leading_symbols(text: str) -> str:
         str: The text with leading punctuation or symbols removed.
     """
     # Match Unicode ranges for punctuation and symbols
-    pattern = r"^[\u2000-\u206F\u2E00-\u2E7F\u3000-\u303F!\"#$%&'()*+,\-./:;<=>?@\[\]^_`{|}~]+"
+    # FIXME this pattern is confused quick fix for #11868 maybe refactor it later
+    pattern = r"^[\u2000-\u206F\u2E00-\u2E7F\u3000-\u303F!\"#$%&'()*+,./:;<=>?@^_`~]+"
     return re.sub(pattern, "", text)