From 8339d2c7c971301e87ac25835c3b7dea5053c2dd Mon Sep 17 00:00:00 2001 From: yihong Date: Thu, 26 Dec 2024 12:17:55 +0800 Subject: [PATCH] fix: issue #11868 bring old logic back (#12100) Signed-off-by: yihong0618 --- api/core/tools/utils/text_processing_utils.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/api/core/tools/utils/text_processing_utils.py b/api/core/tools/utils/text_processing_utils.py index 6db9dfd0d9b578..105823f896788e 100644 --- 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)