From 7fefb39e58eba639062870a49836c07944a726dd Mon Sep 17 00:00:00 2001 From: Adriane Boyd Date: Tue, 9 Aug 2022 10:59:36 +0200 Subject: [PATCH] Fix regex invalid escape sequences (#11276) --- spacy/lang/ko/punctuation.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/spacy/lang/ko/punctuation.py b/spacy/lang/ko/punctuation.py index 7f7b40c5b..f5f1c51da 100644 --- a/spacy/lang/ko/punctuation.py +++ b/spacy/lang/ko/punctuation.py @@ -3,7 +3,7 @@ from ..punctuation import TOKENIZER_INFIXES as BASE_TOKENIZER_INFIXES _infixes = ( - ["·", "ㆍ", "\(", "\)"] + ["·", "ㆍ", r"\(", r"\)"] + [r"(?<=[0-9])~(?=[0-9-])"] + LIST_QUOTES + BASE_TOKENIZER_INFIXES