diff --git a/spacy/lang/fr/tokenizer_exceptions.py b/spacy/lang/fr/tokenizer_exceptions.py index 997a81534..b0f188278 100644 --- a/spacy/lang/fr/tokenizer_exceptions.py +++ b/spacy/lang/fr/tokenizer_exceptions.py @@ -423,5 +423,5 @@ _regular_exp.append(URL_PATTERN) TOKENIZER_EXCEPTIONS = _exc TOKEN_MATCH = re.compile( - "|".join("(?:{})".format(m) for m in _regular_exp), re.IGNORECASE + "|".join("(?:{})".format(m) for m in _regular_exp), re.IGNORECASE, re.UNICODE ).match