Merge pull request #302 from yolain/v1.2.2-beta

Fix filtering embedding carries chinese #299
2024-08-11 12:30:18 +08:00
parent 9e85e3a25c f1ab83f429
commit ef64db05e3
1 changed files with 1 additions and 1 deletions
@@ -80,7 +80,7 @@ def has_chinese(text):
    _text = text
    _text = re.sub(r'<.*?>', '', _text)
    _text = re.sub(r'__.*?__', '', _text)
-    _text = re.sub(r'embedding:.*?(\d+)?', '', _text)
+    _text = re.sub(r'embedding:.*?$', '', _text)
    for char in _text:
        if '\u4e00' <= char <= '\u9fff':
            has_cn = True