|
|
@@ -12,12 +12,20 @@ if not os.getenv("FTLANG_CACHE"):
|
|
|
from fast_langdetect import detect_language
|
|
|
|
|
|
|
|
|
+def remove_invalid_surrogates(text):
|
|
|
+ # 移除无效的 UTF-16 代理对
|
|
|
+ return ''.join(c for c in text if not (0xD800 <= ord(c) <= 0xDFFF))
|
|
|
+
|
|
|
+
|
|
|
def detect_lang(text: str) -> str:
|
|
|
|
|
|
if len(text) == 0:
|
|
|
return ""
|
|
|
|
|
|
text = text.replace("\n", "")
|
|
|
+ text = remove_invalid_surrogates(text)
|
|
|
+
|
|
|
+ # print(text)
|
|
|
try:
|
|
|
lang_upper = detect_language(text)
|
|
|
except:
|
|
|
@@ -37,3 +45,4 @@ if __name__ == '__main__':
|
|
|
print(detect_lang("<html>This is a test</html>"))
|
|
|
print(detect_lang("这个是中文测试。"))
|
|
|
print(detect_lang("<html>这个是中文测试。</html>"))
|
|
|
+ print(detect_lang("〖\ud835\udc46\ud835〗这是个包含utf-16的中文测试"))
|
myhloli