Merge pull request #15 from LlmKira/dev-20250304

✨ feat(app): improve language detection by normalizing input

Author: sudoskys

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "fast-langdetect"
-version = "0.3.1"
+version = "0.3.2"
 description = "Quickly detect text language and segment language"
 authors = [
     { name = "sudoskys", email = "coldlando@hotmail.com" },

src/fast_langdetect/__init__.py

@@ -12,14 +12,14 @@ def is_japanese(string):
     return False
 
 
-def detect_language(sentence, *, low_memory: bool = True):
+def detect_language(sentence: str, *, low_memory: bool = True):
     """
     Detect language
     :param sentence: str sentence
     :param low_memory: bool (default: True) whether to use low memory mode
     :return: ZH, EN, JA, KO, FR, DE, ES, .... (two uppercase letters)
     """
-    lang_code = detect(sentence, low_memory=low_memory).get("lang").upper()
+    lang_code = detect(sentence.lower(), low_memory=low_memory).get("lang").upper()
     if lang_code == "JA" and not is_japanese(sentence):
         lang_code = "ZH"
     return lang_code