translit

requirements.txt

@@ -14,3 +14,4 @@ tqdm~=4.65.0
 peewee~=3.15.4
 ffmpeg-python~=0.2.0
 platformdirs~=3.2.0
+transliterate~=1.10.2

src/music_kraken/utils/string_processing.py

@@ -1,12 +1,22 @@
+from transliterate.exceptions import LanguageDetectionError
+from transliterate import translit
+
+
 def unify(string: str) -> str:
     """
-    returns an unified str, to make comparosons easy.
-    an unified string has following attributes:
+    returns a unified str, to make comparisons easy.
+    a unified string has the following attributes:
      - is lowercase
     """
 
+    try:
+        string = translit(string, reversed=True)
+    except LanguageDetectionError:
+        pass
+
     return string.lower()
 
+
 def fit_to_file_system(string: str) -> str:
     string = string.strip()
 
@@ -19,4 +29,3 @@ def fit_to_file_system(string: str) -> str:
     string = string.replace("/", "|").replace("\\", "|")
 
     return string
-