Try more encodings when parsing song file

karaokatalog/organize/move.py

@@ -5,7 +5,7 @@ from pathlib import Path
 from karaokatalog.instructions.MoveInstruction import MoveInstruction
 from karaokatalog.Song import Song
 
-FORBIDDEN_CHARACTERS = re.compile(r'[/<>:"\\|?*]')
+FORBIDDEN_CHARACTERS = re.compile(r'[\/<>:"\\|?*]')
 
 
 def _get_canonical_song_dir(song: Song, variant: int = 0) -> Path:

karaokatalog/parse_song_txt.py

@@ -26,8 +26,20 @@ def _parse_tag_line(tag_line: str) -> tuple[str, str | None]:
     )
 
 
-def parse_song_txt(song_txt: Path) -> dict[str, Any]:
+def _parse_song_txt_with_encoding(song_txt: Path, encoding: str) -> dict[str, Any]:
-    with song_txt.open(encoding="utf-8", errors="ignore") as f:
+    with song_txt.open(encoding=encoding) as f:
         tags = dict(_parse_tag_line(line) for line in f if line.startswith("#"))
 
     return tags
+
+
+def parse_song_txt(song_txt: Path) -> dict[str, Any]:
+    encodings_to_try = ("utf-8", "cp1252")
+
+    for encoding_to_try in encodings_to_try:
+        try:
+            return _parse_song_txt_with_encoding(song_txt, encoding_to_try)
+        except UnicodeDecodeError:
+            pass
+
+    raise UnicodeError(f"Could not guess encoding for {song_txt}")