progress

lyric_search_new/utils.py

@@ -2,7 +2,7 @@
 
 from difflib import SequenceMatcher
 from typing import List, Optional, Tuple
-import re
+import regex
 
 class TrackMatcher:
     """Track Matcher"""
@@ -16,16 +16,16 @@ class TrackMatcher:
         """
         self.threshold = threshold
 
-    def find_best_match(self, input_track: str, candidate_tracks: List[str]) -> Optional[Tuple[str, float]]:
+    def find_best_match(self, input_track: str, candidate_tracks: List[tuple[int|str, str]]) -> Optional[Tuple[str, float]]:
         """
         Find the best matching track from the candidate list.
         
         Args:
             input_track (str): Input track in "ARTIST - SONG" format
-            candidate_tracks (List[str]): List of candidate tracks in same format
+            candidate_tracks (List[tuple[int, str]]): List of candidate tracks
             
         Returns:
-            Optional[Tuple[str, float]]: Tuple of (best matching track, similarity score)
+            Optional[Tuple[int, str, float]]: Tuple of (best matching track, similarity score)
                                        or None if no good match found
         """
         if not input_track or not candidate_tracks:
@@ -33,12 +33,14 @@ class TrackMatcher:
 
         # Normalize input track
         input_track = self._normalize_string(input_track)
+
+        print(f"input_track: {input_track}")
         
         best_match = None
         best_score = 0
 
         for candidate in candidate_tracks:
-            normalized_candidate = self._normalize_string(candidate)
+            normalized_candidate = self._normalize_string(candidate[1])
             
             # Calculate various similarity scores
             exact_score = 1.0 if input_track == normalized_candidate else 0.0
@@ -61,7 +63,7 @@ class TrackMatcher:
         extra spaces, and converting to lowercase.
         """
         # Remove special characters and convert to lowercase
-        text = re.sub(r'[^\w\s-]', '', text.lower())
+        text = regex.sub(r'[^\w\s-]', '', text.lower())
         # Normalize spaces
         text = ' '.join(text.split())
         return text
@@ -79,4 +81,16 @@ class TrackMatcher:
         intersection = tokens1.intersection(tokens2)
         union = tokens1.union(tokens2)
         
-        return len(intersection) / len(union)
+        return len(intersection) / len(union)
+    
+class DataUtils:
+    """
+    Data Utils
+    """
+    def scrub_lyrics(self, lyrics: str) -> str:
+        # Regex chain
+        lyrics = regex.sub(r'(\[.*?\])(\s){0,}(\:){0,1}', '', lyrics)
+        lyrics = regex.sub(r'(\d?)(Embed\b)', '', lyrics, flags=regex.IGNORECASE)
+        lyrics = regex.sub(r'\n{2}', '\n', lyrics)  # Gaps between verses
+        lyrics = regex.sub(r'[0-9]\b$', '', lyrics)
+        return lyrics