finalize metadata edit_database

asd

audiobook_metadata/metadata_genre_edit_database.py

@@ -39,6 +39,11 @@ def main():
         action="store_true",
         help="Print data only",
     )
+    parser.add_argument(
+        "--print-all",
+        action="store_true",
+        help="Print all data only",
+    )
     parser.add_argument(
         "database",
         type=Path,
@@ -56,9 +61,11 @@ def main():
     cur = db.cursor()
 
     list_genres = load_genre(cur,True)
+    if args.print_all:
+        for genre in list_genres:
+            print(genre)
+        return
 
-    #for genre in list_genres:
-    #    print(genre)
     rows = cur.execute(
         "SELECT id, genres FROM books"
     ).fetchall()
@@ -67,34 +74,75 @@ def main():
         if not genres_json:
             continue
         genres = json.loads(genres_json)
+        genres_new = []
         new_genres = []
         print("=================================")
         print(f"Before sed: {genres}")
         for genre in genres:
+            if "Drachen" in genre:
+                pass
+            if "Fantastic" in genre:
+                pass
             genre = re.sub(r'(?i)^audio\s*books?$', '', genre)
             genre = re.sub(r'(?i)^audiobooks?$', '', genre)
-            genre = re.sub(r'(?i)\bhörb(uch|ücher)\b', '', genre)
+            genre = re.sub(r'(?i)\b(hörb(uch|ücher)|hoerb(uch|uecher))\b', '', genre)
             genre = re.sub(r'(?i)^(hörspiele?|hoerspiele?)$', '', genre)
             genre = re.sub(r'(?i)^spoken\s*word$', '', genre)
+            genre = re.sub(r'(?i)gesprochene\s*inhalte$', '', genre)
             genre = re.sub(r'(?i)^speech$', '', genre)
+            genre = re.sub(r'Fanasie', 'Fantasie', genre)
+            genre = re.sub(r'Mit Videospiel', 'Videospielbezug', genre)
+            genre = re.sub(r'(?i)nonfiction', 'NonFiction', genre)
+
+            genre = re.sub(r'(?i)^speech$', '', genre)
+            genre = re.sub(r'(?i)^vocal$', '', genre)
+            genre = re.sub(r'(?i)^retail$', '', genre)
+            genre = re.sub(r'(?i)^other$', '', genre)
+            genre = re.sub(r'(?i)^misc$', '', genre)
 
             genre = re.sub(r'(?i)^(sci[- ]?fi|sf)$', 'Science Fiction', genre)
-            genre = re.sub(r'(?i)^nonfiction$', 'NonFiction', genre)
+            genre = re.sub(r'(?i)^\(?science fiction\)?$', 'Science Fiction', genre)
-
+            genre = re.sub(r'Thrillers', 'Thriller', genre)
+            genre = re.sub(r"(?i)\bchildren'?s audiobooks?\b", "",genre)
             genre = re.sub(r'^-\s*|\s*-$', '', genre)
+            genre = re.sub(r'(?i)Engelske\s*\sLydbånd','',genre)
+            genre = re.sub(r'^FIC028000.*$', '', genre)
+            genre = re.sub(r'^800.*$', '', genre)
+            genre = re.sub(r'^Fantastic Beasts.*$', '', genre)
+            genre = re.sub(r'^and thei.*$', '', genre)
+            genre = re.sub(r'^those you.*$', '', genre)
             genre = genre.strip()
+            genre = genre.lstrip()
 
-            new_genres.append(genre)
+            if "," in genre:
+                genre = genre.split(",")
+            elif " - " in genre:
+                genre = genre.split(" - ")
+            elif "Historical Adventure Thriller Mystery" in genre:
+                genre = genre.split(" ")
+
+            if isinstance(genre, str):
+                if len(genre) > 50 or (5 > len(genre) > 0):
+                    genre = ""
+                    print(f"Too long or too short: {genre}")
+
+                genre = genre.strip()
+                genre = genre.lstrip()
+
+                new_genres.append(genre)
+            elif isinstance(genre, list):
+                if len(genres) > 1:
+                    genres = [g for g in genres if g]
+                new_genres.extend(genre)
 
         new_genres = sorted(set(new_genres))
-        
-        print("Write to Database")
 
         print(f"After sed: {new_genres}")
-        print("=================================")
 
         list_difference = False
-
+        print("Write to Database")
+        if len(new_genres) < len(genres):
+            list_difference = True
         for old,new in zip(genres,new_genres):
             if old != new:
                 list_difference = True
@@ -109,6 +157,9 @@ def main():
             continue
 
         print("Write to Database")
+
+
+        print("=================================")
         cur.execute(
             "UPDATE books SET genres=? WHERE id=?",
             (json.dumps(new_genres), book_id),