feat(ffmpeg_handling): dictonary expansion, change russ search function

generate search function from translation keys
dont require perfect match for translation
expand vocabulary

media_editing/ffmpeg_handling.py

@@ -49,26 +49,41 @@ commands = {
 }
 # ------ Russian Dictonary --------------#
 AUDIO_TRANSLATIONS = {
-    # Additional descriptors
+    # Voice-over / dubbing
     "Закадровый": "Voice-over",
     "Закадровое озвучивание": "Voice-over",
-    "Многоголосый закадровый": "Multi-voice voice-over",
-    "Многоголосное закадровое озвучивание": "Multi-voice voice-over",
-    # Variants found in metadata
-    "Оригинален език": "Original language",
-    "Многоголосное озвучивание": "Multi-voice dub",
-    "Многоголосый": "Multi-voice",
-    "Любительский": "Amateur voice-over",
-    "многоголосый": "Multi-voice",
-    "Профессиональный": "Professional",
-    "Одноголосый": "Single voice",
-    "Двухголосый": "Dual voice",
-    "Авторский": "Author voice-over",
     "закадровый": "Voice-over",
+    "Многоголосый закадровый": "Voice-over",
+    "Многоголосное закадровое озвучивание": "Voice-over",
+    "Многоголосное озвучивание": "Voice-over",
+    "Многоголосый": "Voice-over",
+    "Одноголосый": "Voice-over",
+    "Двухголосый": "Voice-over",
+    "Авторский": "Voice-over",
+    "Любительский": "Voice-over",
+    "Профессиональный": "Professional",
     "Оригинал": "Original",
     "Дубляж": "Dubbed",
-    # Russian groups
+    # Languages
+    r"русск": "Russian",
+    "Английски": "English",
+    "български": "Bulgarian",
+    "Български": "Bulgarian",
+    "Українська": "Ukrainian",
+    "українська": "Ukrainian",
+    "Македонски": "Macedonian",
+    "Српски": "Serbian",
+    "Немецкая": "German",
+    "Немецкое": "German",
+    "немецкие": "German",
+    "Английская": "English",
+    "Английское": "English",
+    "Французская": "French",
+    "Французское": "French",
+    # Studios / groups
     "Кубик в кубе": "Kubik v Kube",
+    "Синема УС": "Cinema US",
+    "Озвучка Rumble": "Rumble",
     "LostFilm": "LostFilm",
     "AlexFilm": "AlexFilm",
     "Baibako": "Baibako",
@@ -77,60 +92,42 @@ AUDIO_TRANSLATIONS = {
     "Kerob": "Kerob",
     "TVShows": "TVShows",
     "HDRezka": "HDRezka",
-    # Groups / studios
-    "Синема УС": "Cinema US",
     "KinoPub": "KinoPub",
-    "Озвучка Rumble": "Rumble",
     "Rumble": "Rumble",
-    # Voice actor
+    "супербит": "Superbit",
+    "Видеосервис": "Videoservice",
+    "Семён Гальцев": "Semyon Galtsev",
+    # Voice actors
     "Юрий Сербин": "Yuriy Serbin",
     "Ю. Сербин": "Y. Serbin",
-    # Languages
+    "П.Либергал": "P. Libergal",
-    "Английски": "English",
+    "Визгунов": "Vizgunov",
-    "Русский": "Russian",
+    # Misc
-    "Русская": "Russian",
+    # Subtitles
-    "Русское": "Russian",
+    "субтитры": "Russian Subtitles",
-    # ISO codes
+    "Оригинален език": "Original language",
+    # ISO
     "rus": "Russian",
     "ru": "Russian",
-    "ger": "German",
-    "deu": "German",
-    "eng": "English",
-    "und": "Unknown",
 }
+IGNORE_WORDS = {
+    "English",
+    "German",
+    "French",
+}
+
 RUSSIAN_RE = re.compile(
-    r"\brus\b|"
+    "|".join(
-    r"\bru\b|"
+        sorted(
-    r"russian|"
+            (
-    r"рус|"
+                re.escape(key)
-    r"русский|"
+                for key in AUDIO_TRANSLATIONS
-    r"русская|"
+                if AUDIO_TRANSLATIONS[key] not in IGNORE_WORDS
-    r"русское|"
+            ),
-    r"дубляж|"
+            key=len,
-    r"оригинал|"
+            reverse=True,
-    r"многоголос|"
+        )
-    r"двухголос|"
+    ),
-    r"одноголос|"
-    r"авторский|"
-    r"любительский|"
-    r"профессиональн|"
-    r"закадров|"
-    r"юрий\s+сербин|"
-    r"ю\.\s*сербин|"
-    r"сербин|"
-    r"синема\s+ус|"
-    r"kinopub|"
-    r"rumble|"
-    r"озвучка\s+rumble|"
-    r"кубик\s+в\s+кубе|"
-    r"lostfilm|"
-    r"alexfilm|"
-    r"baibako|"
-    r"newstudio|"
-    r"jaskier|"
-    r"kerob|"
-    r"tvshows|"
-    r"hdrezka",
     re.IGNORECASE,
 )
 
@@ -175,18 +172,13 @@ def translate_audio_tracks(tracks: list[dict]) -> list[dict]:
         for key, value in new_track.items():
             if not isinstance(value, str):
                 continue
-
             for src, dst in AUDIO_TRANSLATIONS.items():
-                value = re.sub(
+                if re.search(rf"\b{re.escape(src)}\b", value, flags=re.IGNORECASE):
-                    rf"\b{re.escape(src)}\b",
+                    value = dst
-                    dst,
+                    break
-                    value,
-                    flags=re.IGNORECASE,
-                )
-
             if CYRILLIC_RE.search(value):
                 raise ValueError(
-                    f"Contains unidentified Cyrillic characters in {key}: {value}"
+                    f"Track contains unidentified Cyrillic characters in {key}: {value}"
                 )
 
             new_track[key] = value
@@ -520,7 +512,10 @@ def cmd_convert_video(args):
     )
     return True, out
 
+
 from collections.abc import Callable
+
+
 def remove_streams(
     args,
     remove_indices: set[int] | list[int],
@@ -533,8 +528,7 @@ def remove_streams(
     remaining_audio = [
         s
         for s in probe["streams"]
-        if s["codec_type"] == "audio"
+        if s["codec_type"] == "audio" and s["index"] not in remove_indices
-        and s["index"] not in remove_indices
     ]
 
     if not remaining_audio:
@@ -618,14 +612,13 @@ def remove_streams(
         logger.error("STDERR:\n%s", e.stderr)
         raise
 
+
 def cmd_remove_subs(args):
     probe = ffmpeg.probe(str(args.input))
 
     if args.num is None:
         remove_indices = {
-            s["index"]
+            s["index"] for s in probe["streams"] if s["codec_type"] == "subtitle"
-            for s in probe["streams"]
-            if s["codec_type"] == "subtitle"
         }
     else:
         remove_indices = set(args.num)
@@ -635,10 +628,10 @@ def cmd_remove_subs(args):
         remove_indices=remove_indices,
     )
 
+
 def cmd_remove_audio_track(args):
     remove_indices = {
-        select_audio_stream(args.input, audio_index)
+        select_audio_stream(args.input, audio_index) for audio_index in args.audio_index
-        for audio_index in args.audio_index
     }
 
     return remove_streams(
@@ -646,6 +639,8 @@ def cmd_remove_audio_track(args):
         remove_indices=remove_indices,
         output_subtitle_codec=True,
     )
+
+
 def cmd_extract_audio_track(args):
     """
     1. Saves that specific audio track as a standalone MP3 (Extra Output).
@@ -929,6 +924,7 @@ def cmd_set_primary_audio(args):
 
     return True, out
 
+
 def cmd_show_metadata(args, show_metadata=False, return_tags=None):
     probe = ffmpeg.probe(str(args.input))
     format_tags = probe.get("format", {}).get("tags", {})
@@ -942,7 +938,6 @@ def cmd_show_metadata(args, show_metadata=False, return_tags=None):
         for k, v in format_tags.items():
             logger.info(f"{k}: {v}")
 
-
     # logger.info(f"\n=== STREAM METADATA ===")
     # for i, stream in enumerate(probe.get("streams", [])):
     #    logger.info(f"\n--- Stream {i} ({stream.get('codec_type')}) ---")
@@ -1113,8 +1108,8 @@ def cmd_remove_russian_from_db(args):
     try:
         audio_tracks = translate_audio_tracks(get_audio_tracks(file))
         subtitle_tracks = translate_audio_tracks(get_subtitle_tracks(file))
-    except ValueError as e:
+    except ValueError as error_msg:
-        logger.warning("%s", e)
+        logger.warning(f"File {file.name} {error_msg}")
         return False, "nooutputneeded"
 
     logger.trace("Remove Russian from File: %s", file.name)
@@ -1409,7 +1404,9 @@ def cmd_test(args):
             logger.debug(f"Subtitle tracks: {subtitle_tracks}")
             for subtitle_track in subtitle_tracks:
                 if is_russian_track(subtitle_track):
-                   logger.error(f"Found russian track: {subtitle_track} in file {file_path}")
+                    logger.error(
+                        f"Found russian track: {subtitle_track} in file {file_path}"
+                    )
                     return return_value and False
 
         logger.info(f"{green_tag('PASS')} {file_path}")