Upload folder using huggingface_hub

modules/dropbox/audio.py

@@ -67,6 +67,10 @@ audio_cache: dict[tuple[str, int, str], dict] = {}
 CACHE_TTL = timedelta(hours=3, minutes=30)  # refresh before 4h expiry
 
 
+from dropbox.files import FileMetadata
+from datetime import datetime, timezone
+from fastapi import HTTPException
+
 async def get_audio_urls(req: AudioRequest):
     base_path = f"/{req.scripture_name}/audio"
     prefix = f"{req.global_index}-"
@@ -75,12 +79,19 @@ async def get_audio_urls(req: AudioRequest):
     now = datetime.now(timezone.utc)
 
     try:
-        # List all files under the scripture's audio directory
-        entries = dbx.files_list_folder(base_path).entries
+        # Initial listing (first batch of up to 500)
+        result = dbx.files_list_folder(base_path)
+        entries = result.entries
+
+        # Continue listing if there are more entries
+        while result.has_more:
+            result = dbx.files_list_folder_continue(result.cursor)
+            entries.extend(result.entries)
+
     except dropbox.exceptions.ApiError:
         raise HTTPException(status_code=404, detail="Audio directory not found")
 
-    # Filter files that match the prefix
+    # Filter files matching the prefix
     matching_files = [
         entry for entry in entries
         if isinstance(entry, FileMetadata) and entry.name.startswith(prefix)
@@ -90,20 +101,16 @@ async def get_audio_urls(req: AudioRequest):
         raise HTTPException(status_code=404, detail="No audio files found")
 
     for entry in matching_files:
-        # Extract file type from "<global_index>-<type>.mp3"
-        # Example: "123-recitation.mp3" -> "recitation"
         filename = entry.name
         file_type = filename[len(prefix):].rsplit(".", 1)[0]
 
         cache_key = (req.scripture_name, req.global_index, file_type)
 
-        # Check cache
         cached = audio_cache.get(cache_key)
         if cached and cached["expiry"] > now:
             urls[file_type] = cached["url"]
             continue
 
-        # Generate temporary link
         file_path = f"{base_path}/{filename}"
         try:
             temp_link = dbx.files_get_temporary_link(file_path).link
@@ -115,7 +122,6 @@ async def get_audio_urls(req: AudioRequest):
     return urls
 
 
-
 async def cleanup_audio_url_cache(interval_seconds: int = 600):
     """Periodically remove expired entries from audio_cache."""
     while True: