fix: detect CIFS/NFS via /proc/mounts before opening DB

Instead of trying WAL mode and recovering after failure, proactively
detect network filesystems by parsing /proc/mounts and skip WAL
entirely. This avoids the stale WAL/SHM files that made recovery
impossible on CIFS mounts.

README.md

@@ -11,7 +11,7 @@ A self-hostable yt-dlp web frontend. Paste a URL, pick quality, download — wit
 - **Real-time progress** — Server-Sent Events stream download progress to the browser instantly.
 - **Session isolation** — Each browser gets its own download queue. No cross-talk.
 - **Playlist support** — Collapsible parent/child jobs with per-video status tracking.
-- **Three built-in themes** — Cyberpunk (default), Dark, Light. Switch in the header.
+- **9 built-in themes** — 5 dark (Cyberpunk, Dark, Midnight, Hacker, Neon) + 4 light (Light, Paper, Arctic, Solarized). Admin picks the pair, visitors toggle dark/light.
 - **Custom themes** — Drop a CSS file into `/themes` volume. No rebuild needed.
 - **Admin panel** — Session management, storage info, manual purge, error logs. Protected by bcrypt auth.
 - **Cookie auth** — Upload cookies.txt per session for paywalled/private content.
@@ -21,8 +21,32 @@ A self-hostable yt-dlp web frontend. Paste a URL, pick quality, download — wit
 
 ## Quickstart
 
+The Docker image is published to GitHub Container Registry:
+
+```
+ghcr.io/xpltdco/media-rip:latest
+```
+
+Pull and run with Docker Compose (recommended):
+
 ```bash
-docker compose up
+# Download the compose file
+curl -O https://raw.githubusercontent.com/xpltdco/media-rip/master/docker-compose.yml
+
+# Start the container
+docker compose up -d
+```
+
+Or pull and run directly:
+
+```bash
+docker run -d \
+  --name mediarip \
+  -p 8080:8000 \
+  -v ./downloads:/downloads \
+  -v mediarip-data:/data \
+  --restart unless-stopped \
+  ghcr.io/xpltdco/media-rip:latest
 ```
 
 Open [http://localhost:8080](http://localhost:8080) and paste a URL. On first run, you'll set an admin password.

backend/app/core/database.py

@@ -1,8 +1,10 @@
-"""SQLite database layer with WAL mode and async CRUD operations.
+"""SQLite database layer with async CRUD operations.
 
 Uses aiosqlite for async access.  ``init_db`` sets critical PRAGMAs
-(busy_timeout, WAL, synchronous) *before* creating any tables so that
-concurrent download workers never hit ``SQLITE_BUSY``.
+(busy_timeout, journal_mode, synchronous) *before* creating any tables so
+that concurrent download workers never hit ``SQLITE_BUSY``.  WAL mode is
+preferred on local filesystems; DELETE mode is used automatically when a
+network filesystem (CIFS, NFS) is detected.
 """
 
 from __future__ import annotations
@@ -90,19 +92,31 @@ async def init_db(db_path: str) -> aiosqlite.Connection:
 
     PRAGMA order matters:
       1. ``busy_timeout`` — prevents immediate ``SQLITE_BUSY`` on lock contention
-      2. ``journal_mode=WAL`` — enables concurrent readers + single writer
-      3. ``synchronous=NORMAL`` — safe durability level for WAL mode
+      2. ``journal_mode`` — WAL for local filesystems, DELETE for network mounts
+         (CIFS/NFS lack the shared-memory primitives WAL requires)
+      3. ``synchronous=NORMAL`` — safe durability level
 
     Returns the ready-to-use connection.
     """
+    # Detect network filesystem *before* opening the DB so we never attempt
+    # WAL on CIFS/NFS (which creates broken SHM files that persist).
+    use_wal = not _is_network_filesystem(db_path)
+
     db = await aiosqlite.connect(db_path)
     db.row_factory = aiosqlite.Row
 
     # --- PRAGMAs (before any DDL) ---
     await db.execute("PRAGMA busy_timeout = 5000")
-    result = await db.execute("PRAGMA journal_mode = WAL")
-    row = await result.fetchone()
-    journal_mode = row[0] if row else "unknown"
+
+    if use_wal:
+        journal_mode = await _try_journal_mode(db, "wal")
+    else:
+        logger.info(
+            "Network filesystem detected for %s — using DELETE journal mode",
+            db_path,
+        )
+        journal_mode = await _try_journal_mode(db, "delete")
+
     logger.info("journal_mode set to %s", journal_mode)
 
     await db.execute("PRAGMA synchronous = NORMAL")
@@ -115,6 +129,54 @@ async def init_db(db_path: str) -> aiosqlite.Connection:
     return db
 
 
+def _is_network_filesystem(db_path: str) -> bool:
+    """Return True if *db_path* resides on a network filesystem (CIFS, NFS, etc.).
+
+    Parses ``/proc/mounts`` (Linux) to find the filesystem type of the
+    longest-prefix mount matching the database directory.  Returns False
+    on non-Linux hosts or if detection fails.
+    """
+    import os
+
+    network_fs_types = {"cifs", "nfs", "nfs4", "smb", "smbfs", "9p", "fuse.sshfs"}
+    try:
+        db_dir = os.path.dirname(os.path.abspath(db_path))
+        with open("/proc/mounts", "r") as f:
+            mounts = f.readlines()
+        best_match = ""
+        best_fstype = ""
+        for line in mounts:
+            parts = line.split()
+            if len(parts) < 3:
+                continue
+            mountpoint, fstype = parts[1], parts[2]
+            if db_dir.startswith(mountpoint) and len(mountpoint) > len(best_match):
+                best_match = mountpoint
+                best_fstype = fstype
+        is_net = best_fstype in network_fs_types
+        if is_net:
+            logger.info(
+                "Detected %s filesystem at %s for database %s",
+                best_fstype, best_match, db_path,
+            )
+        return is_net
+    except Exception:
+        return False
+
+
+async def _try_journal_mode(
+    db: aiosqlite.Connection, mode: str,
+) -> str:
+    """Try setting *mode* and return the actual journal mode string."""
+    try:
+        result = await db.execute(f"PRAGMA journal_mode = {mode}")
+        row = await result.fetchone()
+        return (row[0] if row else "unknown").lower()
+    except Exception as exc:
+        logger.warning("PRAGMA journal_mode=%s failed: %s", mode, exc)
+        return "error"
+
+
 # ---------------------------------------------------------------------------
 # CRUD helpers
 # ---------------------------------------------------------------------------

backend/app/services/download.py

@@ -561,6 +561,31 @@ class DownloadService:
         url_lower = url.lower()
         return any(domain in url_lower for domain in audio_domains)
 
+    @staticmethod
+    def _url_or_ext_implies_video(url: str, ext: str | None) -> bool:
+        """Return True if the URL path or reported extension is a known video container.
+
+        This acts as a fallback when yt-dlp's extract_flat mode strips codec
+        metadata (common for archive.org, direct-file URLs, etc.), which would
+        otherwise cause the UI to wrongly label the source as "audio only".
+        """
+        video_extensions = {
+            "mp4", "mkv", "webm", "avi", "mov", "flv", "wmv", "mpg",
+            "mpeg", "m4v", "ts", "3gp", "ogv",
+        }
+        # Check the extension reported by yt-dlp
+        if ext and ext.lower() in video_extensions:
+            return True
+        # Check the URL path for a video file extension
+        from urllib.parse import urlparse
+        path = urlparse(url).path.lower()
+        # Strip any trailing slashes / query residue
+        path = path.rstrip("/")
+        for vext in video_extensions:
+            if path.endswith(f".{vext}"):
+                return True
+        return False
+
     @staticmethod
     def _get_auth_hint(url: str) -> str | None:
         """Return a user-facing hint for sites that commonly need auth."""
@@ -645,13 +670,27 @@ class DownloadService:
                         "url": e.get("url") or e.get("webpage_url", ""),
                         "duration": e.get("duration"),
                     })
+            # Domain-based detection may miss video playlists on generic
+            # hosting sites (e.g. archive.org).  If any entry URL looks like
+            # a video file, override domain_audio for the whole playlist.
+            playlist_audio = domain_audio
+            if playlist_audio:
+                for e_check in entries:
+                    entry_url = e_check.get("url", "")
+                    if self._url_or_ext_implies_video(entry_url, None):
+                        playlist_audio = False
+                        break
+            if not playlist_audio and not domain_audio:
+                # Also check the top-level URL itself
+                if self._url_or_ext_implies_video(url, info.get("ext")):
+                    playlist_audio = False
             result = {
                 "type": "playlist",
                 "title": info.get("title", "Playlist"),
                 "count": len(entries),
                 "entries": entries,
-                "is_audio_only": domain_audio,
-                "default_ext": self._guess_ext_from_url(url, domain_audio),
+                "is_audio_only": playlist_audio,
+                "default_ext": self._guess_ext_from_url(url, playlist_audio),
             }
             if unavailable_count > 0:
                 result["unavailable_count"] = unavailable_count
@@ -659,6 +698,11 @@ class DownloadService:
         else:
             # Single video/track
             has_video = bool(info.get("vcodec") and info["vcodec"] != "none")
+            # extract_flat mode often strips codec info, so also check the
+            # URL extension and the reported ext — if either is a known video
+            # container we should NOT mark it as audio-only.
+            if not has_video:
+                has_video = self._url_or_ext_implies_video(url, info.get("ext"))
             is_audio_only = domain_audio or not has_video
             # Detect likely file extension
             ext = info.get("ext")