Merge branch 'fix/videos-tmdb-matching'

1 files changed, 49 insertions, 0 deletions

diff --git a/packages/meshbay-node/src/meshbay_node/media_cache.py b/packages/meshbay-node/src/meshbay_node/media_cache.py
index 707a046..4600a09 100644
--- a/packages/meshbay-node/src/meshbay_node/media_cache.py
+++ b/packages/meshbay-node/src/meshbay_node/media_cache.py
@@ -34,6 +34,14 @@ CREATE TABLE IF NOT EXISTS file_tmdb (
     tmdb_id     TEXT NOT NULL,
     media_type  TEXT NOT NULL
 );
+-- Files whose match was set by an explicit operator "Fix match"
+-- correction, not by the automatic matcher. `ops.rematch_video` and a
+-- rename's re-enrichment wipe the *auto-resolved* file->tmdb mappings so
+-- they re-resolve against the current matcher; a manual correction must
+-- survive that, so it is recorded here and skipped.
+CREATE TABLE IF NOT EXISTS tmdb_override (
+    file_id     TEXT PRIMARY KEY
+);
 CREATE TABLE IF NOT EXISTS tmdb_meta (
     tmdb_id     TEXT NOT NULL,
     media_type  TEXT NOT NULL,
@@ -144,6 +152,46 @@ class MediaCache:
         )
         await self._db.commit()
 
+    # ── manual "Fix match" corrections vs auto-resolved matches ──────────────
+
+    async def mark_tmdb_override(self, file_id: str) -> None:
+        """Record that this file's current match is an explicit operator
+        correction — `clear_file_tmdb` / `clear_tmdb_matches` skip it."""
+        await self._db.execute(
+            "INSERT OR IGNORE INTO tmdb_override (file_id) VALUES (?)", (file_id,))
+        await self._db.commit()
+
+    async def clear_file_tmdb(self, file_id: str) -> None:
+        """
+        Drop one file's *auto-resolved* match. Used on rename: the new name
+        re-derives the title, so the old name's match no longer applies —
+        but file_tmdb is keyed by content hash, unchanged by a rename, so
+        nothing else would ever dislodge it. A manual "Fix match"
+        correction is kept: the content, hence what the operator corrected,
+        is the same.
+        """
+        await self._db.execute(
+            "DELETE FROM file_tmdb WHERE file_id = ? AND file_id NOT IN "
+            "(SELECT file_id FROM tmdb_override)", (file_id,))
+        await self._db.commit()
+
+    async def clear_tmdb_matches(self, file_ids: list[str]) -> int:
+        """
+        Drop the auto-resolved file->tmdb mappings for these files so the
+        next `media_meta_req` re-resolves each against the current matcher
+        (`ops.rematch_video`, run by the operator after a matcher/parser
+        fix). Manual "Fix match" corrections (`tmdb_override`) are left in
+        place. Returns the number of rows removed.
+        """
+        if not self._db or not file_ids:
+            return 0
+        marks = ",".join("?" * len(file_ids))
+        cur = await self._db.execute(
+            f"DELETE FROM file_tmdb WHERE file_id IN ({marks}) AND file_id NOT IN "
+            "(SELECT file_id FROM tmdb_override)", file_ids)
+        await self._db.commit()
+        return cur.rowcount
+
     # ── tmdb id -> metadata json ─────────────────────────────────────────────
 
     async def get_tmdb_meta(self, tmdb_id: str, media_type: str) -> dict | None:
@@ -324,5 +372,6 @@ class MediaCache:
         await self._db.execute("DELETE FROM photo_meta WHERE file_id = ?", (file_id,))
         await self._db.execute("DELETE FROM video_meta WHERE file_id = ?", (file_id,))
         await self._db.execute("DELETE FROM file_tmdb WHERE file_id = ?", (file_id,))
+        await self._db.execute("DELETE FROM tmdb_override WHERE file_id = ?", (file_id,))
         await self._db.execute("DELETE FROM file_mbid WHERE file_id = ?", (file_id,))
         await self._db.commit()