Backfill YouTube titles through the queue

media-scrape/src/store.ts

@@ -171,6 +171,8 @@ export interface MediaRow {
     preview_attempts: number;
     /** Embed title from Discord (YouTube and friends). */
     title: string | null;
+    title_attempts: number;
+    title_error: string | null;
     /** Lowercased, punctuation-collapsed title for token-prefix search. */
     title_key: string | null;
     created_at: string;
@@ -224,6 +226,8 @@ CREATE TABLE IF NOT EXISTS media (
     preview_attempts INTEGER NOT NULL DEFAULT 0,
     title TEXT,
     title_key TEXT,
+    title_attempts INTEGER NOT NULL DEFAULT 0,
+    title_error TEXT,
     created_at TEXT NOT NULL
 );
 
@@ -273,6 +277,10 @@ export class ScrapeStore {
             this.db.exec("ALTER TABLE media ADD COLUMN title TEXT");
             this.db.exec("ALTER TABLE media ADD COLUMN title_key TEXT");
         }
+        if (!names.has("title_attempts")) {
+            this.db.exec("ALTER TABLE media ADD COLUMN title_attempts INTEGER NOT NULL DEFAULT 0");
+            this.db.exec("ALTER TABLE media ADD COLUMN title_error TEXT");
+        }
     }
 
     close(): void {
@@ -434,6 +442,8 @@ export class ScrapeStore {
         pending: number;
         cached: number;
         failed: number;
+        /** YouTube-like rows still missing a title. */
+        titlePending: number;
         byKind: Record<MediaKind, { total: number; pending: number; cached: number; failed: number }>;
     } {
         const empty = () => ({ total: 0, pending: 0, cached: 0, failed: 0 });
@@ -477,10 +487,58 @@ export class ScrapeStore {
             totals.failed += row.failed ?? 0;
         }
 
-        return { ...totals, byKind };
+        const titles = this.db
+            .prepare(
+                `SELECT COUNT(*) AS count FROM media
+                 WHERE title IS NULL AND title_error IS NULL
+                   AND (lower(COALESCE(provider, '')) LIKE '%youtube%'
+                        OR lower(url) LIKE '%youtube.com/%'
+                        OR lower(url) LIKE '%youtu.be/%')`
+            )
+            .get() as { count: number | null } | undefined;
+
+        return { ...totals, titlePending: titles?.count ?? 0, byKind };
     }
 
     /** Count one transient preview failure and return the new total. */
+    /**
+     * YouTube-like rows whose title Discord did not provide, oldest first. Resolved through the
+     * provider oEmbed in the backfill queue.
+     */
+    pendingTitles(limit = 500): MediaRow[] {
+        return this.db
+            .prepare(
+                `SELECT * FROM media
+                 WHERE title IS NULL AND title_error IS NULL
+                   AND (lower(COALESCE(provider, '')) LIKE '%youtube%'
+                        OR lower(url) LIKE '%youtube.com/%'
+                        OR lower(url) LIKE '%youtu.be/%')
+                 ORDER BY id LIMIT ?`
+            )
+            .all(limit) as unknown as MediaRow[];
+    }
+
+    /** Store a resolved title and its search key. */
+    markTitle(id: number, title: string): void {
+        this.db
+            .prepare("UPDATE media SET title = ?, title_key = ?, title_error = NULL WHERE id = ?")
+            .run(title.slice(0, 300), normalizeTitleKey(title), id);
+    }
+
+    /** Count one transient title failure and return the new total. */
+    bumpTitleAttempt(id: number): number {
+        this.db.prepare("UPDATE media SET title_attempts = title_attempts + 1 WHERE id = ?").run(id);
+        const row = this.db.prepare("SELECT title_attempts FROM media WHERE id = ?").get(id) as
+            | { title_attempts: number | null }
+            | undefined;
+
+        return row?.title_attempts ?? 0;
+    }
+
+    markTitleError(id: number, error: string): void {
+        this.db.prepare("UPDATE media SET title_error = ? WHERE id = ?").run(error.slice(0, 200), id);
+    }
+
     /** Count one transient preview failure and return the new total. */
     bumpPreviewAttempt(id: number): number {
         this.db.prepare("UPDATE media SET preview_attempts = preview_attempts + 1 WHERE id = ?").run(id);