From 296422ff5729500b2428ddf23d57df267904d41d Mon Sep 17 00:00:00 2001
From: "Gan, Jimmy" <jimmy.gan@adidas.com>
Date: Thu, 9 Jul 2026 10:52:03 +0800
Subject: [PATCH] remove unused ffmpeg from Dockerfile (saves ~450MB)

---
 Dockerfile  |  1 -
 run_sync.py | 39 ++++++++++++++++++++++++++++++++++-----
 2 files changed, 34 insertions(+), 6 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index b19a9da..f7a695d 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -13,7 +13,6 @@ WORKDIR /app
 # Install system dependencies
 RUN apt-get update && apt-get install -y --no-install-recommends \
     curl \
-    ffmpeg \
     && rm -rf /var/lib/apt/lists/*
 
 
diff --git a/run_sync.py b/run_sync.py
index cbb4ac2..643a333 100755
--- a/run_sync.py
+++ b/run_sync.py
@@ -9,7 +9,7 @@ if os.path.exists(ENV_PATH):
             line = line.strip()
             if line and not line.startswith("#") and "=" in line:
                 key, _, value = line.partition("=")
-                value = value.strip().strip("'\"")
+                value = value.strip().strip("'\\"")
                 os.environ[key] = value
 
 sys.path.insert(0, REPO_ROOT)
@@ -18,17 +18,46 @@ sys.path.insert(0, os.path.join(REPO_ROOT, "backend"))
 from backend.db import init_db
 from backend.fetcher import fetch_subscriptions
 from backend.summarizer import summarize_all_pending
+import aiosqlite
+
+BATCH_SIZE = int(os.environ.get("SUMMARIZE_BATCH", "50"))
+BATCH_DELAY = float(os.environ.get("SUMMARIZE_BATCH_DELAY", "1.0"))
 
 logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
 
 async def main():
     await init_db()
+    
+    # Fetch new videos first
     count = await fetch_subscriptions()
     print(f"Fetched {count} new videos")
-    if count > 0:
-        print(f"Summarizing {count} videos...")
-        await summarize_all_pending()
-    print("Done")
+    
+    # Count pending
+    async with aiosqlite.connect(os.path.join(REPO_ROOT, "backend", "data", "videos.db")) as db:
+        cur = await db.execute("SELECT COUNT(*) FROM videos WHERE summary IS NULL OR summary = ''")
+        total = (await cur.fetchone())[0]
+    
+    if total == 0:
+        print("No pending videos to summarize.")
+        return
+    
+    print(f"Processing batch of up to {BATCH_SIZE} videos (of {total} pending)...")
+    
+    # Get pending video IDs
+    async with aiosqlite.connect(os.path.join(REPO_ROOT, "backend", "data", "videos.db")) as db:
+        db.row_factory = aiosqlite.Row
+        cur = await db.execute("SELECT video_id FROM videos WHERE summary IS NULL OR summary = '' LIMIT ?", (BATCH_SIZE,))
+        rows = await cur.fetchall()
+    
+    from backend.summarizer import summarize_video
+    done = 0
+    for row in rows:
+        await summarize_video(row["video_id"])
+        done += 1
+        if done < len(rows):
+            await asyncio.sleep(BATCH_DELAY)
+    
+    print(f"Processed {done}/{len(rows)} in batch, {total - done} remaining")
 
 if __name__ == "__main__":
     asyncio.run(main())