Fix FK constraint violation in bulk_ingest by filtering dropped assets

Co-authored-by: Amp <amp@ampcode.com>
Amp-Thread-ID: https://ampcode.com/threads/T-019c3626-c6ad-7139-a570-62da4e656a1a

app/assets/database/queries/__init__.py

@@ -2,6 +2,7 @@ from app.assets.database.queries.asset import (
     asset_exists_by_hash,
     bulk_insert_assets,
     get_asset_by_hash,
+    get_existing_asset_ids,
     upsert_asset,
 )
 from app.assets.database.queries.asset_info import (
@@ -76,6 +77,7 @@ __all__ = [
     "fetch_asset_info_and_asset",
     "fetch_asset_info_asset_and_tags",
     "get_asset_by_hash",
+    "get_existing_asset_ids",
     "get_asset_info_by_id",
     "get_asset_info_ids_by_ids",
     "get_asset_tags",

app/assets/database/queries/asset.py

@@ -88,3 +88,16 @@ def bulk_insert_assets(
     ins = sqlite.insert(Asset).on_conflict_do_nothing(index_elements=[Asset.hash])
     for chunk in iter_chunks(rows, calculate_rows_per_statement(5)):
         session.execute(ins, chunk)
+
+
+def get_existing_asset_ids(
+    session: Session,
+    asset_ids: list[str],
+) -> set[str]:
+    """Return the subset of asset_ids that exist in the database."""
+    if not asset_ids:
+        return set()
+    rows = session.execute(
+        select(Asset.id).where(Asset.id.in_(asset_ids))
+    ).fetchall()
+    return {row[0] for row in rows}