feat(fc2a): add Celery tasks — scan_directory, import_media_file, generate_thumbnail

scan_directory walks ImportSettings.import_scan_path, creates an ImportBatch, enumerates supported files into ImportTasks, and enqueues import_media_file per task. import_media_file moves the task through its state machine (pending → queued → processing → complete/skipped/failed), updates ImportBatch counters atomically (UPDATE ... SET col = col + 1), enqueues a thumbnail task on success, and marks the batch complete when the last task drains. generate_thumbnail runs on its own queue (thumbnail) so big imports don't starve thumbnail throughput; failure here is logged and does not fail the import. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-14 12:08:37 -04:00
parent f38a1d48c5
commit d3bb8c509a
5 changed files with 272 additions and 1 deletions
@@ -0,0 +1,78 @@
+"""scan_directory task: walks the configured import path, creates an
+ImportBatch, enumerates files into ImportTasks, and enqueues
+import_media_file for each.
+"""
+
+from pathlib import Path
+
+from sqlalchemy import create_engine, select
+from sqlalchemy.orm import sessionmaker
+
+from ..celery_app import celery
+from ..config import get_config
+from ..models import ImportBatch, ImportSettings, ImportTask
+from ..services.importer import is_supported
+
+
+def _sync_session_factory():
+    cfg = get_config()
+    engine = create_engine(cfg.database_url_sync, future=True, pool_pre_ping=True)
+    return sessionmaker(engine, expire_on_commit=False)
+
+
+@celery.task(name="backend.app.tasks.scan.scan_directory", bind=True)
+def scan_directory(self, triggered_by: str = "manual") -> int:
+    """Walks the import root and creates ImportTasks. Returns the batch id."""
+    SessionLocal = _sync_session_factory()
+    with SessionLocal() as session:
+        settings = session.execute(
+            select(ImportSettings).where(ImportSettings.id == 1)
+        ).scalar_one()
+        import_root = Path(settings.import_scan_path)
+
+        batch = ImportBatch(
+            triggered_by=triggered_by,
+            source_path=str(import_root),
+            scan_mode="quick",  # FC-2a is quick only; FC-2d adds 'deep'
+            status="running",
+        )
+        session.add(batch)
+        session.flush()
+        batch_id = batch.id
+
+        # Walk and enumerate.
+        files_seen = 0
+        for entry in import_root.rglob("*"):
+            if not entry.is_file():
+                continue
+            if not is_supported(entry):
+                continue
+            try:
+                size = entry.stat().st_size
+            except OSError:
+                size = None
+            task = ImportTask(
+                batch_id=batch_id,
+                source_path=str(entry),
+                task_type="media",
+                status="pending",
+                size_bytes=size,
+            )
+            session.add(task)
+            files_seen += 1
+
+        batch.total_files = files_seen
+        session.commit()
+
+        # Now enqueue import_media_file for each pending task.
+        for task in session.execute(
+            select(ImportTask).where(ImportTask.batch_id == batch_id)
+        ).scalars():
+            task.status = "queued"
+            session.add(task)
+            from .import_file import import_media_file
+
+            import_media_file.delay(task.id)
+        session.commit()
+
+    return batch_id