""" Tests for cloud item metadata schema, model isolation, and reconciliation service. Task 2 tests (model/schema/isolation/quota): - ORM model fields match migration schema expectations. - Metadata, extracted text, topic links, and semantic data persist without requiring an object key or byte cache row. - Identical provider item IDs coexist across different connections. - Foreign-owner queries do not return rows for other users. - Provider size never alters Quota.used_bytes. - Root folder state can be represented without a CloudItem parent row. Task 3 tests (reconciliation service): - Repeated reconciliation creates no duplicate rows. - Rename/move updates metadata without changing the CloudItem UUID. - Incomplete or failed listing cannot mark unseen children deleted. - All queries include both owner and connection scope. - Idempotent repeated reconciliation. """ from __future__ import annotations import uuid from datetime import datetime, timezone from typing import Optional import pytest import pytest_asyncio from sqlalchemy import String, Text, event from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine from sqlalchemy.pool import StaticPool from sqlalchemy.dialects.postgresql import UUID, INET, JSONB from db.models import Base, CloudItem, CloudItemTopic, CloudFolderState, CloudConnection, Topic, User, Quota from storage.cloud_base import CloudListing, CloudResource, CloudCapability, STATE_SUPPORTED from services.cloud_items import ( resolve_owned_connection, list_cloud_children, upsert_cloud_item, reconcile_cloud_listing, get_or_create_folder_state, update_folder_state, CloudItemNotFound, ConnectionNotFound, ) # ── SQLite test engine setup ────────────────────────────────────────────────── @pytest_asyncio.fixture async def db_session(): """In-memory SQLite session with PostgreSQL-type shims.""" engine = create_async_engine( "sqlite+aiosqlite:///:memory:", connect_args={"check_same_thread": False}, poolclass=StaticPool, ) # Shim PostgreSQL types to SQLite-compatible equivalents from sqlalchemy import event as sa_event @sa_event.listens_for(engine.sync_engine, "connect") def set_sqlite_pragma(dbapi_connection, connection_record): cursor = dbapi_connection.cursor() cursor.execute("PRAGMA foreign_keys=ON") cursor.close() # Patch dialect-specific column types before table creation import sqlalchemy.dialects.postgresql as pg _orig_uuid_init = pg.UUID.__init__ def _patch_columns(metadata): for table in metadata.tables.values(): for col in table.columns: if isinstance(col.type, pg.UUID): col.type = String(36) elif isinstance(col.type, pg.INET): col.type = String(45) elif isinstance(col.type, pg.JSONB): col.type = Text() async with engine.begin() as conn: _patch_columns(Base.metadata) await conn.run_sync(Base.metadata.create_all) session_factory = async_sessionmaker(engine, expire_on_commit=False) async with session_factory() as session: yield session async with engine.begin() as conn: await conn.run_sync(Base.metadata.drop_all) await engine.dispose() # ── Helpers ─────────────────────────────────────────────────────────────────── def _user_id() -> str: return str(uuid.uuid4()) def _conn_id() -> str: return str(uuid.uuid4()) def _item_id() -> str: return str(uuid.uuid4()) async def _make_user(session: AsyncSession, user_id: Optional[str] = None) -> str: uid = user_id or _user_id() u = User( id=uid, handle=f"user_{uid[:8]}", email=f"{uid[:8]}@example.com", password_hash="hash", role="user", ) session.add(u) await session.flush() return uid async def _make_connection( session: AsyncSession, user_id: str, conn_id: Optional[str] = None ) -> str: cid = conn_id or _conn_id() conn = CloudConnection( id=cid, user_id=user_id, provider="onedrive", display_name="My OneDrive", credentials_enc="enc", status="ACTIVE", ) session.add(conn) await session.flush() return cid def _cloud_resource( connection_id: str, user_id: str, provider_item_id: str = "item-001", name: str = "test.pdf", kind: str = "file", parent_ref: Optional[str] = None, size: Optional[int] = None, etag: Optional[str] = None, ) -> CloudResource: return CloudResource( id=uuid.uuid4(), provider_item_id=provider_item_id, connection_id=uuid.UUID(connection_id), user_id=uuid.UUID(user_id), name=name, kind=kind, parent_ref=parent_ref, size=size, etag=etag, ) # ── Task 2: model/schema tests ──────────────────────────────────────────────── @pytest.mark.asyncio async def test_model_cloud_item_basic_fields(db_session: AsyncSession): """CloudItem persists metadata without requiring an object key.""" uid = await _make_user(db_session) cid = await _make_connection(db_session, uid) item_id = _item_id() item = CloudItem( id=item_id, user_id=uid, connection_id=cid, provider_item_id="driveitem-123", name="report.pdf", kind="file", content_type="application/pdf", provider_size=204800, etag="etag-v1", ) db_session.add(item) await db_session.flush() await db_session.refresh(item) assert item.id == item_id assert item.provider_item_id == "driveitem-123" assert item.name == "report.pdf" assert item.kind == "file" assert item.provider_size == 204800 assert item.analysis_status == "pending" assert item.semantic_index_status == "none" assert item.deleted_at is None @pytest.mark.asyncio async def test_model_cloud_item_extracted_text_without_object_key(db_session: AsyncSession): """Extracted text and semantic data persist with no MinIO object key field.""" uid = await _make_user(db_session) cid = await _make_connection(db_session, uid) item = CloudItem( id=_item_id(), user_id=uid, connection_id=cid, provider_item_id="item-text", name="notes.txt", kind="file", extracted_text="Sample extracted text", semantic_index_status="indexed", # No object_key field exists — provider bytes are not retained here ) db_session.add(item) await db_session.flush() await db_session.refresh(item) assert item.extracted_text == "Sample extracted text" assert item.semantic_index_status == "indexed" # Confirm no object_key attribute at all assert not hasattr(item, "object_key") @pytest.mark.asyncio async def test_model_cloud_item_topics_no_document_row(db_session: AsyncSession): """CloudItemTopic links item to topic without requiring a Document row.""" uid = await _make_user(db_session) cid = await _make_connection(db_session, uid) topic = Topic(id=_item_id(), user_id=uid, name="Finance", description="", color="#ff0000") db_session.add(topic) await db_session.flush() item = CloudItem( id=_item_id(), user_id=uid, connection_id=cid, provider_item_id="item-topic", name="budget.xlsx", kind="file", ) db_session.add(item) await db_session.flush() link = CloudItemTopic(cloud_item_id=item.id, topic_id=topic.id) db_session.add(link) await db_session.flush() # Verify link persisted from sqlalchemy import select result = await db_session.execute( select(CloudItemTopic).where(CloudItemTopic.cloud_item_id == item.id) ) rows = result.scalars().all() assert len(rows) == 1 assert rows[0].topic_id == topic.id @pytest.mark.asyncio async def test_model_schema_isolation_same_provider_item_different_connections(db_session: AsyncSession): """Identical provider_item_id can coexist across different connections.""" uid = await _make_user(db_session) cid1 = await _make_connection(db_session, uid) cid2 = await _make_connection(db_session, uid) shared_pid = "shared-item-001" item1 = CloudItem( id=_item_id(), user_id=uid, connection_id=cid1, provider_item_id=shared_pid, name="file.pdf", kind="file", ) item2 = CloudItem( id=_item_id(), user_id=uid, connection_id=cid2, provider_item_id=shared_pid, name="file.pdf", kind="file", ) db_session.add_all([item1, item2]) await db_session.flush() from sqlalchemy import select result = await db_session.execute( select(CloudItem).where(CloudItem.provider_item_id == shared_pid) ) rows = result.scalars().all() assert len(rows) == 2 @pytest.mark.asyncio async def test_model_schema_foreign_owner_query_returns_nothing(db_session: AsyncSession): """Items for user A are not returned when querying for user B.""" uid_a = await _make_user(db_session) uid_b = await _make_user(db_session) cid_a = await _make_connection(db_session, uid_a) item = CloudItem( id=_item_id(), user_id=uid_a, connection_id=cid_a, provider_item_id="item-a", name="private.pdf", kind="file", ) db_session.add(item) await db_session.flush() from sqlalchemy import select result = await db_session.execute( select(CloudItem).where( CloudItem.user_id == uid_b, CloudItem.provider_item_id == "item-a", ) ) assert result.scalars().first() is None @pytest.mark.asyncio async def test_model_quota_unchanged_after_item_upsert(db_session: AsyncSession): """Upserting a cloud item with provider_size must not alter Quota.used_bytes.""" uid = await _make_user(db_session) cid = await _make_connection(db_session, uid) quota = Quota(user_id=uid, limit_bytes=104857600, used_bytes=0) db_session.add(quota) await db_session.flush() item = CloudItem( id=_item_id(), user_id=uid, connection_id=cid, provider_item_id="large-file", name="video.mp4", kind="file", provider_size=5_000_000_000, # 5 GB provider-reported size ) db_session.add(item) await db_session.flush() await db_session.refresh(quota) # Quota must remain unchanged assert quota.used_bytes == 0 @pytest.mark.asyncio async def test_model_folder_state_root_no_parent_item(db_session: AsyncSession): """Root folder state can be created with parent_ref='' without a CloudItem row.""" uid = await _make_user(db_session) cid = await _make_connection(db_session, uid) fs = CloudFolderState( id=_item_id(), user_id=uid, connection_id=cid, parent_ref="", # root refresh_state="fresh", ) db_session.add(fs) await db_session.flush() await db_session.refresh(fs) assert fs.parent_ref == "" assert fs.refresh_state == "fresh" assert fs.last_refreshed_at is None # ── Task 3: reconciliation service tests ───────────────────────────────────── @pytest.mark.asyncio async def test_service_resolve_owned_connection_found(db_session: AsyncSession): uid = await _make_user(db_session) cid = await _make_connection(db_session, uid) conn = await resolve_owned_connection(db_session, connection_id=cid, user_id=uid) assert str(conn.id) == cid @pytest.mark.asyncio async def test_service_resolve_owned_connection_wrong_owner_raises(db_session: AsyncSession): uid_a = await _make_user(db_session) uid_b = await _make_user(db_session) cid = await _make_connection(db_session, uid_a) with pytest.raises(ConnectionNotFound): await resolve_owned_connection(db_session, connection_id=cid, user_id=uid_b) @pytest.mark.asyncio async def test_service_upsert_creates_item(db_session: AsyncSession): uid = await _make_user(db_session) cid = await _make_connection(db_session, uid) resource = _cloud_resource(cid, uid, provider_item_id="new-001", name="doc.pdf") item = await upsert_cloud_item(db_session, user_id=uid, resource=resource) assert item.provider_item_id == "new-001" assert item.name == "doc.pdf" @pytest.mark.asyncio async def test_service_upsert_idempotent_same_uuid(db_session: AsyncSession): """Repeated upsert with unchanged data creates no duplicate row.""" uid = await _make_user(db_session) cid = await _make_connection(db_session, uid) resource = _cloud_resource(cid, uid, provider_item_id="idem-001") item1 = await upsert_cloud_item(db_session, user_id=uid, resource=resource) item2 = await upsert_cloud_item(db_session, user_id=uid, resource=resource) assert item1.id == item2.id # same DocuVault UUID preserved @pytest.mark.asyncio async def test_service_upsert_rename_preserves_uuid(db_session: AsyncSession): """Rename updates name but keeps the same CloudItem UUID.""" uid = await _make_user(db_session) cid = await _make_connection(db_session, uid) resource = _cloud_resource(cid, uid, provider_item_id="rename-001", name="old.pdf") item1 = await upsert_cloud_item(db_session, user_id=uid, resource=resource) original_uuid = item1.id renamed = _cloud_resource(cid, uid, provider_item_id="rename-001", name="new.pdf") item2 = await upsert_cloud_item(db_session, user_id=uid, resource=renamed) assert item2.id == original_uuid assert item2.name == "new.pdf" @pytest.mark.asyncio async def test_service_list_children_owner_scoped(db_session: AsyncSession): """list_cloud_children only returns items for the correct (user, connection, parent).""" uid_a = await _make_user(db_session) uid_b = await _make_user(db_session) cid_a = await _make_connection(db_session, uid_a) res = _cloud_resource(cid_a, uid_a, provider_item_id="child-001", parent_ref="parent-ref") await upsert_cloud_item(db_session, user_id=uid_a, resource=res) # User A sees the item children_a = await list_cloud_children( db_session, user_id=uid_a, connection_id=cid_a, parent_ref="parent-ref" ) assert len(children_a) == 1 # User B does not children_b = await list_cloud_children( db_session, user_id=uid_b, connection_id=cid_a, parent_ref="parent-ref" ) assert len(children_b) == 0 @pytest.mark.asyncio async def test_service_reconcile_complete_marks_missing_deleted(db_session: AsyncSession): """Complete listing marks items not in the listing as deleted.""" uid = await _make_user(db_session) cid = await _make_connection(db_session, uid) # Pre-existing item existing = _cloud_resource(cid, uid, provider_item_id="keep-001", parent_ref="root") gone = _cloud_resource(cid, uid, provider_item_id="gone-001", parent_ref="root") await upsert_cloud_item(db_session, user_id=uid, resource=existing) await upsert_cloud_item(db_session, user_id=uid, resource=gone) # Reconcile with only "keep-001" in the complete listing listing = CloudListing(items=[existing], complete=True) await reconcile_cloud_listing( db_session, user_id=uid, connection_id=cid, parent_ref="root", listing=listing ) from sqlalchemy import select result = await db_session.execute( select(CloudItem).where(CloudItem.provider_item_id == "gone-001") ) gone_item = result.scalars().first() assert gone_item is not None assert gone_item.deleted_at is not None @pytest.mark.asyncio async def test_service_reconcile_incomplete_does_not_delete(db_session: AsyncSession): """Incomplete (partial/failed) listing must not mark unseen children deleted.""" uid = await _make_user(db_session) cid = await _make_connection(db_session, uid) item = _cloud_resource(cid, uid, provider_item_id="retain-001", parent_ref="root") await upsert_cloud_item(db_session, user_id=uid, resource=item) # Reconcile with empty incomplete listing listing = CloudListing(items=[], complete=False) await reconcile_cloud_listing( db_session, user_id=uid, connection_id=cid, parent_ref="root", listing=listing ) from sqlalchemy import select result = await db_session.execute( select(CloudItem).where(CloudItem.provider_item_id == "retain-001") ) retained = result.scalars().first() assert retained is not None assert retained.deleted_at is None @pytest.mark.asyncio async def test_service_folder_state_create_and_update(db_session: AsyncSession): uid = await _make_user(db_session) cid = await _make_connection(db_session, uid) fs = await get_or_create_folder_state(db_session, user_id=uid, connection_id=cid, parent_ref="") assert fs.refresh_state == "fresh" await update_folder_state( db_session, user_id=uid, connection_id=cid, parent_ref="", refresh_state="warning", error_code="token_expired", error_message="Re-authenticate to refresh.", ) from sqlalchemy import select result = await db_session.execute( select(CloudFolderState).where( CloudFolderState.connection_id == cid, CloudFolderState.parent_ref == "", ) ) updated = result.scalars().first() assert updated.refresh_state == "warning" assert updated.error_code == "token_expired" @pytest.mark.asyncio async def test_service_folder_state_idempotent(db_session: AsyncSession): """get_or_create is idempotent — no duplicate rows.""" uid = await _make_user(db_session) cid = await _make_connection(db_session, uid) fs1 = await get_or_create_folder_state(db_session, user_id=uid, connection_id=cid, parent_ref="") fs2 = await get_or_create_folder_state(db_session, user_id=uid, connection_id=cid, parent_ref="") assert fs1.id == fs2.id