feat(01-05): final cutover — delete data/, prune config.py, async-only tests
- Delete backend/data/ tracked files (D-04): flat-file metadata, settings.json, topics.json, and uploaded files removed from git; backend/data/ added to .gitignore (empty dir remains on macOS due to ACL — no tracked files remain) - Prune backend/config.py: remove DATA_DIR, UPLOADS_DIR, METADATA_DIR, TOPICS_FILE, ensure_data_dirs(); rebase SETTINGS_FILE as derived path from settings.data_dir (Phase 1 flat-file settings kept per plan decision) - Prune backend/tests/conftest.py: remove isolated_data_dir autouse fixture and sync TestClient client fixture; add SQLite type compatibility shim (visit_INET/JSONB) so in-memory db_session can create tables with PostgreSQL-specific column types; add live_services_available fixture - Rewrite backend/tests/test_documents.py: delete all legacy sync tests, remove all @pytest.mark.xfail markers; async-only document tests now use async_client + storage service directly for topic wiring - Rewrite backend/tests/test_health.py: delete legacy sync test_health(client); remove @pytest.mark.xfail from test_health_checks_postgres_and_minio - Port backend/tests/test_topics.py to async_client (sync client removed) - Port backend/tests/test_settings.py to async_client with monkeypatch for SETTINGS_FILE isolation (settings remain flat-file in Phase 1)
This commit is contained in:
curo1305
+142
-93
@@ -1,61 +1,161 @@
|
||||
"""
|
||||
pytest configuration: isolate each test with a temporary data directory.
|
||||
pytest configuration for DocuVault backend tests.
|
||||
|
||||
Async fixtures (db_session, async_client) are added for Phase 1 — sync fixtures remain until Plan 05 cuts over.
|
||||
Plan 05 cutover: all sync flat-file fixtures (isolated_data_dir, sync client)
|
||||
removed. Tests use async fixtures only.
|
||||
|
||||
Service availability detection:
|
||||
- INTEGRATION=1 env var: assume live Docker services are available
|
||||
- Default (no INTEGRATION): use in-memory SQLite + skip tests requiring real
|
||||
PostgreSQL/MinIO/Redis
|
||||
|
||||
SQLite compatibility note:
|
||||
The ORM models use PostgreSQL-specific types (UUID, INET, JSONB). SQLite does
|
||||
not understand these. The db_session fixture patches them before creating
|
||||
tables so the in-memory engine can build the schema successfully.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import json
|
||||
import socket
|
||||
|
||||
import pytest
|
||||
import pytest_asyncio
|
||||
import tempfile
|
||||
import shutil
|
||||
from pathlib import Path
|
||||
from fastapi.testclient import TestClient
|
||||
from httpx import AsyncClient, ASGITransport
|
||||
from sqlalchemy.ext.asyncio import create_async_engine, async_sessionmaker, AsyncSession
|
||||
from httpx import ASGITransport, AsyncClient
|
||||
from sqlalchemy import String, Text
|
||||
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
|
||||
from sqlalchemy.pool import StaticPool
|
||||
|
||||
|
||||
# ── Sync fixtures (legacy — retained until Plan 05 cuts over) ──────────────────
|
||||
# ── Service availability ──────────────────────────────────────────────────────
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def isolated_data_dir(monkeypatch, tmp_path):
|
||||
"""Each test gets its own clean data directory."""
|
||||
data_dir = tmp_path / "data"
|
||||
(data_dir / "uploads").mkdir(parents=True)
|
||||
(data_dir / "metadata").mkdir(parents=True)
|
||||
(data_dir / "topics.json").write_text(json.dumps({"topics": []}))
|
||||
|
||||
from config import DEFAULT_SETTINGS
|
||||
(data_dir / "settings.json").write_text(json.dumps(DEFAULT_SETTINGS))
|
||||
|
||||
monkeypatch.setenv("DATA_DIR", str(data_dir))
|
||||
|
||||
# Patch the module-level path constants so the running app sees the temp dir
|
||||
import config
|
||||
monkeypatch.setattr(config, "DATA_DIR", data_dir)
|
||||
monkeypatch.setattr(config, "UPLOADS_DIR", data_dir / "uploads")
|
||||
monkeypatch.setattr(config, "METADATA_DIR", data_dir / "metadata")
|
||||
monkeypatch.setattr(config, "TOPICS_FILE", data_dir / "topics.json")
|
||||
monkeypatch.setattr(config, "SETTINGS_FILE", data_dir / "settings.json")
|
||||
|
||||
# Plan 04: services.storage is now async (PostgreSQL + MinIO).
|
||||
# The flat-file _topics_lock / _settings_lock attributes no longer exist.
|
||||
# Only SETTINGS_FILE is still used by the sync load_settings/save_settings.
|
||||
import services.storage as st
|
||||
monkeypatch.setattr(st, "SETTINGS_FILE", data_dir / "settings.json")
|
||||
|
||||
yield data_dir
|
||||
def _port_open(host: str, port: int, timeout: float = 1.0) -> bool:
|
||||
"""Return True if the given TCP port is reachable."""
|
||||
try:
|
||||
with socket.create_connection((host, port), timeout=timeout):
|
||||
return True
|
||||
except OSError:
|
||||
return False
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def client(isolated_data_dir):
|
||||
@pytest.fixture(scope="session")
|
||||
def live_services_available():
|
||||
"""True when Docker Compose services are reachable (or INTEGRATION=1 is set)."""
|
||||
if os.environ.get("INTEGRATION") == "1":
|
||||
return True
|
||||
return (
|
||||
_port_open("localhost", 5432)
|
||||
and _port_open("localhost", 9000)
|
||||
and _port_open("localhost", 6379)
|
||||
)
|
||||
|
||||
|
||||
# ── Core async fixtures ───────────────────────────────────────────────────────
|
||||
|
||||
def _patch_pg_types_for_sqlite():
|
||||
"""Patch PostgreSQL-specific column types so SQLite can create the schema.
|
||||
|
||||
SQLite does not know about INET, UUID (as_uuid=True), or JSONB. We
|
||||
replace them with Text/String equivalents for the in-memory test engine.
|
||||
This is done by monkey-patching the dialect-type mapping rather than
|
||||
modifying the models.
|
||||
"""
|
||||
try:
|
||||
from sqlalchemy.dialects.postgresql import UUID as PG_UUID, INET, JSONB
|
||||
|
||||
# Override compile methods so SQLite renders them as TEXT
|
||||
for pg_type in (INET, JSONB):
|
||||
pg_type.__class_getitem__ = classmethod(lambda cls, item: cls())
|
||||
|
||||
# Patch impl so SQLite uses String
|
||||
if not hasattr(INET, "_sqlite_patched"):
|
||||
INET.impl = String
|
||||
INET._sqlite_patched = True
|
||||
if not hasattr(JSONB, "_sqlite_patched"):
|
||||
JSONB.impl = Text
|
||||
JSONB._sqlite_patched = True
|
||||
except Exception:
|
||||
pass # If patching fails, the fixture will raise a CompileError naturally
|
||||
|
||||
|
||||
@pytest_asyncio.fixture
|
||||
async def db_session():
|
||||
"""In-memory async SQLite session for unit tests.
|
||||
|
||||
PostgreSQL-specific column types are overridden to Text/String so that
|
||||
Base.metadata.create_all works against the SQLite dialect.
|
||||
"""
|
||||
from sqlalchemy.dialects.sqlite.base import SQLiteTypeCompiler
|
||||
from sqlalchemy.dialects.postgresql import INET, JSONB
|
||||
|
||||
from db.models import Base
|
||||
|
||||
# ── Type compatibility shims ──────────────────────────────────────────────
|
||||
# PostgreSQL-specific types (INET, JSONB) are unknown to the SQLite dialect.
|
||||
# Temporarily add visit_* methods that render them as TEXT so that
|
||||
# Base.metadata.create_all can build the schema in SQLite.
|
||||
|
||||
_orig_visit_INET = getattr(SQLiteTypeCompiler, "visit_INET", None)
|
||||
_orig_visit_JSONB = getattr(SQLiteTypeCompiler, "visit_JSONB", None)
|
||||
|
||||
def _visit_inet(self, type_, **kw):
|
||||
return "TEXT"
|
||||
|
||||
def _visit_jsonb(self, type_, **kw):
|
||||
return "TEXT"
|
||||
|
||||
SQLiteTypeCompiler.visit_INET = _visit_inet # type: ignore[attr-defined]
|
||||
SQLiteTypeCompiler.visit_JSONB = _visit_jsonb # type: ignore[attr-defined]
|
||||
|
||||
# UUID(as_uuid=True) renders as CHAR(32) in SQLite — already handled by
|
||||
# SQLAlchemy's built-in UUID type mapping — no patch needed.
|
||||
|
||||
engine = create_async_engine(
|
||||
"sqlite+aiosqlite:///:memory:",
|
||||
connect_args={"check_same_thread": False},
|
||||
poolclass=StaticPool,
|
||||
)
|
||||
try:
|
||||
async with engine.begin() as conn:
|
||||
await conn.run_sync(Base.metadata.create_all)
|
||||
|
||||
AsyncTestSession = async_sessionmaker(engine, expire_on_commit=False)
|
||||
async with AsyncTestSession() as session:
|
||||
yield session
|
||||
finally:
|
||||
await engine.dispose()
|
||||
# Restore compiler methods to leave no side effects on other tests
|
||||
if _orig_visit_INET is not None:
|
||||
SQLiteTypeCompiler.visit_INET = _orig_visit_INET # type: ignore
|
||||
else:
|
||||
try:
|
||||
del SQLiteTypeCompiler.visit_INET # type: ignore
|
||||
except AttributeError:
|
||||
pass
|
||||
if _orig_visit_JSONB is not None:
|
||||
SQLiteTypeCompiler.visit_JSONB = _orig_visit_JSONB # type: ignore
|
||||
else:
|
||||
try:
|
||||
del SQLiteTypeCompiler.visit_JSONB # type: ignore
|
||||
except AttributeError:
|
||||
pass
|
||||
|
||||
|
||||
@pytest_asyncio.fixture
|
||||
async def async_client(db_session: AsyncSession):
|
||||
"""Async HTTP test client with the DB dependency overridden to use in-memory SQLite."""
|
||||
from deps.db import get_db
|
||||
from main import app
|
||||
with TestClient(app) as c:
|
||||
|
||||
app.dependency_overrides[get_db] = lambda: db_session
|
||||
|
||||
async with AsyncClient(transport=ASGITransport(app=app), base_url="http://test") as c:
|
||||
yield c
|
||||
|
||||
app.dependency_overrides.clear()
|
||||
|
||||
|
||||
# ── File fixtures ─────────────────────────────────────────────────────────────
|
||||
|
||||
@pytest.fixture
|
||||
def sample_txt(tmp_path):
|
||||
@@ -68,6 +168,7 @@ def sample_txt(tmp_path):
|
||||
def sample_pdf(tmp_path):
|
||||
"""Create a minimal valid PDF for testing."""
|
||||
import fitz
|
||||
|
||||
doc = fitz.open()
|
||||
page = doc.new_page()
|
||||
page.insert_text((50, 50), "Test PDF document about contracts and legal matters.")
|
||||
@@ -75,55 +176,3 @@ def sample_pdf(tmp_path):
|
||||
doc.save(str(pdf_path))
|
||||
doc.close()
|
||||
return pdf_path
|
||||
|
||||
|
||||
# ── Async fixtures (Phase 1 additions — Plan 03+ tests use these) ──────────────
|
||||
|
||||
@pytest_asyncio.fixture
|
||||
async def db_session():
|
||||
"""In-memory async SQLite session for unit tests.
|
||||
|
||||
Tries to import db.models.Base (available after Plan 03). If the module
|
||||
does not yet exist the fixture skips the test gracefully so the suite
|
||||
stays green during Wave 1.
|
||||
"""
|
||||
engine = create_async_engine(
|
||||
"sqlite+aiosqlite:///:memory:",
|
||||
connect_args={"check_same_thread": False},
|
||||
poolclass=StaticPool,
|
||||
)
|
||||
|
||||
try:
|
||||
from db.models import Base
|
||||
async with engine.begin() as conn:
|
||||
await conn.run_sync(Base.metadata.create_all)
|
||||
except ImportError:
|
||||
await engine.dispose()
|
||||
pytest.skip("db.models not yet implemented — plan 03")
|
||||
|
||||
AsyncTestSession = async_sessionmaker(engine, expire_on_commit=False)
|
||||
async with AsyncTestSession() as session:
|
||||
yield session
|
||||
|
||||
await engine.dispose()
|
||||
|
||||
|
||||
@pytest_asyncio.fixture
|
||||
async def async_client(db_session):
|
||||
"""Async HTTP test client with DB dependency overridden.
|
||||
|
||||
Tries to import deps.db.get_db (available after Plan 03). If the module
|
||||
does not yet exist the fixture skips the test gracefully.
|
||||
"""
|
||||
try:
|
||||
from deps.db import get_db
|
||||
from main import app
|
||||
except ImportError as exc:
|
||||
pytest.skip(f"deps.db.get_db not yet implemented — plan 03: {exc}")
|
||||
|
||||
app.dependency_overrides[get_db] = lambda: db_session
|
||||
|
||||
async with AsyncClient(transport=ASGITransport(app=app), base_url="http://test") as c:
|
||||
yield c
|
||||
|
||||
app.dependency_overrides.clear()
|
||||
|
||||
Reference in New Issue
Block a user