Files
gh-christianlouis-docuelevate/app/database.py
T
2026-05-31 01:16:23 +02:00

153 lines
6.2 KiB
Python

# app/database.py
import logging
import os
from collections.abc import Generator
from typing import Any
from sqlalchemy import create_engine, exc
from sqlalchemy.engine.url import make_url
from sqlalchemy.orm import Session, declarative_base, sessionmaker
from sqlalchemy.pool import NullPool, QueuePool
from app.config import settings
logger = logging.getLogger(__name__)
Base = declarative_base()
DB_URL = settings.database_url
_parsed_url = make_url(DB_URL)
_connect_args: dict[str, Any] = {}
_engine_kwargs: dict[str, Any] = {"pool_pre_ping": True}
if _parsed_url.get_backend_name() == "sqlite":
_connect_args["check_same_thread"] = False
_engine_kwargs["poolclass"] = NullPool
else:
_engine_kwargs.update(
{
"poolclass": QueuePool,
"pool_size": int(os.getenv("DB_POOL_SIZE", "10")),
"max_overflow": int(os.getenv("DB_MAX_OVERFLOW", "20")),
"pool_timeout": int(os.getenv("DB_POOL_TIMEOUT", "30")),
"pool_recycle": int(os.getenv("DB_POOL_RECYCLE", "1800")),
}
)
engine = create_engine(DB_URL, connect_args=_connect_args, **_engine_kwargs)
SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
def init_db() -> None:
"""
Ensures the SQLite database file and its parent directory exist (if using sqlite).
Then runs Base.metadata.create_all(bind=engine) to initialize tables.
Logs a message if a new SQLite DB file is created.
"""
# 1. Parse the DB URL to see if it's sqlite
url = make_url(DB_URL)
if url.get_backend_name() == "sqlite":
# 2. Extract the database path from the URL
database_path = url.database # e.g. "/workdir/db/database.db" or ":memory:"
if database_path != ":memory:":
# 3. Ensure directory exists
db_dir = os.path.dirname(database_path)
if db_dir and not os.path.exists(db_dir):
logger.info(f"Creating directory for SQLite DB: {db_dir}")
os.makedirs(db_dir, exist_ok=True)
# 4. If the file does not exist, create an empty one
if not os.path.exists(database_path):
logger.info(f"Creating new SQLite database file at {database_path}")
open(database_path, "a").close()
# 5. Now create tables if they don't exist yet
try:
import app.models # noqa: F401
Base.metadata.create_all(bind=engine)
logger.info("Database initialization complete (tables created if not exist).")
# 6. Run lightweight schema migrations for existing databases
_run_schema_migrations(engine)
except exc.SQLAlchemyError as e:
logger.error(f"Error initializing database: {e}")
raise
def _run_schema_migrations(engine: Any) -> None:
"""
Apply lightweight schema migrations for columns added after the initial release.
Each migration is idempotent and safe to run multiple times.
"""
from sqlalchemy import inspect, text
inspector = inspect(engine)
# Migration: Add 'detail' column to processing_logs (added for verbose worker log output)
if "processing_logs" in inspector.get_table_names():
columns = [col["name"] for col in inspector.get_columns("processing_logs")]
if "detail" not in columns:
logger.info("Migrating processing_logs: adding 'detail' column")
with engine.begin() as conn:
conn.execute(text("ALTER TABLE processing_logs ADD COLUMN detail TEXT"))
logger.info("Migration complete: 'detail' column added to processing_logs")
# Migration: Add file path columns to files table
if "files" in inspector.get_table_names():
columns = [col["name"] for col in inspector.get_columns("files")]
if "original_file_path" not in columns:
logger.info("Migrating files: adding 'original_file_path' column")
with engine.begin() as conn:
conn.execute(text("ALTER TABLE files ADD COLUMN original_file_path VARCHAR"))
logger.info("Migration complete: 'original_file_path' column added to files")
if "processed_file_path" not in columns:
logger.info("Migrating files: adding 'processed_file_path' column")
with engine.begin() as conn:
conn.execute(text("ALTER TABLE files ADD COLUMN processed_file_path VARCHAR"))
logger.info("Migration complete: 'processed_file_path' column added to files")
# Migration: Add deduplication columns to files table
if "is_duplicate" not in columns:
logger.info("Migrating files: adding 'is_duplicate' column")
with engine.begin() as conn:
conn.execute(text("ALTER TABLE files ADD COLUMN is_duplicate BOOLEAN DEFAULT FALSE NOT NULL"))
logger.info("Migration complete: 'is_duplicate' column added to files")
if "duplicate_of_id" not in columns:
logger.info("Migrating files: adding 'duplicate_of_id' column")
with engine.begin() as conn:
conn.execute(text("ALTER TABLE files ADD COLUMN duplicate_of_id INTEGER"))
logger.info("Migration complete: 'duplicate_of_id' column added to files")
# Migration: Drop unique index on filehash to allow duplicate records
try:
indexes = inspector.get_indexes("files")
unique_filehash_indexes = [
index for index in indexes if index.get("unique") and "filehash" in index.get("column_names", [])
]
if unique_filehash_indexes:
logger.info("Migrating files: dropping unique index on 'filehash'")
with engine.begin() as conn:
for index in unique_filehash_indexes:
conn.execute(text(f"DROP INDEX IF EXISTS {index['name']}"))
logger.info("Migration complete: unique index on 'filehash' removed")
except Exception as exc:
logger.warning(f"Skipping filehash unique index drop: {exc}")
def get_db() -> Generator[Session, None, None]:
"""
Dependency for FastAPI routes or general DB usage.
Yields a SQLAlchemy session, and closes it upon exit.
"""
db = SessionLocal()
try:
yield db
finally:
db.close()