deerflow-code/offline-backend-20260512/backend/app/gateway/auth/repositories/sqlite.py
2026-09-07 18:24:55 +08:00

188 lines
8.1 KiB
Python

"""SQLAlchemy-backed UserRepository implementation.
Uses the shared async session factory from
``deerflow.persistence.engine`` — the ``users`` table lives in the
same database as ``threads_meta``, ``runs``, ``run_events``, and
``feedback``.
Constructor takes the session factory directly (same pattern as the
other four repositories in ``deerflow.persistence.*``). Callers
construct this after ``init_engine_from_config()`` has run.
"""
from __future__ import annotations
from datetime import UTC
from uuid import UUID
from sqlalchemy import func, select
from sqlalchemy.exc import IntegrityError
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker
from app.gateway.auth.models import User
from app.gateway.auth.repositories.base import UserNotFoundError, UserRepository
from deerflow.persistence.user.model import UserRow
class SQLiteUserRepository(UserRepository):
"""Async user repository backed by the shared SQLAlchemy engine."""
def __init__(self, session_factory: async_sessionmaker[AsyncSession]) -> None:
self._sf = session_factory
# ── Converters ────────────────────────────────────────────────────
@staticmethod
def _row_to_user(row: UserRow) -> User:
return User(
id=UUID(row.id),
email=row.email,
password_hash=row.password_hash,
system_role=row.system_role, # type: ignore[arg-type]
# SQLite loses tzinfo on read; reattach UTC so downstream
# code can compare timestamps reliably.
created_at=row.created_at if row.created_at.tzinfo else row.created_at.replace(tzinfo=UTC),
oauth_provider=row.oauth_provider,
oauth_id=row.oauth_id,
needs_setup=row.needs_setup,
token_version=row.token_version,
approved=row.approved,
login_password=row.login_password,
)
@staticmethod
def _user_to_row(user: User) -> UserRow:
return UserRow(
id=str(user.id),
email=user.email,
password_hash=user.password_hash,
system_role=user.system_role,
created_at=user.created_at,
oauth_provider=user.oauth_provider,
oauth_id=user.oauth_id,
needs_setup=user.needs_setup,
token_version=user.token_version,
approved=user.approved,
login_password=user.login_password,
)
# ── CRUD ──────────────────────────────────────────────────────────
async def create_user(self, user: User) -> User:
"""Insert a new user. Raises ``ValueError`` on duplicate email."""
row = self._user_to_row(user)
async with self._sf() as session:
session.add(row)
try:
await session.commit()
except IntegrityError as exc:
await session.rollback()
raise ValueError(f"Email already registered: {user.email}") from exc
return user
async def get_user_by_id(self, user_id: str) -> User | None:
async with self._sf() as session:
row = await session.get(UserRow, user_id)
return self._row_to_user(row) if row is not None else None
async def get_user_by_email(self, email: str) -> User | None:
stmt = select(UserRow).where(UserRow.email == email)
async with self._sf() as session:
result = await session.execute(stmt)
row = result.scalar_one_or_none()
return self._row_to_user(row) if row is not None else None
async def find_user_by_email_local_part(self, local_part: str) -> User | None:
local = (local_part or "").strip().lower()
if not local:
return None
# Escape SQL LIKE wildcards so usernames like ``foo_bar`` or ``a%b`` do
# not match unrelated rows. ``\`` is the chosen escape char below.
escaped = local.replace("\\", "\\\\").replace("%", "\\%").replace("_", "\\_")
pattern = f"{escaped}@%"
# Case-insensitive prefix match on the email field, oldest first so a
# subsequent registration cannot shadow an existing account.
stmt = (
select(UserRow)
.where(func.lower(UserRow.email).like(pattern, escape="\\"))
.order_by(UserRow.created_at.asc())
.limit(1)
)
async with self._sf() as session:
result = await session.execute(stmt)
row = result.scalar_one_or_none()
return self._row_to_user(row) if row is not None else None
async def find_users_by_email_local_part_like(self, substring: str, *, limit: int = 500) -> list[User]:
term = (substring or "").strip().lower()
if not term:
return []
# Escape SQL LIKE wildcards so a literal ``_``/``%`` in the query does
# not turn into a wildcard. ``\`` is the chosen escape char.
escaped = term.replace("\\", "\\\\").replace("%", "\\%").replace("_", "\\_")
pattern = f"%{escaped}%"
# Prefilter in SQL on the whole email (portable across sqlite/postgres/
# mysql), then keep only rows whose *local part* contains the term so a
# domain-only hit (e.g. searching "gmail") doesn't pull unrelated users.
stmt = (
select(UserRow)
.where(func.lower(UserRow.email).like(pattern, escape="\\"))
.order_by(UserRow.created_at.asc())
.limit(max(1, limit))
)
async with self._sf() as session:
result = await session.execute(stmt)
rows = result.scalars().all()
out: list[User] = []
for row in rows:
local = (row.email or "").split("@", 1)[0].lower()
if term in local:
out.append(self._row_to_user(row))
return out
async def update_user(self, user: User) -> User:
async with self._sf() as session:
row = await session.get(UserRow, str(user.id))
if row is None:
# Hard fail on concurrent delete: callers (reset_admin,
# password change handlers, _ensure_admin_user) all
# fetched the user just before this call, so a missing
# row here means the row vanished underneath us. Silent
# success would let the caller log "password reset" for
# a row that no longer exists.
raise UserNotFoundError(f"User {user.id} no longer exists")
row.email = user.email
row.password_hash = user.password_hash
row.system_role = user.system_role
row.oauth_provider = user.oauth_provider
row.oauth_id = user.oauth_id
row.needs_setup = user.needs_setup
row.token_version = user.token_version
row.approved = user.approved
row.login_password = user.login_password
await session.commit()
return user
async def count_users(self) -> int:
stmt = select(func.count()).select_from(UserRow)
async with self._sf() as session:
return await session.scalar(stmt) or 0
async def count_admin_users(self) -> int:
stmt = select(func.count()).select_from(UserRow).where(UserRow.system_role == "admin")
async with self._sf() as session:
return await session.scalar(stmt) or 0
async def list_users(self) -> list[User]:
stmt = select(UserRow).order_by(UserRow.created_at.asc())
async with self._sf() as session:
result = await session.execute(stmt)
return [self._row_to_user(row) for row in result.scalars()]
async def get_user_by_oauth(self, provider: str, oauth_id: str) -> User | None:
stmt = select(UserRow).where(UserRow.oauth_provider == provider, UserRow.oauth_id == oauth_id)
async with self._sf() as session:
result = await session.execute(stmt)
row = result.scalar_one_or_none()
return self._row_to_user(row) if row is not None else None