Simon
195f5d41f4
1) 数据装配流式+列裁剪：Repository 新增 stream_range_many_columns（只 SELECT 所需列、SQL 侧转 REAL、yield_per 分批），引擎按 required_columns 取数 （LocalEngine 仅 close+因子字段），消除 ORM/Decimal 全量物化； 2) 研究 Job 独立子进程执行（job.mode=subprocess）：python -m app.cli.run_job 在子进程内设 RLIMIT_AS 上限，OOM 归档 failed 而非拖垮 API worker； 子进程异常退出由父进程补记 failed；并发上限 2； 3) 服务启动清理：残留 queued/running Job 标记 failed（防永久 running）。 实测同款全市场回测：uvicorn worker RSS 稳定 ~220MB，任务峰值内存由 4.1GB+ 降至 ~470MB，24s 完成并归档（此前 43s 未完成即 OOM）。 新增/更新测试 96 passed，ruff 干净。
88 lines
2.8 KiB
Python
88 lines
2.8 KiB
Python
"""Repository Protocol（Phase 1 数据层）。
|
||
|
||
业务层只依赖这些 Protocol；具体实现位于 infrastructure/persistence。
|
||
实体一律以 domain.entities 类型进出，禁止把 ORM Model 泄漏到上层。
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
from collections.abc import Iterator, Sequence
|
||
from datetime import date
|
||
from typing import Protocol
|
||
|
||
from app.domain.entities.market import (
|
||
AdjustFactor,
|
||
DailyBar,
|
||
FinancialIndicator,
|
||
Stock,
|
||
SyncLog,
|
||
TradingCalendar,
|
||
)
|
||
|
||
|
||
class StockRepository(Protocol):
|
||
def get_by_symbol(self, symbol: str) -> Stock | None: ...
|
||
|
||
def list(self) -> list[Stock]: ...
|
||
|
||
def upsert_many(self, stocks: Sequence[Stock]) -> int:
|
||
"""批量写入，以 symbol 为幂等键，返回写入/更新的行数。"""
|
||
|
||
|
||
class TradingCalendarRepository(Protocol):
|
||
def upsert_many(self, days: Sequence[TradingCalendar]) -> int: ...
|
||
|
||
def list_range(self, start: date, end: date) -> list[TradingCalendar]: ...
|
||
|
||
def is_open(self, day: date) -> bool: ...
|
||
|
||
|
||
class DailyBarRepository(Protocol):
|
||
def upsert_many(self, bars: Sequence[DailyBar]) -> int: ...
|
||
|
||
def get_range(self, symbol: str, start: date, end: date) -> list[DailyBar]: ...
|
||
|
||
def get_range_many(self, symbols: Sequence[str], start: date, end: date) -> list[DailyBar]:
|
||
"""批量区间查询（研究服务装配面板用，避免逐只查询）。"""
|
||
|
||
def stream_range_many_columns(
|
||
self,
|
||
symbols: Sequence[str],
|
||
start: date,
|
||
end: date,
|
||
columns: Sequence[str],
|
||
) -> Iterator[tuple]:
|
||
"""流式（分批 yield）返回 symbol, trade_date(iso str), 数值列(float) 元组。
|
||
|
||
研究装配大数据面板专用：只 SELECT 所需列并在 SQL 侧转 REAL，
|
||
避免 ORM 对象 / Decimal 全量物化（内存大头，见内存优化专项）。
|
||
实现可选——ResearchService 会对缺失该方法的老实现回退到 get_range_many。
|
||
"""
|
||
|
||
def latest_date(self, symbol: str) -> date | None:
|
||
"""断点续传用：该股票本地已有数据的最新交易日。"""
|
||
|
||
|
||
class AdjustFactorRepository(Protocol):
|
||
def upsert_many(self, factors: Sequence[AdjustFactor]) -> int: ...
|
||
|
||
def get_range(self, symbol: str, start: date, end: date) -> list[AdjustFactor]: ...
|
||
|
||
|
||
class FinancialRepository(Protocol):
|
||
def upsert_many(self, rows: Sequence[FinancialIndicator]) -> int: ...
|
||
|
||
def list_announced(
|
||
self,
|
||
symbol: str,
|
||
as_of_date: date,
|
||
report_start: date | None = None,
|
||
) -> list[FinancialIndicator]:
|
||
"""只返回 announce_date <= as_of_date 的记录 —— 未来函数红线。"""
|
||
|
||
|
||
class SyncLogRepository(Protocol):
|
||
def add(self, log: SyncLog) -> SyncLog: ...
|
||
|
||
def recent(self, source: str | None = None, limit: int = 20) -> list[SyncLog]: ...
|