chore: 重构前基线 — 9 个 sync task 全部 ok + akshare 移除 + mairui 资金流接入

状态： - 9 个 sync task（stock_basic / kline_daily / kline_index / kline_5min / moneyflow / industry_sector / sector_features / share_snapshot / market_regime） - 数据源：baostock + mairui + 雪球(pysnowball) + 新浪（4 个） - 项目级约束：永远不用 akshare（已落实） - kline_5min 改用 DB 快照统一全量/增量逻辑 - 零后端 Chrome 扩展 xueqiu_sync（独立项目）
2026-06-15 15:36:09 +08:00
commit 05635b76b9
55 changed files with 6307 additions and 0 deletions
@@ -0,0 +1,81 @@
+"""一次性跑完所有 sync task（按依赖顺序）。
+
+跳过 industry_sector（已 ok）。
+按顺序触发：stock_basic → kline_daily → kline_index → kline_5min → moneyflow
+          → share_snapshot → market_regime
+
+每个 task 跑完写日志 + 把 result 落到 summary.json。
+"""
+from __future__ import annotations
+
+import json
+import sys
+import time
+from pathlib import Path
+
+_PROJECT_ROOT = Path(__file__).resolve().parent.parent
+if str(_PROJECT_ROOT) not in sys.path:
+    sys.path.insert(0, str(_PROJECT_ROOT))
+
+from app.core.utils.logging import setup_logging, get_logger
+setup_logging()
+logger = get_logger("runall")
+
+from app.core.datasource.registry import build_default_registry
+from app.core.sync.registry import seed_sync_registry
+build_default_registry()
+seed_sync_registry()
+
+from app.tasks import get_task
+
+# 顺序执行，便于排查
+TASKS = [
+    "stock_basic",
+    "industry_sector",  # 已 ok，但再跑一次全量也 OK (用 SKIP 标志)
+    "kline_index",
+    "kline_daily",
+    "kline_5min",
+    "moneyflow",
+    "share_snapshot",
+    "market_regime",
+]
+
+# industry_sector 跑过一次（291s 全量）已 ok，跳过
+SKIP = {"industry_sector"}
+
+results = {}
+t_all = time.time()
+for tid in TASKS:
+    if tid in SKIP:
+        results[tid] = {"status": "skipped", "message": "已 ok"}
+        logger.info(f"[runall] {tid} 跳过（已 ok）")
+        continue
+    logger.info(f"[runall] >>> 开始 {tid}")
+    t0 = time.time()
+    try:
+        task = get_task(tid)
+        # 大表 task 限小批量股票，避免跑爆；其他 task 跑全量
+        kwargs = {"max_workers": 5}
+        if tid in {"kline_daily", "kline_5min", "moneyflow", "share_snapshot"}:
+            # 这些 task 支持 MARKET_DATA_STOCK_LIMIT 环境变量，但通过 cli 跑可 --codes 限
+            # 测全量费时，先跑全量
+            pass
+        r = task.run(trigger_source="runall", **kwargs)
+        elapsed = round(time.time() - t0, 1)
+        r["elapsed_sec"] = elapsed
+        results[tid] = r
+        logger.info(f"[runall] <<< {tid} 完成 status={r.get('status')} elapsed={elapsed}s msg={r.get('message')}")
+    except Exception as e:
+        elapsed = round(time.time() - t0, 1)
+        logger.exception(f"[runall] !!! {tid} 异常: {e}")
+        results[tid] = {"status": "error", "message": str(e), "elapsed_sec": elapsed}
+
+    # 每个 task 之间 sleep 5s 让健康监控跑
+    time.sleep(5)
+
+elapsed_total = round(time.time() - t_all, 1)
+summary = {"total_elapsed_sec": elapsed_total, "tasks": results}
+out = _PROJECT_ROOT / "logs" / "runall_summary.json"
+out.write_text(json.dumps(summary, ensure_ascii=False, indent=2))
+logger.info(f"[runall] 全部完成 total={elapsed_total}s summary={out}")
+print(json.dumps(summary, ensure_ascii=False, indent=2))