"""数据核验日报(每日 18:30):RIIN/SDS 数量一致性 + 状态差异 + OCR 当日 + 失败任务回顾。
对应 daily-report deployment,cron 30 18 * * *。报告结构:
1. RIIN/SDS:先报订单数量(远程 vs 本地,有差异修复后重数)与商品行数是否一致;
再报核验时发现多少单状态不符(已自动刷新修复)。subflow 复用 riin/sds-verify。
2. OCR:今天处理了多少订单、识别失败多少(按 ocrProcessedAt 盖章统计)。
3. 失败任务:近 24h 哪些 workflow、哪些 run、失败几次、何时失败(事件报警的兜底汇总)。
消息排版遵循 WeCom aibot markdown 子集(无表格、无 font 标签,引用块 + emoji)。
"""
from __future__ import annotations
from datetime import datetime, timedelta
from prefect import flow
from flows.monitor.device_check import check_prefect_failures
from flows.riin.verify import riin_verify
from flows.sds.verify import sds_verify
from flows.shared import SyncDB, emit_sync_summary, send_markdown, start_of_day
def _affected_units(diff: dict) -> int:
"""状态不符单数 ≈ 本地比远程多的状态计数之和(远程改了状态的单)。"""
return sum(v for v in (diff or {}).values() if v > 0)
def _system_lines(name: str, report: dict, goods: dict, lines: list[str]) -> bool:
"""单系统一行结论:数量(远程 vs 本地,一致只显示一个数)+商品;状态不符进引用行。"""
vr = (report.get("verifyReport") or {}) if isinstance(report, dict) else {}
days_r = vr.get("days") or []
post = vr.get("post")
if post:
remote_t, local_t = post["remote"], post["local"]
else:
remote_t = sum(d.get("remote", 0) for d in days_r)
local_t = sum(d.get("local", 0) for d in days_r)
ok = remote_t == local_t # 数量一致只看总量;状态差异属第二段,不混入数量结论
g = goods or {}
zero = g.get("zeroGoodsOrders", 0)
goods_txt = f"{g.get('goods', 0):,} 行" + (f'(缺 {zero:,})' if zero else "")
if ok:
order_txt = f"订单 {remote_t:,} 一致"
else:
order_txt = f"订单 远程 {remote_t:,} / 本地 {local_t:,} 不一致"
lines.append(f"**{name}** {order_txt} · 商品 {goods_txt}")
diff_days = [d for d in days_r if not d.get("ok")]
diff_units = sum(_affected_units(d.get("diff")) for d in diff_days)
if diff_units:
lines.append(f"> 状态不符约 {diff_units:,} 单({len(diff_days)} 天),已自动刷新修复")
return (not ok) or bool(zero)
def build_daily_message(
days: int, window: str, riin: dict, sds: dict,
goods: dict, ocr_today: dict, ocr_pending: int, failures: list[dict],
) -> tuple[str, bool]:
"""拼装日报 markdown,返回 (消息, 是否需关注)。单行结论 + 引用详情的紧凑排版。"""
lines = [f"## 数据核验日报 {datetime.now():%m-%d %H:%M}(近 {days} 天 {window})"]
attention = False
for name, report in (("RIIN", riin), ("SDS", sds)):
try:
attention |= _system_lines(name, report, (goods or {}).get(name), lines)
except Exception as err: # noqa: BLE001
lines.append(f"**{name}** 核验结果解析失败:{err}")
attention = True
processed, failed = (ocr_today or {}).get("processed", 0), (ocr_today or {}).get("failed", 0)
ocr_txt = f"**OCR** 今日处理 {processed:,} · 识别失败 "
ocr_txt += f'{failed:,}' if failed else "0"
if ocr_pending:
ocr_txt += f" · 待处理 {ocr_pending:,}"
lines.append(ocr_txt)
if failures:
attention = True
lines.append(f'**任务** 失败 {len(failures)} 次(24h)')
for f in failures[:6]:
start = (f.get("start") or "")[5:] # MM-DD HH:MM
lines.append(f"> {f.get('flow', '?')}:{f.get('name', '?')} {f.get('state', '?')} {start}")
if len(failures) > 6:
lines.append(f"> …等共 {len(failures)} 次")
else:
lines.append("**任务** 失败 0 次(24h)")
lines.append('存在需关注项,见上' if attention
else '数据全部一致,无异常')
return "\n".join(lines), attention
@flow(name="daily-report", log_prints=True)
def daily_report(days: int = 7) -> dict:
"""近 N 天数据核验 + 商品完整性 + OCR/失败回顾,发企微群日报。"""
today = start_of_day(datetime.now())
window_start = today - timedelta(days=days)
window_end = today # 与 verify 的 recent 约定一致:近 N 天、不含今天
riin = riin_verify(mode="recent", recent_days=days)
sds = sds_verify(mode="recent", recent_days=days)
db = SyncDB()
goods = {sys: db.get_goods_integrity(sys, window_start, window_end) for sys in ("RIIN", "SDS")}
ocr_today = db.count_ocr_today(today)
ocr = db.count_ocr_status()
failures = check_prefect_failures(hours=24)
window = f"{window_start:%m-%d}~{window_end:%m-%d}"
content, attention = build_daily_message(days, window, riin, sds, goods,
ocr_today, ocr.get("pending", 0), failures)
sent = send_markdown(content)
emit_sync_summary("数据核验日报", [
("核验窗口", f"近{days}天"), ("需关注", "是" if attention else "否"),
("RIIN 零商品订单", goods["RIIN"]["zeroGoodsOrders"]),
("RIIN 商品无名称", goods["RIIN"]["goodsNoName"]),
("SDS 零商品订单", goods["SDS"]["zeroGoodsOrders"]),
("SDS 商品无名称", goods["SDS"]["goodsNoName"]),
("全库孤儿商品", goods["RIIN"]["orphanGoods"]),
("OCR 今日处理", ocr_today.get("processed", 0)), ("OCR 今日失败", ocr_today.get("failed", 0)),
("OCR 待处理", ocr.get("pending", 0)), ("失败 runs(24h)", len(failures)),
("已发企微", "是" if sent else "否"),
])
return {"attention": attention, "sent": sent,
"goods": goods, "ocrToday": ocr_today, "failures24h": len(failures)}
if __name__ == "__main__":
daily_report.serve(name="daily-report", cron="30 18 * * *")