128 lines
5.8 KiB
Python
128 lines
5.8 KiB
Python
"""数据核验日报(每日 18:30):近 N 天 RIIN/SDS 订单+商品数据准确性核验并上报企微。
|
||
|
||
对应 daily-report deployment,cron 30 18 * * *。内容:
|
||
1. 复用 riin-verify / sds-verify 逻辑(subflow 调用):远程 vs 本地逐天逐状态计数比对,
|
||
有差异自动拉取修复——与早 6/7 点的每日核验互补,二次确认白天同步质量。
|
||
2. 商品数据完整性:窗口内零商品订单 / 商品无名称 / 全库孤儿商品(本地 SQL)。
|
||
3. OCR 处理状态与当日失败 flow runs 回顾(事件报警的兜底汇总)。
|
||
|
||
消息排版遵循 WeCom markdown 子集(无表格,引用块+彩色字体)。
|
||
"""
|
||
|
||
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 _short_date(date_str: str) -> str:
|
||
return date_str[5:] if len(date_str) == 10 and date_str[:4].isdigit() else date_str
|
||
|
||
|
||
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 build_daily_message(
|
||
days: int, window: str, riin: dict, sds: dict,
|
||
goods: dict, ocr: dict, failures: list[dict],
|
||
) -> tuple[str, bool]:
|
||
"""拼装日报 markdown,返回 (消息, 是否需关注)。结论式极简排版,不暴露内部术语。"""
|
||
lines = [f"📊 **数据核验日报** {datetime.now().strftime('%m-%d %H:%M')}"
|
||
f"（近 {days} 天，{window}）", ""]
|
||
attention = False
|
||
diff_names: list[str] = []
|
||
|
||
for name, report in (("RIIN", riin), ("SDS", sds)):
|
||
try:
|
||
days_r = (report.get("verifyReport") or {}).get("days") or []
|
||
summary = (report.get("verifyReport") or {}).get("summary") or {}
|
||
diff_days = [d for d in days_r if not d.get("ok")]
|
||
total = summary.get("totalDays", len(days_r))
|
||
if not diff_days:
|
||
lines.append(f"**{name}** {total}/{total} 天与远程一致 ✅")
|
||
else:
|
||
diff_names.append(name)
|
||
attention = True
|
||
lines.append(f"**{name}** {total - len(diff_days)}/{total} 天与远程一致 ⚠️")
|
||
if len(diff_days) <= 4:
|
||
per_day = " · ".join(
|
||
f"{_short_date(d['date'])} {_affected_units(d.get('diff'))}单" for d in diff_days)
|
||
lines.append(f"> {per_day}状态不符，已自动重新同步")
|
||
else:
|
||
total_affected = sum(_affected_units(d.get("diff")) for d in diff_days)
|
||
lines.append(f"> {len(diff_days)} 天共约 {total_affected:,} 单状态不符，已自动重新同步")
|
||
except Exception as err: # noqa: BLE001
|
||
lines.append(f"**{name}** 核验结果解析失败：{err}")
|
||
attention = True
|
||
|
||
zero_total = sum(g["zeroGoodsOrders"] for g in goods.values())
|
||
lines += ["", f"**商品** RIIN {goods['RIIN']['orders']:,} 单/{goods['RIIN']['goods']:,} 行"
|
||
f" · SDS {goods['SDS']['orders']:,} 单/{goods['SDS']['goods']:,} 行"
|
||
+ (" ⚠️" if zero_total else " ✅")]
|
||
if zero_total:
|
||
lines.append(f"> 有 {zero_total} 单缺商品数据")
|
||
attention = True
|
||
lines.append(f"**OCR** 已完成 {ocr.get('done', 0):,} · 待处理 {ocr.get('pending', 0):,}"
|
||
f" · 失败 {ocr.get('error', 0):,}")
|
||
if failures:
|
||
attention = True
|
||
names = "、".join(f"{f['name']}（{f['state']}）" for f in failures[:4])
|
||
lines.append(f"**失败任务(24h)** {len(failures)} 个：{names}")
|
||
else:
|
||
lines.append("**失败任务(24h)** 0 个 ✅")
|
||
|
||
lines.append("")
|
||
if attention:
|
||
lines.append("⚠️ **存在需关注项，见上**")
|
||
if diff_names:
|
||
lines.append("> 每天都出现的相同差异属远程统计口径问题，非数据丢失")
|
||
else:
|
||
lines.append("✅ **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 = 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, 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 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, "ocr": ocr, "failures24h": len(failures)}
|
||
|
||
|
||
if __name__ == "__main__":
|
||
daily_report.serve(name="daily-report", cron="30 18 * * *")
|