feat(db_compare): add PostgreSQL-based comparison engine with SF handling

Replace Excel-based undelivered comparison with DB queries for all four
sites. The engine anchors on actual scan_time, reverse-lookups handover
batches, and compares expected vs actual waybill-by-waybill.

Shunxin SF waybills: use COUNT(*) instead of COUNT(DISTINCT piece_no)
since SF piece numbers are random and not derivable from the waybill.

Changes:
- db_compare.py: new module with compare_site_date(), compare_site_batch(),
  write_result_excel(), and POST /compare API endpoint
- runtime.py: switch _site_undelivered_handler from compare.write_site_file
  (Excel) to db_compare (DB); downloads succeed independently of comparison
- server.py: add POST /compare endpoint with date validation
- docs: implementation plan for Shunxin DB comparison

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Misaka_Company
2026-07-31 16:31:54 +08:00
parent 95597fbb0c
commit 541836fd1b
4 changed files with 894 additions and 9 deletions

View File

@@ -476,23 +476,44 @@ def _web_handler(site, download_func):
def _site_undelivered_handler(site):
"""4 站未到:下应到+实到 → 比对写 downloads/<站>-未到数据.xlsx。
任一下载失败 → 清掉旧未到文件、返回 False前端不展示陈旧未到"""
"""4 站未到:下应到+实到 → DB 比对 → 写 output/<站>-<日期>-未到数据.xlsx。
应到全量去重(已落库则跳过导出),因此比对不依赖 Excel 文件,走数据库查询。
下载成功则返回 True比对失败不影响任务判定数据已入库"""
def handler(ctx, force=False, date=None):
# 各站下载入口约定返回 True/False顺心历史返回 None视为成功与 dispatch 一致)
exp_ok = TASK_HANDLERS[(site, "expected")](ctx, force, date) is not False
act_ok = (
(TASK_HANDLERS[(site, "actual")](ctx, force, date) is not False)
if exp_ok
else False
)
if exp_ok and act_ok:
return compare.write_site_file(site)
stale = os.path.join(DOWNLOAD_DIR, SITE_UNDELIVERED_FILE.format(name=site))
if os.path.exists(stale):
os.remove(stale)
return False
if not exp_ok or not act_ok:
stale = os.path.join(DOWNLOAD_DIR, SITE_UNDELIVERED_FILE.format(name=site))
if os.path.exists(stale):
os.remove(stale)
return False
# ── DB 比对(替代旧 Excel 比对)──
try:
from inbound_verify import db_compare # 懒导入,避免成环
if date:
target_date = date
else:
offset = state_store.get_offset(site, "expected")
target_date = (datetime.now().date() - timedelta(days=offset)).strftime(
"%Y-%m-%d"
)
result = db_compare.compare_site_date(site, target_date)
if result is not None:
db_compare.write_result_excel(result)
else:
print(f">> [未到] {site} {target_date}: 当天无实到数据,跳过比对")
except Exception as e:
print(f">> [未到] {site} DB 比对异常(不影响下载结果): {e}")
return True # 下载成功即返回 True比对失败不影响任务判定
return handler