Files
fa-agent/finance/management/commands/import_worker.py
T
Jayway Liu 5ebe83afbb
Verify / verify (push) Failing after 1s
Verify / verify (pull_request) Failing after 25s
fix(worker): F08 执行/下载统一核验角色与账号状态,恢复卡死的 processing 任务
- worker 执行前重新核验账号 is_active 与 admin/analyst 角色:撤权/停用后排队任务
  直接失败,不发布敏感工作簿
- formula-exports 状态与下载接口补齐与创建接口一致的角色白名单,被降为 viewer
  的账号不能再查询/下载旧导出
- import_worker 对超过 15 分钟仍处于 processing 的任务重新认领(PostgreSQL 依赖
  咨询锁立即恢复),崩溃重启不再无限停留 processing;新近 processing 不被抢占
- 测试:撤权/停用执行、viewer 下载与状态 403、半成品/缺文件下载 409/410、
  超时任务恢复且无重复临时文件、新近 processing 不被重复认领
2026-09-26 01:22:37 +08:00

85 lines
3.5 KiB
Python

import time
from datetime import timedelta
from django.core.management.base import BaseCommand
from django.db import connection, transaction
from django.db.models import Q
from django.utils import timezone
from finance.exporting import process_formula_export
from finance.importing import process_dataset
from finance.models import Dataset, FormulaExport
# 无咨询锁的数据库(如 SQLite)上等待该时限后才重新认领 processing 任务,
# 避免与仍在运行的 worker 抢任务;PostgreSQL 由咨询锁保证单 worker,可立即恢复。
STALE_PROCESSING_SECONDS = 15 * 60
class Command(BaseCommand):
help = "Process durable import and formula-export jobs"
def add_arguments(self, parser):
parser.add_argument("--once", action="store_true")
def handle(self, *args, **options):
postgres = connection.vendor == "postgresql"
if postgres:
with connection.cursor() as cursor:
cursor.execute("SELECT pg_try_advisory_lock(782146291)")
if not cursor.fetchone()[0]:
self.stdout.write("Another worker owns the database lock")
return
try:
self.run_jobs(options, postgres)
finally:
if postgres:
with connection.cursor() as cursor:
cursor.execute("SELECT pg_advisory_unlock(782146291)")
def run_jobs(self, options, recover_immediately):
while True:
processed = self._next_import(recover_immediately)
if not processed:
processed = self._next_export(recover_immediately)
if options["once"]:
return
if not processed:
time.sleep(2)
def _claim(self, model, immediate_recovery):
stale_before = timezone.now() - timedelta(seconds=STALE_PROCESSING_SECONDS)
claimable = Q(status="queued") | Q(status="processing", created_at__lt=stale_before)
if immediate_recovery:
claimable = Q(status="queued") | Q(status="processing")
with transaction.atomic():
qs = model.objects.filter(claimable).order_by("created_at")
if connection.features.has_select_for_update_skip_locked:
qs = qs.select_for_update(skip_locked=True)
item = qs.first()
if not item:
return None
# CAS 认领 queued 任务互斥;processing 仅在超时或咨询锁保护下重认领,
# 重复发布对同一目标路径写入相同内容,不会产生重复文件。
claimed = model.objects.filter(pk=item.pk, status=item.status).update(status="processing")
return item if claimed else None
def _next_import(self, recover_immediately):
item = self._claim(Dataset, recover_immediately)
if not item:
return False
Dataset.objects.filter(pk=item.pk).update(started_at=timezone.now())
result = process_dataset(item.pk)
self.stdout.write(f"{result.pk}: {result.status}, {result.row_count} rows")
return True
def _next_export(self, recover_immediately):
item = self._claim(FormulaExport, recover_immediately)
if not item:
return False
try:
stats = process_formula_export(item.pk)
self.stdout.write(f"{item.pk}: formula export ready, {stats['rows']} rows")
except Exception as exc:
self.stderr.write(f"Formula export {item.pk} failed: {exc}")
return True