浅念
421998be54
根因(服务器实测):sessions 对 owner 全量 message GROUP BY,重账号 5.2万条 3~5s;staff-chat-stats 全时段窗 6.9s——128MB buffer pool 下被推过前端 15s 超时(ECONNABORTED)。EXPLAIN ANALYZE 证实最优 covering 索引也要 18.9s,瓶颈是磁盘不是查询形状。 修复(预聚合,云客同款思路): - msg_daily_stats 表:每「渠道×账号×会话×上海自然日」一行(收发计数/ 当日最后时间与方向);迁移 a7d3e9f1c2b4(幂等建表) - 写路径:repos.upsert_messages 落库自动重算本批触及的会话×天(所有 抓取路径汇到该函数,一处挂全;失败不阻塞写入) - 读路径:sessions/staff-chat-stats 表有行时读汇总(namedtuple 同形, 端点主体零改动),空表守卫回退旧聚合(部署回填前不空白) - 自愈:CLI daily-stats 全量重建(幂等);full_sync_all.sh 夜间追加第 11 步——顺带修掉尾部 sqlite3 直连 smoke.db 的硬编码(服务器 MySQL 上会炸) - 口径统一:day 一律 Asia/Shanghai Python 计算(旧 from_unixtime 跟随 DB 会话时区与今日数割裂);统计窗口对齐自然日(文档化语义变化) 测试:12 新增(汇总层 8 + 端点判别/对拍 4,判别手法=回填后删光 message 仍出完整数据),全量 512 绿。 Co-Authored-By: Claude Code <noreply@anthropic.com>
99 lines
4.3 KiB
Bash
99 lines
4.3 KiB
Bash
#!/bin/bash
|
|
# FULL page-based re-sync: ALL channels, ALL entities — ZERO API calls, ZERO 风控
|
|
cd "$(dirname "$0")/.."
|
|
# DB_URL:外部已设则沿用(容器里由 docker-compose 注入 MySQL);本地默认 SQLite
|
|
export DB_URL="${DB_URL:-sqlite+aiosqlite:///./smoke.db}"
|
|
# 可移植 python:容器里 python 在 PATH;本地 Windows 用 venv 的解释器(2026-08-21 部署阻塞点#3)
|
|
if [ -f ".venv/Scripts/python.exe" ]; then
|
|
PY=".venv/Scripts/python.exe"
|
|
else
|
|
PY="python"
|
|
fi
|
|
|
|
echo "=============================================="
|
|
echo "$(date) === FULL PAGE-BASED RE-SYNC (NO API) ==="
|
|
echo "=============================================="
|
|
|
|
echo "$(date) --- 1/10 WeChat accounts ---"
|
|
$PY scripts/scrape_via_page.py --entity accounts
|
|
echo "$(date) --- 2/10 WA accounts ---"
|
|
$PY scripts/scrape_via_page.py --entity wa-accounts
|
|
echo "$(date) --- 3/10 WeChat customers ---"
|
|
$PY scripts/scrape_via_page.py --entity friends --max-employees 100
|
|
echo "$(date) --- 4/10 WA customers ---"
|
|
$PY scripts/scrape_via_page.py --entity wa-friends
|
|
echo "$(date) --- 5/10 WeChat groups ---"
|
|
$PY scripts/scrape_via_page.py --entity groups --max-employees 100
|
|
echo "$(date) --- 5b/10 WA groups ---"
|
|
$PY scripts/scrape_via_page.py --entity wa-groups
|
|
echo "$(date) --- 6/10 Voice calls (WeChat + WA) ---"
|
|
$PY scripts/scrape_via_page.py --entity voice-calls
|
|
# 语音重扫会把 record_media_hash 覆盖回 None —— 必须紧跟录音重链接
|
|
$PY -m app.sync.cli sync --entity call_recordings
|
|
echo "$(date) --- 7/10 Voice clips ---"
|
|
$PY scripts/scrape_via_page.py --entity voice-clips
|
|
echo "$(date) --- 8/10 WeChat messages ---"
|
|
$PY scripts/scrape_via_page.py --entity messages --max-conversations 99999
|
|
echo "$(date) --- 8b/10 WeChat group messages + members ---"
|
|
$PY scripts/scrape_via_page.py --entity group-messages --max-conversations 99999
|
|
$PY -m scripts.backfill_group_members
|
|
echo "$(date) --- 9/10 WA messages ---"
|
|
$PY scripts/scrape_via_page.py --entity wa-messages --max-conversations 99999
|
|
echo "$(date) --- 9b/10 WA group messages ---"
|
|
$PY scripts/scrape_via_page.py --entity wa-group-messages --max-conversations 99999
|
|
echo "$(date) --- 9c/10 Moments (员工朋友圈) ---"
|
|
$PY scripts/scrape_via_page.py --entity moments
|
|
echo "$(date) --- 10/10 Media download (audio+images) ---"
|
|
$PY scripts/scrape_via_page.py --entity media
|
|
# 11:会话日汇总全量重建(夜间自愈:绕过 upsert 钩子的写入由它纠正;
|
|
# sessions/staff-chat-stats 读路径依赖此表,2026-09-03)
|
|
echo "$(date) --- 11/11 Daily-stats rebuild ---"
|
|
$PY -m app.sync.cli daily-stats
|
|
|
|
echo "=============================================="
|
|
echo "$(date) === FULL RE-SYNC COMPLETE ==="
|
|
echo "=============================================="
|
|
|
|
# 终局数据快照:走 app 引擎(DB_URL 可移植,SQLite/MySQL 通吃;原 sqlite3
|
|
# 直连 smoke.db 的写法在服务器 MySQL 上会炸,2026-09-03 修)
|
|
$PY - <<'PYEOF'
|
|
import asyncio
|
|
|
|
from sqlalchemy import text
|
|
from sqlalchemy.ext.asyncio import create_async_engine
|
|
|
|
from app.config import get_settings
|
|
|
|
TABLES = [
|
|
("wechat accounts", "SELECT COUNT(*) FROM wechat_account"),
|
|
("whatsapp accounts", "SELECT COUNT(*) FROM whatsapp_account"),
|
|
("wechat customers", "SELECT COUNT(*) FROM customer WHERE channel='wechat'"),
|
|
("whatsapp customers", "SELECT COUNT(*) FROM customer WHERE channel='whatsapp'"),
|
|
("wechat groups", "SELECT COUNT(*) FROM chat_group WHERE channel='wechat'"),
|
|
("whatsapp groups", "SELECT COUNT(*) FROM chat_group WHERE channel='whatsapp'"),
|
|
("wechat messages", "SELECT COUNT(*) FROM message WHERE channel='wechat'"),
|
|
("whatsapp messages", "SELECT COUNT(*) FROM message WHERE channel='whatsapp'"),
|
|
("daily stats rows", "SELECT COUNT(*) FROM msg_daily_stats"),
|
|
("voice calls", "SELECT COUNT(*) FROM phone_call WHERE channel IN ('voice_call','wa_voice_call')"),
|
|
("voice clips", "SELECT COUNT(*) FROM voice_clip"),
|
|
("moments posts", "SELECT COUNT(*) FROM moments_post"),
|
|
("media files", "SELECT COUNT(*) FROM media"),
|
|
]
|
|
|
|
|
|
async def main() -> None:
|
|
engine = create_async_engine(get_settings().db_url)
|
|
try:
|
|
async with engine.connect() as conn:
|
|
print()
|
|
print("=== FINAL DATA SUMMARY ===")
|
|
for label, sql in TABLES:
|
|
n = (await conn.execute(text(sql))).scalar_one()
|
|
print(f" {label:22s} {n:>6}")
|
|
finally:
|
|
await engine.dispose()
|
|
|
|
|
|
asyncio.run(main())
|
|
PYEOF
|