110 lines
3.5 KiB
Bash
Executable File
110 lines
3.5 KiB
Bash
Executable File
#!/bin/bash
|
||
# run_daily.sh - 每日数据采集与报告生成流水线
|
||
# Sprint 3: 完整调度脚本（采集→质量检查→报告生成→归档→通知）
|
||
set -euo pipefail
|
||
|
||
PROJECT_DIR="/home/long/project/llm-intelligence"
|
||
DB_URL="${DATABASE_URL:-host=/var/run/postgresql dbname=llm_intelligence user=long sslmode=disable}"
|
||
REPORT_DATE=$(date +%Y-%m-%d)
|
||
LOG_FILE="/tmp/llm_hub_daily_${REPORT_DATE}.log"
|
||
FEISHU_WEBHOOK="${FEISHU_WEBHOOK:-}"
|
||
|
||
# 日志函数
|
||
log() {
|
||
echo "[$(date '+%Y-%m-%d %H:%M:%S')] $1" | tee -a "$LOG_FILE"
|
||
}
|
||
|
||
# 错误处理
|
||
error_exit() {
|
||
log "❌ 错误: $1"
|
||
# 降级：复制昨日报告
|
||
fallback_report
|
||
# 发送告警
|
||
if [ -n "$FEISHU_WEBHOOK" ]; then
|
||
send_alert "$1"
|
||
fi
|
||
exit 1
|
||
}
|
||
|
||
# 降级：复制昨日报告
|
||
fallback_report() {
|
||
local yesterday=$(date -d "yesterday" +%Y-%m-%d)
|
||
local yesterday_md="${PROJECT_DIR}/reports/daily/daily_report_${yesterday}.md"
|
||
local today_md="${PROJECT_DIR}/reports/daily/daily_report_${REPORT_DATE}.md"
|
||
|
||
if [ -f "$yesterday_md" ]; then
|
||
cp "$yesterday_md" "$today_md"
|
||
sed -i "s/${yesterday}/${REPORT_DATE}/g" "$today_md"
|
||
sed -i "1s/^/# [数据延迟] /" "$today_md"
|
||
log "⚠️ 已复制昨日报告并标记[数据延迟]"
|
||
else
|
||
log "⚠️ 无昨日报告可供复制"
|
||
fi
|
||
}
|
||
|
||
# 发送飞书告警
|
||
send_alert() {
|
||
local msg="$1"
|
||
local payload="{\"msg_type\":\"text\",\"content\":{\"text\":\"🚨 LLM Hub 日报失败\\n日期: ${REPORT_DATE}\\n错误: ${msg}\\n请检查日志: ${LOG_FILE}\"}}"
|
||
|
||
curl -s -X POST -H "Content-Type: application/json" \
|
||
-d "$payload" \
|
||
"$FEISHU_WEBHOOK" > /dev/null || true
|
||
log "📢 飞书告警已发送"
|
||
}
|
||
|
||
# 主流程
|
||
log "🚀 开始每日流水线: ${REPORT_DATE}"
|
||
|
||
cd "$PROJECT_DIR"
|
||
|
||
# 1. 数据采集
|
||
log "1️⃣ 数据采集..."
|
||
if ! go run scripts/fetch_openrouter.go >> "$LOG_FILE" 2>&1; then
|
||
error_exit "数据采集失败"
|
||
fi
|
||
log "✅ 数据采集完成"
|
||
|
||
# 2. 数据质量检查
|
||
log "2️⃣ 数据质量检查..."
|
||
MODEL_COUNT=$(psql "$DB_URL" -t -c "SELECT COUNT(*) FROM models WHERE deleted_at IS NULL" 2>/dev/null | tr -d ' ')
|
||
if [ "$MODEL_COUNT" -lt 10 ]; then
|
||
error_exit "模型数量不足: ${MODEL_COUNT} < 10"
|
||
fi
|
||
log "✅ 数据质量检查通过 (模型数: ${MODEL_COUNT})"
|
||
|
||
# 3. 生成日报
|
||
log "3️⃣ 生成日报..."
|
||
export DATABASE_URL="$DB_URL"
|
||
if ! go run scripts/generate_daily_report.go >> "$LOG_FILE" 2>&1; then
|
||
error_exit "日报生成失败"
|
||
fi
|
||
log "✅ 日报生成完成"
|
||
|
||
# 4. 归档
|
||
log "4️⃣ 归档报告..."
|
||
ARCHIVE_DIR="reports/daily/$(date +%Y/%m)"
|
||
mkdir -p "$ARCHIVE_DIR"
|
||
cp "reports/daily/daily_report_${REPORT_DATE}.md" "$ARCHIVE_DIR/" 2>/dev/null || true
|
||
cp "reports/daily/html/daily_report_${REPORT_DATE}.html" "$ARCHIVE_DIR/" 2>/dev/null || true
|
||
log "✅ 归档完成"
|
||
|
||
# 5. 更新 daily_report 表
|
||
log "5️⃣ 更新日报记录..."
|
||
psql "$DB_URL" -c "
|
||
INSERT INTO daily_report (report_date, status, model_count, output_path, created_at, updated_at)
|
||
VALUES ('${REPORT_DATE}', 'generated', ${MODEL_COUNT}, 'reports/daily/daily_report_${REPORT_DATE}.md', NOW(), NOW())
|
||
ON CONFLICT (report_date) DO UPDATE SET
|
||
status = 'generated',
|
||
model_count = EXCLUDED.model_count,
|
||
output_path = EXCLUDED.output_path,
|
||
updated_at = NOW()
|
||
" >> "$LOG_FILE" 2>&1
|
||
log "✅ 日报记录更新完成"
|
||
|
||
log "🎉 每日流水线全部完成！"
|
||
log "📄 Markdown: reports/daily/daily_report_${REPORT_DATE}.md"
|
||
log "🌐 HTML: reports/daily/html/daily_report_${REPORT_DATE}.html"
|
||
|
||
exit 0
|