#!/bin/bash
# 验证双实例 watchdog 的判定逻辑（不真重启，靠 DRY_RUN + 桩函数）
#
# 为什么要专门测：双实例引入的分支不少（哪个死了/哪个低连接/公网通不通），
# 直接覆盖生产脚本风险太大。
set -u

SRC=/tmp/wd_v4.sh
OUT=/tmp/wd_test_out

# 先语法检查
echo "════════ 0. 语法检查 ════════"
if bash -n "$SRC" 2>&1; then
    echo "  ✓ 语法 OK"
else
    echo "  ✗ 语法有错"
    exit 1
fi

# 造一个测试环境：把所有外部依赖替换成桩
setup_env() {
    rm -rf /tmp/wdtest
    mkdir -p /tmp/wdtest/relay
    sed -e 's#^RELAY_DIR=.*#RELAY_DIR=/tmp/wdtest/relay#' \
        -e 's#^URL_FILE=.*#URL_FILE=/tmp/wdtest/relay/public_url.txt#' \
        -e 's#^STATE_FILE=.*#STATE_FILE=/tmp/wdtest/relay/watchdog.state#' \
        -e 's#^LAST_RESTART_FILE=.*#LAST_RESTART_FILE=/tmp/wdtest/relay/watchdog.last_restart#' \
        -e 's#^TUNNEL_LOGS=.*#TUNNEL_LOGS=("/tmp/wdtest/relay/tunnel.log" "/tmp/wdtest/relay/tunnel-h2.log")#' \
        "$SRC" > /tmp/wdtest/wd.sh
    echo "https://relay.example" > /tmp/wdtest/relay/public_url.txt
    touch /tmp/wdtest/relay/tunnel.log /tmp/wdtest/relay/tunnel-h2.log
    # logger 桩：别真写 syslog
    mkdir -p /tmp/wdtest/bin
    cat > /tmp/wdtest/bin/logger <<'EOF'
#!/bin/bash
exit 0
EOF
    cat > /tmp/wdtest/bin/curl <<'EOF'
#!/bin/bash
# 桩：METRICS_CURL 决定 metrics 返回什么，HEALTH_CODE 决定公网状态
for a in "$@"; do
    case "$a" in
        */metrics)
            printf '# TYPE cloudflared_tunnel_ha_connections gauge\ncloudflared_tunnel_ha_connections %s\n' "${STUB_CONNS_20241:-0}"
            exit 0 ;;
        *:20242/metrics)
            printf 'cloudflared_tunnel_ha_connections %s\n' "${STUB_CONNS_20242:-0}"
            exit 0 ;;
    esac
done
# 公网健康检查
if [ "${STUB_HEALTH:-200}" = "000" ]; then exit 7; fi
echo "${STUB_HEALTH:-200}"
EOF
    cat > /tmp/wdtest/bin/systemctl <<'EOF'
#!/bin/bash
if [ "$1" = "is-active" ]; then
    svc="${@: -1}"
    # STUB_DEAD_SVC 指定的服务返回非 active
    if [ "$svc" = "${STUB_DEAD_SVC:-}" ]; then exit 3; fi
    exit 0
fi
if [ "$1" = "restart" ]; then
    echo "RESTART:$2"
    exit 0
fi
exit 0
EOF
    chmod +x /tmp/wdtest/bin/*
    # 重置状态
    rm -f /tmp/wdtest/relay/watchdog.state /tmp/wdtest/relay/watchdog.last_restart
}

# 跑一个场景
#   $1 = 场景名
#   $2 = CONNS 20241（"X" 表示端口不通）
#   $3 = CONNS 20242
#   $4 = 公网码
#   $5 = 哪个服务 is-active 返回 false（可空）
run_case() {
    local name="$1" c1="$2" c2="$3" health="$4" dead="${5:-}"
    setup_env

    # "X" 表示端口不通 -> 桩 curl 直接失败
    local stub1="$c1" stub2="$c2"
    if [ "$c1" = "X" ]; then stub1=""; fi
    if [ "$c2" = "X" ]; then stub2=""; fi

    # 用一个特制 curl：端口不通时不输出
    cat > /tmp/wdtest/bin/curl <<EOF
#!/bin/bash
for a in "\$@"; do
    case "\$a" in
        *:20241/metrics) [ -n "$stub1" ] && echo "cloudflared_tunnel_ha_connections $stub1"; exit 0 ;;
        *:20242/metrics) [ -n "$stub2" ] && echo "cloudflared_tunnel_ha_connections $stub2"; exit 0 ;;
    esac
done
[ "$health" = "000" ] && exit 7
echo "$health"
EOF
    chmod +x /tmp/wdtest/bin/curl

    echo "  ── $name ──"
    echo "     输入: 主=$c1 副=$c2 公网=$health 停的服务=${dead:-无}"
    PATH=/tmp/wdtest/bin:$PATH \
    DRY_RUN=1 \
    STUB_DEAD_SVC="$dead" \
        bash /tmp/wdtest/wd.sh > /tmp/wdtest/out.txt 2>&1
    # 只看这次运行产生的判断行
    grep -E '已建齐|公网|重启|先不重启|DRY_RUN|继续等' /tmp/wdtest/out.txt | tail -4 | sed 's/^/       /'
    echo
}

echo "════════ 1. 双实例都健康 + 公网通 -> 不该有任何动作 ════════"
run_case "都健康" 5 5 200

echo "════════ 2. 主实例没连接，副实例正常 + 公网通 ════════"
echo "    （期望：只重启主实例，因为副实例还在扛）"
run_case "主实例 0 条" 0 5 200

echo "════════ 3. 主实例 metrics 端口不通（进程卡死）════════"
echo "    （期望：重启主实例）"
run_case "主实例无响应" X 5 200

echo "════════ 4. 两个实例都 0 条 + 公网不通 ════════"
echo "    （期望：重启两个）"
run_case "双实例全垮" 0 0 000

echo "════════ 5. 连接数正常但公网 502（连续第 1 次）════════"
echo "    （期望：只记一次，不重启）"
run_case "公网 502 首次" 5 5 502

echo "════════ 6. 只有一个实例低连接 + 公网不通 ════════"
echo "    （期望：重启那个低连接的实例，不动另一个）"
run_case "副实例低连接" 5 1 000