#!/usr/bin/env bash
# Confirm the lab infrastructure is intact. Run on the lab host.
#
# A 404 from the HTTPS entry point is the success signal: TLS terminated and the
# request reached Traefik, which simply had no matching ingress rule. A 502 or a
# refused connection means the chain is broken somewhere.
set -uo pipefail

export LIBVIRT_DEFAULT_URI="${LIBVIRT_DEFAULT_URI:-qemu:///system}"
HOSTS="${HOSTS:-auth.hyeonworks.com app1.hyeonworks.com app2.hyeonworks.com}"
NODE_IPS="${NODE_IPS:-192.168.122.11 192.168.122.12}"
fail=0

check() { # description, expected, actual
  if [ "$2" = "$3" ]; then printf '  ok    %-34s %s\n' "$1" "$3"
  else printf '  FAIL  %-34s got %s, want %s\n' "$1" "$3" "$2"; fail=1; fi
}

echo "== guests =="
for name in kc-lab-1 kc-lab-2; do
  check "$name" running "$(virsh domstate "$name" 2>/dev/null || echo absent)"
done

echo "== k3s =="
ready="$(kubectl get nodes --no-headers 2>/dev/null | grep -c ' Ready ')"
check "nodes Ready" 2 "$ready"
lb="$(kubectl -n kube-system get svc traefik \
      -o jsonpath='{.status.loadBalancer.ingress[*].ip}' 2>/dev/null | wc -w)"
check "traefik node IPs" 2 "$lb"

echo "== host nginx =="
check "service" active "$(systemctl is-active nginx)"
check "cert renew timer" active "$(systemctl is-active certbot-renew.timer)"
for ip in $NODE_IPS; do
  check "traefik $ip" 404 "$(curl -s -o /dev/null -w '%{http_code}' --max-time 5 "http://${ip}/")"
done

echo "== public entry point =="
for h in $HOSTS; do
  check "https://$h" 404 "$(curl -s -o /dev/null -w '%{http_code}' --max-time 8 "https://${h}/")"
  check "tls verify $h" 0 "$(curl -s -o /dev/null -w '%{ssl_verify_result}' --max-time 8 "https://${h}/")"
done
check "http redirect" 301 "$(curl -s -o /dev/null -w '%{http_code}' --max-time 8 "http://${HOSTS%% *}/")"

echo
[ "$fail" -eq 0 ] && echo "lab is healthy" || echo "lab has failures"
exit "$fail"