#!/usr/bin/env bash
# Ad hoc clone of a single VM/CT from pve1 (production) to pve-test
# (sandbox), via vzdump + qmrestore/pct restore -- not a general-purpose
# backup tool, just a quick "give me a disposable copy of this thing on
# pve-test" for testing against real-ish data without touching prod.
#
# Flow:
#   1. vzdump the resource on pve1 into its "local" storage (--mode
#      snapshot by default, so the source keeps running throughout --
#      see --mode below for when that's not possible).
#   2. Stream the resulting archive straight from pve1 to pve-test
#      (ssh pve1 cat ... | ssh pve-test cat > ...) -- this machine is
#      just the relay, no separate on-disk staging copy here.
#   3. qmrestore / pct restore it on pve-test under --new-vmid (default:
#      same VMID as the source -- pve-test is a separate node/cluster, so
#      no collision unless that VMID is already in use there too).
#      Always restored with --unique 1 (fresh MAC addresses) since the
#      source is typically still running on the same LAN -- restoring
#      with the *same* MAC would put two live guests on the wire with
#      identical hardware addresses.
#   4. Delete the vzdump archive from pve1's local storage and the
#      relayed copy on pve-test, so neither node accumulates ad hoc
#      backup files from this script. Only the pve1 original is
#      preserved on any failure after step 1, so a failed
#      transfer/restore can be retried without re-running the backup.
#
# This script's own defaults are pve1 -> pve-test, unlike
# create-proxmox-resource.sh's --node (which defaults to production) --
# see CLAUDE.md's "Two Proxmox nodes" section. pve1 is only ever touched
# here after typing the source VMID back to confirm; pve-test is treated
# as disposable, matching this repo's usual policy for that node.
#
# See --help for the full option list.
set -euo pipefail

repo_root="$(cd "$(dirname "$0")/../.." && pwd)"
# shellcheck source=../env.sh
source "${repo_root}/scripts/env.sh"
# shellcheck source=../lib/confirm.sh
source "${repo_root}/scripts/lib/confirm.sh"

usage() {
  cat <<EOF
Usage: $0 --vmid <n> [options]

  --vmid <n>              Required: VMID on the source node to clone.
                           Kind (qemu VM vs LXC CT) is auto-detected.
  --new-vmid <n>           VMID to restore as on the target node
                           (default: same as --vmid).
  --mode snapshot|suspend|stop
                           vzdump backup mode (default: snapshot -- the
                           source resource keeps running throughout;
                           requires snapshot-capable storage, e.g.
                           ZFS/LVM-thin/Ceph/qcow2). Fall back to
                           "suspend" (brief pause) or "stop" (source
                           goes down for the duration) if the source's
                           storage doesn't support live snapshots --
                           vzdump's own error will say so.
  --source-node <host>      (default: \$PVE1_HOST, ${PVE1_HOST})
  --target-node <host>       (default: \$PVE_TEST_HOST, ${PVE_TEST_HOST})
  --source-storage <pool>      Where vzdump writes the backup on the
                               source node (default: local).
  --target-storage <pool>       Where the restored disk/rootfs lands on
                               the target node (default: \$PROXMOX_STORAGE, ${PROXMOX_STORAGE}).
  --keep-backup                  Don't delete the vzdump archive from
                                 either node afterward (debugging aid).
  --yes                            Skip the typed VMID confirmation
                                   before touching the source node.
  --dry-run                          Print the full plan and skip every
                                     mutating step (vzdump, transfer,
                                     restore, delete) and the confirm
                                     prompt. Still makes read-only SSH
                                     calls to look up the source kind
                                     and check the target VMID is free
                                     -- harmless on either node.
  -h, --help
EOF
}

vmid=""
new_vmid=""
mode="snapshot"
source_node="$PVE1_HOST"
target_node="$PVE_TEST_HOST"
source_storage="local"
target_storage="$PROXMOX_STORAGE"
keep_backup=0
skip_confirm=0
dry_run=0

while [[ $# -gt 0 ]]; do
  case "$1" in
  --vmid) vmid="$2"; shift 2 ;;
  --new-vmid) new_vmid="$2"; shift 2 ;;
  --mode) mode="$2"; shift 2 ;;
  --source-node) source_node="$2"; shift 2 ;;
  --target-node) target_node="$2"; shift 2 ;;
  --source-storage) source_storage="$2"; shift 2 ;;
  --target-storage) target_storage="$2"; shift 2 ;;
  --keep-backup) keep_backup=1; shift ;;
  --yes) skip_confirm=1; shift ;;
  --dry-run) dry_run=1; shift ;;
  -h | --help) usage; exit 0 ;;
  *) echo "Unknown option: $1" >&2; usage >&2; exit 1 ;;
  esac
done

if [[ -z "$vmid" ]]; then
  echo "ERROR: --vmid is required." >&2
  usage >&2
  exit 1
fi
if [[ "$mode" != "snapshot" && "$mode" != "suspend" && "$mode" != "stop" ]]; then
  echo "ERROR: --mode must be snapshot, suspend, or stop." >&2
  exit 1
fi
[[ -z "$new_vmid" ]] && new_vmid="$vmid"

source_target="${PROXMOX_SSH_USER}@${source_node}"
target_target="${PROXMOX_SSH_USER}@${target_node}"

# No dry-run wrapper needed for the calls below: every mutating step
# (vzdump, transfer, restore, delete) is reached only after the --dry-run
# early-exit further down, so a plain `ssh` call is never in the dry-run
# path.

# --- identify the resource kind on the source node -----------------------
echo "==> Looking up VMID ${vmid} on ${source_node}..."
kind=""
if ssh "$source_target" "qm status ${vmid}" >/dev/null 2>&1; then
  kind="vm"
elif ssh "$source_target" "pct status ${vmid}" >/dev/null 2>&1; then
  kind="lxc"
else
  echo "ERROR: VMID ${vmid} doesn't exist on ${source_node} as either a VM or CT." >&2
  exit 1
fi
echo "VMID ${vmid} on ${source_node} is a ${kind}."

# --- refuse to clobber an existing resource on the target node -----------
if ssh "$target_target" "qm status ${new_vmid}" >/dev/null 2>&1 \
  || ssh "$target_target" "pct status ${new_vmid}" >/dev/null 2>&1; then
  echo "ERROR: VMID ${new_vmid} already exists on ${target_node}. Pass --new-vmid" >&2
  echo "with a free ID, or remove the existing resource there first." >&2
  exit 1
fi

echo
echo "Plan:"
echo "  source: ${kind} VMID ${vmid} on ${source_node} (storage: ${source_storage}, mode: ${mode})"
echo "  target: VMID ${new_vmid} on ${target_node} (storage: ${target_storage}, fresh MAC via --unique)"
[[ "$keep_backup" -eq 1 ]] && echo "  backup archives are kept on both nodes afterward (--keep-backup)"

if [[ "$dry_run" -eq 1 ]]; then
  echo
  echo "[dry-run] No backup, transfer, restore, or delete was performed."
  exit 0
fi

if [[ "$skip_confirm" -ne 1 ]]; then
  echo
  if ! confirm_typed "$vmid" "Type the source VMID (${vmid}) to confirm backing it up from ${source_node}: "; then
    echo "Cancelled -- input didn't match ${vmid}." >&2
    exit 1
  fi
fi

# --- vzdump on the source node --------------------------------------------
echo
echo "==> Backing up VMID ${vmid} on ${source_node} (mode=${mode}, storage=${source_storage})..."
vzdump_log="$(ssh "$source_target" \
  "vzdump ${vmid} --mode ${mode} --storage ${source_storage} --compress zstd" 2>&1)" \
  || {
    echo "$vzdump_log" >&2
    echo "ERROR: vzdump failed on ${source_node}." >&2
    exit 1
  }
echo "$vzdump_log"

archive="$(echo "$vzdump_log" | grep -oP "creating vzdump archive '\K[^']+" | tail -n1)"
if [[ -z "$archive" ]]; then
  echo "ERROR: couldn't find the archive path in vzdump's output above." >&2
  exit 1
fi
archive_basename="$(basename "$archive")"
target_tmp_archive="/var/tmp/${archive_basename}"
echo "Archive: ${archive}"

# Always clean up the relayed copy on the target node, success or failure
# -- it's only ever a working copy, restored or not.
cleanup_target_tmp() {
  if [[ "$keep_backup" -ne 1 ]]; then
    ssh "$target_target" "rm -f '${target_tmp_archive}'" >/dev/null 2>&1 || true
  fi
}
trap cleanup_target_tmp EXIT

# --- relay the archive from source to target ------------------------------
echo
echo "==> Transferring archive to ${target_node}..."
ssh "$source_target" "cat '${archive}'" | ssh "$target_target" "cat > '${target_tmp_archive}'"

# --- restore on the target node --------------------------------------------
echo
echo "==> Restoring as VMID ${new_vmid} on ${target_node} (storage=${target_storage})..."
if [[ "$kind" == "vm" ]]; then
  ssh "$target_target" "qmrestore '${target_tmp_archive}' ${new_vmid} --storage ${target_storage} --unique 1"
else
  ssh "$target_target" "pct restore ${new_vmid} '${target_tmp_archive}' --storage ${target_storage} --unique 1"
fi

# --- clean up the source backup now that the restore succeeded -----------
if [[ "$keep_backup" -ne 1 ]]; then
  echo
  echo "==> Deleting backup archive from ${source_node}'s ${source_storage} storage..."
  ssh "$source_target" "rm -f '${archive}' '${archive}.notes' '${archive}.log'" >/dev/null 2>&1 || true
fi

echo
echo "Done. VMID ${new_vmid} (${kind}) is now on ${target_node}, cloned from" \
  "VMID ${vmid} on ${source_node}."