#!/usr/bin/env bash
# Main pipeline orchestrator.
#
# Execution order:
#   1. Create cold archives for the selected Docker Compose projects.
#   2. Run each enabled transfer stage listed in BACKUP_METHODS.
#   3. Prune old local archives only after every earlier stage succeeds.
#
# An EXIT trap publishes the final MQTT result even when a stage fails. The
# original exit code is preserved so cron, systemd and shell callers can detect
# failure normally.
set -Eeuo pipefail
SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd -P)"
. "$SCRIPT_DIR/lib/common.sh"
DRY_RUN=0; SKIP_CONTAINERS=0; SKIP_PRUNE=0; CONTAINERS_OVERRIDE=""
while [[ $# -gt 0 ]]; do
  case "$1" in
    --dry-run|-t) DRY_RUN=1 ;; --skip-containers) SKIP_CONTAINERS=1 ;; --skip-prune) SKIP_PRUNE=1 ;;
    --containers|-f) CONTAINERS_OVERRIDE="${2:?Missing containers file}"; shift ;;
    -h|--help)
      echo "Usage: ${0##*/} [--dry-run] [--containers FILE] [--skip-containers] [--skip-prune]"
      echo "Transfer stages run in BACKUP_METHODS order. Add stages/NN-name.sh and list name in BACKUP_METHODS."
      exit 0 ;;
    *) die "Unknown option: $1" 2 ;;
  esac
  shift
done

if (( SKIP_CONTAINERS )); then
  BACKUP_LOCAL_ARCHIVE_STATUS="skipped"
else
  BACKUP_LOCAL_ARCHIVE_STATUS="running"
fi
BACKUP_RCLONE_STATUS="not_configured"
BACKUP_SMB_STATUS="not_configured"
for configured_method in $BACKUP_METHODS; do
  case "$configured_method" in
    rclone) if is_true "$RCLONE_ENABLED"; then BACKUP_RCLONE_STATUS="pending"; else BACKUP_RCLONE_STATUS="skipped"; fi ;;
    smb) if is_true "$SMB_ENABLED"; then BACKUP_SMB_STATUS="pending"; else BACKUP_SMB_STATUS="skipped"; fi ;;
  esac
done
BACKUP_REMOTE_COPY_STATUS="pending"
if [[ "$BACKUP_RCLONE_STATUS" == "not_configured" || "$BACKUP_RCLONE_STATUS" == "skipped" ]] && [[ "$BACKUP_SMB_STATUS" == "not_configured" || "$BACKUP_SMB_STATUS" == "skipped" ]]; then
  BACKUP_REMOTE_COPY_STATUS="skipped"
fi
BACKUP_REMOTE_COPY_FINISHED_AT=""
export BACKUP_LOCAL_ARCHIVE_STATUS BACKUP_REMOTE_COPY_STATUS BACKUP_RCLONE_STATUS BACKUP_SMB_STATUS BACKUP_REMOTE_COPY_FINISHED_AT

BACKUP_RUN_ID="$(run_id)"
BACKUP_STARTED_EPOCH="$(date +%s)"
# Every script sourced through this process appends structured log lines here.
# The MQTT reporting stage parses this temporary log to build its summary.
BACKUP_RUN_LOG="$(mktemp "${TMPDIR:-/tmp}/zorruno-docker-backup.XXXXXX.log")"
export BACKUP_RUN_ID BACKUP_STARTED_EPOCH BACKUP_RUN_LOG

finish_run() {
  local exit_code=$? finished status archived_count remote_success=0 remote_failure=0 remote_running=0 remote_dry_run=0 transfer_status
  # Prevent recursion when this function exits with the pipeline's status.
  trap - EXIT
  # Reporting is best-effort and must never replace the real pipeline result.
  set +e
  finished="$(date +%s)"
  if [[ "$BACKUP_LOCAL_ARCHIVE_STATUS" == "running" ]]; then
    if (( DRY_RUN )); then
      BACKUP_LOCAL_ARCHIVE_STATUS="dry_run"
    elif (( exit_code == 0 )); then
      BACKUP_LOCAL_ARCHIVE_STATUS="success"
    else
      archived_count="$(grep -c "\[ARCHIVE\] Created " "$BACKUP_RUN_LOG" || true)"
      if (( archived_count > 0 )); then BACKUP_LOCAL_ARCHIVE_STATUS="partial"; else BACKUP_LOCAL_ARCHIVE_STATUS="failed"; fi
    fi
  fi
  for transfer_status in BACKUP_RCLONE_STATUS BACKUP_SMB_STATUS; do
    if [[ "${!transfer_status}" == "running" ]]; then
      if (( DRY_RUN )); then printf -v "$transfer_status" "%s" "dry_run"; else printf -v "$transfer_status" "%s" "failed"; fi
    elif [[ "${!transfer_status}" == "pending" ]]; then
      printf -v "$transfer_status" "%s" "not_attempted"
    fi
  done
  for transfer_status in "$BACKUP_RCLONE_STATUS" "$BACKUP_SMB_STATUS"; do
    case "$transfer_status" in
      success) (( remote_success++ )) ;;
      partial) (( remote_success++ )); (( remote_failure++ )) ;;
      failed) (( remote_failure++ )) ;;
      running|pending) (( remote_running++ )) ;;
      dry_run) (( remote_dry_run++ )) ;;
    esac
  done
  if (( remote_running > 0 )); then
    BACKUP_REMOTE_COPY_STATUS="running"
  elif (( remote_failure > 0 && remote_success > 0 )); then
    BACKUP_REMOTE_COPY_STATUS="partial"
  elif (( remote_failure > 0 )); then
    BACKUP_REMOTE_COPY_STATUS="failed"
  elif (( remote_success > 0 )); then
    BACKUP_REMOTE_COPY_STATUS="success"
  elif (( remote_dry_run > 0 )); then
    BACKUP_REMOTE_COPY_STATUS="dry_run"
  else
    BACKUP_REMOTE_COPY_STATUS="skipped"
  fi
  if (( exit_code == 0 )); then
    if (( DRY_RUN )); then status="dry_run_success"; else status="success"; fi
  else
    if (( DRY_RUN )); then status="dry_run_failed"; else status="failed"; fi
  fi
  if is_true "$MQTT_REPORT_ENABLED"; then
    "$SCRIPT_DIR/stages/99-mqtt-report.sh" "$status" "$exit_code" \
      "$BACKUP_STARTED_EPOCH" "$finished" "$BACKUP_RUN_ID" "$BACKUP_RUN_LOG" \
      || log ERROR "Unable to publish final MQTT result"
  fi
  rm -f -- "$BACKUP_RUN_LOG"
  exit "$exit_code"
}
trap finish_run EXIT

require_command flock
mkdir -p "$(dirname "$LOCK_FILE")"
# Keep descriptor 9 open for the whole run. Closing it automatically releases
# the advisory lock, including on errors and signals that terminate the shell.
exec 9>"$LOCK_FILE"
flock -n 9 || die "Another backup run holds lock: $LOCK_FILE"
stage_args=()
(( DRY_RUN )) && stage_args+=(--dry-run)
[[ -n "$CONTAINERS_OVERRIDE" ]] && stage_args+=(--containers "$CONTAINERS_OVERRIDE")
log START "Backup pipeline for $BACKUP_HOSTNAME"
if is_true "$MQTT_REPORT_ENABLED"; then
  # The retained running state lets Home Assistant show that work is active.
  "$SCRIPT_DIR/stages/99-mqtt-report.sh" running 0 "$BACKUP_STARTED_EPOCH" \
    "$BACKUP_STARTED_EPOCH" "$BACKUP_RUN_ID" "$BACKUP_RUN_LOG" \
    || log WARN "Unable to publish MQTT running state; backup will continue"
fi
if (( SKIP_CONTAINERS )); then
  BACKUP_LOCAL_ARCHIVE_STATUS="skipped"
else
  "$SCRIPT_DIR/stages/10-containers.sh" "${stage_args[@]}"
  if (( DRY_RUN )); then BACKUP_LOCAL_ARCHIVE_STATUS="dry_run"; else BACKUP_LOCAL_ARCHIVE_STATUS="success"; fi
fi
method_args=(); (( DRY_RUN )) && method_args+=(--dry-run)
# BACKUP_METHODS contains short names (for example: "rclone smb"). Numeric
# prefixes control directory ordering without becoming part of configuration.
for method in $BACKUP_METHODS; do
  method_script=""
  while IFS= read -r candidate; do method_script="$candidate"; break; done < <(find "$SCRIPT_DIR/stages" -maxdepth 1 -type f -name "*-${method}.sh" -print | sort)
  [[ -n "$method_script" ]] || die "Configured backup method not found: $method"
  case "$method" in
    rclone) if is_true "$RCLONE_ENABLED"; then BACKUP_RCLONE_STATUS="running"; fi ;;
    smb) if is_true "$SMB_ENABLED"; then BACKUP_SMB_STATUS="running"; fi ;;
  esac
  "$method_script" "${method_args[@]}"
  if (( DRY_RUN )); then
    case "$method" in
      rclone) [[ "$BACKUP_RCLONE_STATUS" == "running" ]] && BACKUP_RCLONE_STATUS="dry_run" ;;
      smb) [[ "$BACKUP_SMB_STATUS" == "running" ]] && BACKUP_SMB_STATUS="dry_run" ;;
    esac
  else
    case "$method" in
      rclone) if [[ "$BACKUP_RCLONE_STATUS" == "running" ]]; then BACKUP_RCLONE_STATUS="success"; BACKUP_REMOTE_COPY_FINISHED_AT="$(date -u +%FT%TZ)"; fi ;;
      smb) if [[ "$BACKUP_SMB_STATUS" == "running" ]]; then BACKUP_SMB_STATUS="success"; BACKUP_REMOTE_COPY_FINISHED_AT="$(date -u +%FT%TZ)"; fi ;;
    esac
  fi
done
(( SKIP_PRUNE )) || "$SCRIPT_DIR/stages/90-prune.sh" "${method_args[@]}"
log DONE "Backup pipeline completed successfully"