LibrePortal/scripts/restore/restore_first_run.sh

#!/bin/bash

restoreFirstRunDiscover()
{
    local idx="$1"

    if ! resticLocationEnabled "$idx"; then
        isError "Location $idx is not enabled"
        return 1
    fi

    resticEnvExport "$idx" || return 1
    # Via runBackupOp rather than its own sudo: this was the one backup-engine
    # call bypassing that funnel, so it silently missed the -E fix for sudo-rs
    # (and the -H that puts restic's cache under the backup user's HOME).
    runBackupOp restic snapshots --tag engine=libreportal --json --no-lock 2>/dev/null
    local rc=$?
    resticEnvUnset
    return $rc
}

# Restore a host's apps onto this machine.
#
# With no app list this is a WHOLE-HOST restore: the apps are discovered from
# the repository and filtered through the preflight. Both halves matter.
#
# Discovery, because an explicit list has to survive the CLI wrapper's fixed
# positional slots to get here — a 13-app restore arrived as four, restored
# those, and reported success. The wrapper now forwards the real argv, but a
# whole-host restore that never builds a list cannot be truncated at all.
#
# The preflight, because the installer prints its report in a separate process,
# so the decision it made there is gone by the time this runs. Without
# re-applying it, an app the user was told would be skipped — one this version
# no longer ships, or one too big for the disk — gets restored anyway.
restoreFirstRunBulk()
{
    local idx="$1"
    local source_host="$2"
    shift 2
    local apps_to_restore=("$@")
    local -i preflighted=0

    if [[ ${#apps_to_restore[@]} -eq 0 ]]; then
        restorePreflightReport "$idx" "$source_host" >/dev/null 2>&1
        apps_to_restore=("${RESTORE_PREFLIGHT_OK[@]}")
        preflighted=1
    fi

    if [[ ${#apps_to_restore[@]} -eq 0 ]]; then
        isError "No apps to restore for '$source_host' in this repository"
        return 1
    fi

    isHeader "First-run bulk restore from $(resticLocationName "$idx") (host=$source_host)"
    (( preflighted )) && isNotice "Restoring ${#apps_to_restore[@]} apps the preflight approved."

    # Count what actually landed. A per-app failure must not be reported as a
    # complete restore — that is how "4 apps restored" read as success when
    # nine had gone missing.
    #
    # An app can also come back only half-running: continue-on-error (the
    # default) lets a failed compose-up log and carry on, so restoreAppStart
    # still returns 0. That is how a restore reported thirteen successes while
    # stoat's livekit had lost a port race and four containers that depended on
    # it exited 101. checkSuccess appends every such failure to error_report.log,
    # so watch that file grow across each app and name the noisy ones.
    local _errlog="${logs_dir%/}/error_report.log"
    _restoreErrLines() { wc -l < "$_errlog" 2>/dev/null || echo 0; }

    local app
    local -i ok=0 bad=0 before=0 after=0
    local -a failed=() noisy=()
    for app in "${apps_to_restore[@]}"; do
        before=$(_restoreErrLines)
        if restoreAppStart "$app" "latest" "$idx" "$source_host"; then
            ok=$(( ok + 1 ))
            after=$(_restoreErrLines)
            (( after > before )) && noisy+=("$app")
        else
            bad=$(( bad + 1 )); failed+=("$app")
        fi
    done
    unset -f _restoreErrLines

    if (( bad > 0 )); then
        isError "First-run restore finished with failures — $ok of ${#apps_to_restore[@]} restored"
        isNotice "Failed: ${failed[*]}"
        (( ${#noisy[@]} )) && isNotice "Restored but reported errors: ${noisy[*]}"
        return 1
    fi

    if (( ${#noisy[@]} )); then
        isSuccessful "First-run restore complete — $ok apps restored"
        isNotice "${#noisy[@]} reported errors while starting: ${noisy[*]}"
        isNotice "They are restored, but check them: $_errlog"
        return 0
    fi

    isSuccessful "First-run restore complete — $ok apps restored"
    return 0
}

# The WebUI's rebuild: adopt the settings, reconcile the domains, restore the
# apps. Same order the installer uses and for the same reason — the system
# config carries every other backup location's credentials, so one password the
# user remembers unlocks the rest, and only then are apps worth restoring.
#
#   restoreWebuiRebuild <location-idx> <host> [drop-domains]
#
# Called from a task, so its output is the progress the user watches.
restoreWebuiRebuild()
{
    local idx="${1:-}" host="${2:-}" drop="${3:-no}"
    if [[ -z "$idx" ]]; then
        isError "restoreWebuiRebuild requires a backup location"
        return 1
    fi

    isHeader "Rebuilding from backup"

    # --- settings first ------------------------------------------------------
    isNotice "Restoring settings and credentials…"
    if backupRestoreSystemConfig "$idx" >/dev/null 2>&1; then
        # --force: the WebUI is only reachable at all because this machine has
        # a working install on it, so restoreAdoptIsFirstRun will say no. The
        # user asked for this explicitly on the Rebuild step, which is the
        # confirmation the guard exists to require.
        if restoreSystemAdopt "" --force; then
            isSuccessful "Settings and backup repositories restored"
        else
            isNotice "Settings were staged but could not be adopted — apps will still be restored."
        fi
    else
        isNotice "No system config in this backup — apps will still be restored."
    fi

    # --- domains -------------------------------------------------------------
    restoreDomainReport || true
    if [[ "$drop" == "yes" || "$drop" == "true" ]]; then
        restoreDomainsDropElsewhere || true
    fi

    # --- apps ----------------------------------------------------------------
    # No app list, deliberately: bulk discovers the host's apps and re-applies
    # the preflight itself. Passing a list here is what let a 13-app restore
    # arrive as four and still report success.
    isNotice "Restoring apps — this takes a while."
    restoreFirstRunBulk "$idx" "$host"

    isSuccessful "Rebuild complete"
    return 0
}