PacketStation/scripts/backup/ps-restore.sh

#!/usr/bin/env bash
# Packet Station restore on a native VM. Run by root. Restores a ps-backup dump into a fresh
# database, optionally applies the globals file, copies stored files back into an assets folder,
# checks them against the database, and prints the row count of every table at the end.
#
# It never stops, starts or reconfigures a service. Putting the restored database into service
# (renaming it into place) is a separate, deliberate step: see docs/DEPLOY.md, "Restore on a VM".
#
# Usage:
#   ps-restore [--dump FILE --db NAME [--replace]]
#              [--globals FILE]
#              [--assets DIR_OR_TAR --assets-dir DIR]
#              [--verify-assets --db NAME --assets-dir DIR]
#              [--counts-only --db NAME]
#
#   --dump FILE              a ps-*.dump file (pg_dump -Fc).
#   --db NAME                the database to restore into. It must not exist, unless --replace,
#                            which drops it first. DROP DATABASE refuses while anyone is connected.
#                            --replace is refused for packetstation, the live database.
#   --owner ROLE             owner of the new database (default ps_migrate, as install.sh makes it).
#   --app-role ROLE          role given CONNECT and TEMPORARY on it (default ps_app).
#   --locale NAME            the new database's locale (default en_US.UTF-8, as install.sh makes it).
#   --globals FILE           a ps-*.globals.sql file. Roles that already exist are reported and
#                            left alone. The file holds no passwords: install.sh sets them again.
#   --assets SRC             a folder, or a .tar / .tar.gz / .tgz, holding the files that belong
#                            under ASSETS_DIR. Existing files are never overwritten.
#   --assets-dir DIR         the folder to copy into or check (/var/lib/packetstation/assets is the
#                            live one; a scratch folder for a rehearsal).
#   --assets-owner U:G       owner for the copied files (default packetstation:packetstation).
#   --verify-assets          compare sha256 of every file in --assets-dir with assets.sha256 in --db.
#   --counts-only            only print the row counts of --db.
#
# psql and pg_restore run as the postgres OS user on the local socket (peer authentication). The
# files are opened by root and handed over on stdin. No password is read, passed or printed.

set -euo pipefail
umask 077

PG_BINDIR="${PG_BINDIR-/usr/lib/postgresql/16/bin}"
read -r -a PG_AS <<< "${PG_AS:-setpriv --reuid=postgres --regid=postgres --init-groups --reset-env --}"
LIVE_DB=packetstation

log() { printf '%s ps-restore: %s\n' "$(date -u +%Y-%m-%dT%H:%M:%SZ)" "$*" >&2; }
die() { log "$*"; exit 1; }
usage() { sed -n '2,33p' "$0" | sed 's/^# \{0,1\}//' >&2; exit 2; }

dump=""
db=""
replace=0
owner="ps_migrate"
app_role="ps_app"
locale_name="en_US.UTF-8"
globals=""
assets=""
assets_dir=""
assets_owner="packetstation:packetstation"
verify_assets=0
counts_only=0

while [[ $# -gt 0 ]]; do
  case "$1" in
    --dump) dump="${2:?}"; shift 2 ;;
    --db) db="${2:?}"; shift 2 ;;
    --replace) replace=1; shift ;;
    --owner) owner="${2:?}"; shift 2 ;;
    --app-role) app_role="${2:?}"; shift 2 ;;
    --locale) locale_name="${2:?}"; shift 2 ;;
    --globals) globals="${2:?}"; shift 2 ;;
    --assets) assets="${2:?}"; shift 2 ;;
    --assets-dir) assets_dir="${2:?}"; shift 2 ;;
    --assets-owner) assets_owner="${2:?}"; shift 2 ;;
    --verify-assets) verify_assets=1; shift ;;
    --counts-only) counts_only=1; shift ;;
    -h|--help) usage ;;
    *) log "unknown argument $1"; usage ;;
  esac
done

ident_re='^[a-z_][a-z0-9_]{0,62}$'
[[ -z "$db" || "$db" =~ $ident_re ]] || die "--db must be a plain lower-case name (letters, digits, _)"
[[ "$owner" =~ $ident_re ]] || die "--owner must be a plain lower-case role name"
[[ "$app_role" =~ $ident_re ]] || die "--app-role must be a plain lower-case role name"
[[ "$locale_name" =~ ^[A-Za-z0-9_.@-]+$ ]] || die "--locale must be a locale name like en_US.UTF-8"
[[ "$assets_owner" =~ ^[a-z_0-9][a-z0-9_-]*:[a-z_0-9][a-z0-9_-]*$ ]] || die "--assets-owner must be USER:GROUP"

if [[ -n "$dump" || $counts_only -eq 1 || $verify_assets -eq 1 ]]; then
  [[ -n "$db" ]] || die "--db is required"
fi
if [[ -n "$assets" || $verify_assets -eq 1 ]]; then
  [[ -n "$assets_dir" ]] || die "--assets-dir is required"
  [[ -d "$assets_dir" ]] || die "$assets_dir is not a folder"
fi
if [[ -z "$dump" && -z "$globals" && -z "$assets" && $verify_assets -eq 0 && $counts_only -eq 0 ]]; then
  die "nothing to do: give --dump, --globals, --assets, --verify-assets or --counts-only"
fi
if [[ -n "$dump" && $replace -eq 1 && "$db" == "$LIVE_DB" ]]; then
  die "--replace is refused for $LIVE_DB. Restore into another name and rename it into place (docs/DEPLOY.md)."
fi

pgbin() {
  if [[ -n "$PG_BINDIR" ]]; then printf '%s/%s\n' "$PG_BINDIR" "$1"; else printf '%s\n' "$1"; fi
}

# psql as postgres, reading SQL from stdin. Variables go through -v and :'name'.
psql_c() {
  local dbname="$1"; shift
  "${PG_AS[@]}" "$(pgbin psql)" -X -q -v ON_ERROR_STOP=1 -d "$dbname" "$@"
}

db_exists() {
  local n
  n="$(psql_c postgres -At -v name="$1" <<'SQL'
SELECT count(*) FROM pg_database WHERE datname = :'name';
SQL
)"
  [[ "$n" == "1" ]]
}

role_exists() {
  local n
  n="$(psql_c postgres -At -v name="$1" <<'SQL'
SELECT count(*) FROM pg_roles WHERE rolname = :'name';
SQL
)"
  [[ "$n" == "1" ]]
}

print_counts() {
  local dbname="$1"
  log "row counts in $dbname"
  psql_c "$dbname" -A -F $'\t' -P footer=off <<'SQL'
SELECT c.relname AS table_name,
       (xpath('/row/n/text()',
              query_to_xml(format('SELECT count(*) AS n FROM %I.%I', n.nspname, c.relname), false, true, '')
       ))[1]::text::bigint AS row_count
FROM pg_class c
JOIN pg_namespace n ON n.oid = c.relnamespace
WHERE n.nspname = 'public' AND c.relkind IN ('r', 'p')
ORDER BY c.relname;
SQL
}

# ------------------------------------------------------------------ globals

if [[ -n "$globals" ]]; then
  [[ -r "$globals" ]] || die "cannot read $globals"
  if grep -qiE "PASSWORD[[:space:]]+'(SCRAM|md5)" "$globals"; then
    die "$globals holds password hashes; ps-backup writes globals without them. Refusing."
  fi
  log "applying globals from $(basename -- "$globals") (existing roles are left as they are)"
  # Without ON_ERROR_STOP: CREATE ROLE for a role that exists fails and the rest goes on.
  out="$("${PG_AS[@]}" "$(pgbin psql)" -X -q -d postgres < "$globals" 2>&1 || true)"
  exists="$(printf '%s\n' "$out" | grep -c 'already exists' || true)"
  other="$(printf '%s\n' "$out" | grep 'ERROR' | grep -vc 'already exists' || true)"
  log "globals: $exists statements skipped (already exists), $other other errors"
  if [[ "$other" -gt 0 ]]; then
    printf '%s\n' "$out" | grep 'ERROR' | grep -v 'already exists' >&2
    die "globals had errors"
  fi
fi

# ------------------------------------------------------------------ database

if [[ -n "$dump" ]]; then
  [[ -r "$dump" ]] || die "cannot read $dump"
  started=$SECONDS
  if db_exists "$db"; then
    [[ $replace -eq 1 ]] || die "database $db exists. Give --replace to drop it first."
    log "dropping database $db (--replace)"
    psql_c postgres -v name="$db" <<'SQL'
SELECT format('DROP DATABASE %I', :'name') \gexec
SQL
  fi
  role_exists "$owner" || die "role $owner does not exist (apply --globals, or run deploy/vm/install.sh)"

  log "creating database $db owned by $owner"
  # The same shape as deploy/vm/install.sh makes the live one.
  psql_c postgres -v name="$db" -v owner="$owner" -v loc="$locale_name" <<'SQL'
SELECT format('CREATE DATABASE %I OWNER %I ENCODING %L LOCALE %L TEMPLATE template0',
              :'name', :'owner', 'UTF8', :'loc') \gexec
SELECT format('REVOKE ALL ON DATABASE %I FROM PUBLIC', :'name') \gexec
SQL
  if role_exists "$app_role"; then
    psql_c postgres -v name="$db" -v app="$app_role" <<'SQL'
SELECT format('GRANT CONNECT, TEMPORARY ON DATABASE %I TO %I', :'name', :'app') \gexec
SQL
  else
    log "role $app_role does not exist; no CONNECT grant made"
  fi

  log "restoring $(basename -- "$dump") ($(stat -c %s "$dump") bytes) into $db"
  # One transaction: a restore that fails leaves an empty database, never a half-restored one.
  "${PG_AS[@]}" "$(pgbin pg_restore)" -d "$db" --exit-on-error --single-transaction < "$dump" \
    || die "pg_restore failed; database $db is left empty. Drop it with --replace on the next try."
  log "database restored in $(( SECONDS - started )) s"
fi

# ------------------------------------------------------------------ assets

if [[ -n "$assets" ]]; then
  [[ -e "$assets" ]] || die "$assets does not exist"
  started=$SECONDS
  if [[ -d "$assets" ]]; then
    log "copying assets from folder $assets into $assets_dir"
    cp -a -n -- "$assets/." "$assets_dir/"
  else
    case "$assets" in
      *.tar.gz|*.tgz) tar_flags="-xzf" ;;
      *.tar) tar_flags="-xf" ;;
      *) die "--assets must be a folder, .tar, .tar.gz or .tgz" ;;
    esac
    log "copying assets from $(basename -- "$assets") into $assets_dir"
    tar "$tar_flags" "$assets" -C "$assets_dir" --skip-old-files --no-same-owner
  fi
  if [[ "$(id -u)" == "0" ]]; then
    chown -R -- "$assets_owner" "$assets_dir"
  fi
  log "assets copied in $(( SECONDS - started )) s"
fi

# ------------------------------------------------------------------ verify assets

if [[ $verify_assets -eq 1 ]]; then
  work="$(mktemp -d)"
  trap 'rm -rf -- "$work"' EXIT
  # sha256sum check format: "<hex>  <path>".
  psql_c "$db" -At <<'SQL' > "$work/assets.sha256"
SELECT encode(sha256, 'hex') || '  ' || storage_key FROM assets ORDER BY storage_key;
SQL
  rows="$(wc -l < "$work/assets.sha256")"
  log "checking $rows asset rows of $db against $assets_dir"
  ( cd -- "$assets_dir" && sha256sum -c "$work/assets.sha256" 2>/dev/null ) > "$work/result" || true
  ( cd -- "$assets_dir" && find . -type f ! -path './tmp/*' | sed 's|^\./||' | LC_ALL=C sort ) > "$work/files"
  cut -c67- "$work/assets.sha256" | LC_ALL=C sort > "$work/rows"
  LC_ALL=C comm -23 "$work/files" "$work/rows" | sed 's|^|ORPHAN: |' >> "$work/result"
  ok="$(grep -c ': OK$' "$work/result" || true)"
  bad="$(grep -c ': FAILED$' "$work/result" || true)"
  missing="$(grep -c ': FAILED open or read$' "$work/result" || true)"
  orphans="$(grep -c '^ORPHAN: ' "$work/result" || true)"
  log "assets: $rows rows, $ok match, $bad differ, $missing missing, $orphans files with no row"
  grep -v ': OK$' "$work/result" >&2 || true
  if [[ "$ok" -ne "$rows" ]]; then
    die "asset check failed"
  fi
fi

# ------------------------------------------------------------------ counts

if [[ -n "$db" && ( -n "$dump" || $counts_only -eq 1 ) ]]; then
  print_counts "$db"
fi