thermograph/infra/deploy/geoip-refresh.sh

#!/usr/bin/env bash
# Refresh the IP-geolocation database used by the approximate-location fallback
# (backend/data/geoip.py). Runs on the HOST (prod/beta), not in a container, on
# a systemd timer — see geoip-refresh.timer.
#
# Why on the host and not baked into the image:
#   * it is a 100-200 MB data file on its own monthly release cadence, not code;
#     baking it in adds that to every image pull and freezes its freshness to
#     whenever the last deploy happened;
#   * MaxMind's GeoLite EULA *requires* deleting a database within 30 days of a
#     newer release, which a build-time copy cannot honour on its own;
#   * geoip.py memory-maps the file and re-opens it when (mtime, size) changes,
#     so an atomic swap here is picked up with no restart and no deploy.
#
# Default source: DB-IP's IP to City Lite, CC BY 4.0, no account and no licence
# key — which is why this script needs no secret from the vault. Point
# GEOIP_URL elsewhere (e.g. a MaxMind permalink carrying a licence key from
# /etc/thermograph.env) to use a different database; geoip.py reads the file's
# own metadata for the attribution line, so nothing else changes.
#
#   sudo /opt/thermograph/infra/deploy/geoip-refresh.sh
#
# Exit status: 0 on a successful swap AND on "already current" (so the timer
# doesn't alarm); non-zero only on a real failure, leaving any existing
# database untouched — a failed refresh must never be worse than a stale one.
set -euo pipefail

DEST_DIR="${THERMOGRAPH_GEOIP_HOST_DIR:-/var/lib/thermograph/geoip}"
DEST="$DEST_DIR/city.mmdb"
# DB-IP publishes one file per month at a predictable URL. Try this month, then
# last month: the new file appears at some point on the 1st, so a timer firing
# early would otherwise fail for a day.
BASE="${GEOIP_BASE:-https://download.db-ip.com/free}"
THIS_MONTH="$(date -u +%Y-%m)"
LAST_MONTH="$(date -u -d "$(date -u +%Y-%m-01) -1 month" +%Y-%m)"

log() { echo "[geoip-refresh] $*"; }

mkdir -p "$DEST_DIR"
tmp="$(mktemp -d "${TMPDIR:-/tmp}/geoip.XXXXXX")"
trap 'rm -rf "$tmp"' EXIT

url=""
if [ -n "${GEOIP_URL:-}" ]; then
  url="$GEOIP_URL"
else
  for m in "$THIS_MONTH" "$LAST_MONTH"; do
    candidate="$BASE/dbip-city-lite-$m.mmdb.gz"
    if curl -fsSI --max-time 30 "$candidate" >/dev/null 2>&1; then
      url="$candidate"; break
    fi
  done
fi
[ -n "$url" ] || { log "no published database found at $BASE for $THIS_MONTH or $LAST_MONTH"; exit 1; }
log "source: $url"

curl -fsSL --max-time 900 --retry 3 --retry-delay 10 -o "$tmp/db.gz" "$url"
gunzip -c "$tmp/db.gz" > "$tmp/city.mmdb"

# Prove the file actually opens and answers before it can replace a working
# one. A truncated download that merely *exists* would otherwise silently
# disable lookups for a month.
python3 - "$tmp/city.mmdb" <<'PY'
import sys
import maxminddb
with maxminddb.open_database(sys.argv[1]) as r:
    meta = r.metadata()
    if "city" not in (meta.database_type or "").lower():
        sys.exit(f"unexpected database_type: {meta.database_type}")
    if r.get("8.8.8.8") is None and r.get("1.1.1.1") is None:
        sys.exit("database opened but answered nothing for known public addresses")
    print(f"[geoip-refresh] verified {meta.database_type} "
          f"built {meta.build_epoch} nodes={meta.node_count}")
PY

if [ -f "$DEST" ] && cmp -s "$tmp/city.mmdb" "$DEST"; then
  log "already current: $DEST unchanged"
  exit 0
fi

# Atomic swap on the same filesystem: readers either see the whole old file or
# the whole new one, never a half-written mmap. The app's open handle keeps the
# unlinked inode alive until it re-opens on the mtime change.
install -m 0444 "$tmp/city.mmdb" "$DEST.new"
mv -f "$DEST.new" "$DEST"
log "installed $DEST ($(stat -c %s "$DEST") bytes)"

# MaxMind's EULA requires deleting superseded copies within 30 days; keeping no
# copies at all satisfies that trivially and is the right default for DB-IP too.
find "$DEST_DIR" -maxdepth 1 -name 'city.mmdb.*' -type f -delete 2>/dev/null || true