#!/usr/bin/env bash
#
# pull-domains.sh — fetch the rspamd domains CDB from the agent host and
# install it for migadu_counters, the way rcptd's build.sh pulls its maps.
#
# The agent already produces the finished CDB (extract.sh: cdb -m ->
# /usr/local/etc/agent/build/rspamd/rspamd_domains_db), so this is
# pull → compare → install:
#
#   1. rsync the file from the agent into $MAPS_DIR (ssh forced to IPv4, see
#      rcptd: agenthost also has an IPv6 address not reachable from every host).
#   2. cmp against the installed baseline $DOMAINS_CDB.orig; identical → done.
#      Most runs end here: the agent only rewrites the file when its content
#      changed, so the 15-second cron cycle is a no-op cmp.
#   3. Changed: copy to a dotfile next to the target, verify it opens and has
#      records (cdb -s), then mv it over $DOMAINS_CDB — atomic, so the daemon
#      never sees a half-written file — and keep the pulled copy as .orig.
#      The daemon's fsnotify watcher reloads on the mv; the explicit reload is
#      belt and braces.
#
# Never rewrite $DOMAINS_CDB in place: the daemon keeps the file open and an
# in-place rewrite truncates the inode under it. This script only ever mv's.
#
# Environment (templated by the Ansible role; defaults below are the
# production paths). Tests override RSYNC_SRC with a local path.
#
set -u

AGENT_HOST=${AGENT_HOST:-agent@agenthost}
AGENT_PATH=${AGENT_PATH:-/usr/local/etc/agent/build/rspamd/rspamd_domains_db}
RSYNC_SRC=${RSYNC_SRC:-$AGENT_HOST:$AGENT_PATH}   # a local path skips ssh (tests, co-located agent)
RSYNC_RSH=${RSYNC_RSH:-ssh -4}
MAPS_DIR=${MAPS_DIR:-/usr/local/etc/migadu_counters/maps}
DOMAINS_DIR=${DOMAINS_DIR:-/usr/local/etc/migadu_counters/db}
DOMAINS_CDB=${DOMAINS_CDB:-$DOMAINS_DIR/rspamd_domains_db}
LOG_FILE=${LOG_FILE:-/var/log/migadu_counters/pull.log}
LOCK_FILE=${LOCK_FILE:-$DOMAINS_DIR/.pull-lock}
LOCK_MAX_AGE=${LOCK_MAX_AGE:-120}                  # seconds; older locks are stale (crashed run)
RELOAD_CMD=${RELOAD_CMD:-service migadu_counters reload}

NAME=$(basename "$DOMAINS_CDB")
PULLED=$MAPS_DIR/$NAME
TMP=$DOMAINS_DIR/.$NAME.tmp

log() { echo "$(date '+%Y-%m-%d %H:%M:%S') $*" | tee -a "$LOG_FILE"; }
mtime() { stat -f %m "$1" 2>/dev/null || stat -c %Y "$1"; }

cleanup() { rm -f "$TMP" "$LOCK_FILE"; }
fail() { log "FAIL: $*"; cleanup; exit 1; }

mkdir -p "$MAPS_DIR" "$DOMAINS_DIR" "$(dirname "$LOG_FILE")" || { echo "cannot create directories" >&2; exit 1; }

# Lock: cron (@15) cannot overlap this job with itself; the lock guards a
# manual or ansible-triggered run racing the scheduled one.
if [ -f "$LOCK_FILE" ] && [ "$(mtime "$LOCK_FILE")" -ge $(( $(date +%s) - LOCK_MAX_AGE )) ]; then
  log "previous instance is still running, skipping"
  exit 0
fi
touch "$LOCK_FILE" || { echo "cannot create $LOCK_FILE" >&2; exit 1; }
trap 'rm -f "$TMP" "$LOCK_FILE"' EXIT

# 1. pull. --checksum: the agent can rebuild the file with the same size
# within the same second, which rsync's size+mtime quick check would miss;
# checksumming one ~9 MB file every cycle is cheap.
if ! rsync -a --checksum -e "$RSYNC_RSH" "$RSYNC_SRC" "$PULLED" >>"$LOG_FILE" 2>&1; then
  fail "rsync from $RSYNC_SRC failed"
fi
[ -s "$PULLED" ] || fail "pulled $PULLED is missing or empty"

# 2. compare with the installed baseline
if [ -f "$DOMAINS_CDB" ] && cmp -s "$PULLED" "$DOMAINS_CDB.orig"; then
  log "$NAME unchanged"
  exit 0
fi

# 3. verify, then install atomically
rm -f "$TMP"
cp "$PULLED" "$TMP" || fail "copy to $TMP failed"
records=$(cdb -s "$TMP" 2>/dev/null | awk '/number of records/ { print $4 }')
if [ -z "$records" ]; then
  fail "$PULLED is not a valid CDB (cdb -s failed), keeping the installed file"
fi
if [ "$records" -eq 0 ]; then
  fail "$PULLED holds no records, keeping the installed file"
fi
chmod 0644 "$TMP"
mv "$TMP" "$DOMAINS_CDB" || fail "mv into place failed"
cp "$PULLED" "$DOMAINS_CDB.orig" || log "warning: could not update $DOMAINS_CDB.orig (next run will reinstall)"
log "$NAME installed ($records records)"

# The fsnotify watcher already picked up the mv; make sure anyway.
$RELOAD_CMD >>"$LOG_FILE" 2>&1 || true
exit 0