#!/usr/bin/env bash
# backup-prune.sh — enforce retention "keep 30 daily + 12 monthly".
#
# Walks $BACKUP_DIR for librenotes-YYYYMMDD-HHMMSS.tar.gz and
# deletes archives outside the retention policy.
#   - keep the most recent N daily archives (default 30)
#   - additionally keep the most recent archive of each of the
#     last M distinct months (default 12)
# Anything else is removed.

set -euo pipefail

BACKUP_DIR="${BACKUP_DIR:-/var/backups/librenotes}"
DAILY_KEEP="${DAILY_KEEP:-30}"
MONTHLY_KEEP="${MONTHLY_KEEP:-12}"

if [ ! -d "$BACKUP_DIR" ]; then
  echo "backup dir $BACKUP_DIR does not exist; nothing to prune"
  exit 0
fi

cd "$BACKUP_DIR"

# Sort archives by name (date is in the filename, lexicographic
# order == chronological order).
mapfile -t archives < <(ls -1 librenotes-*.tar.gz 2>/dev/null | sort)

declare -A keep
# Keep the newest DAILY_KEEP outright.
for a in "${archives[@]: -$DAILY_KEEP}"; do
  keep["$a"]=1
done

# Walk archives newest-first, recording one per month until we
# have MONTHLY_KEEP distinct months.
declare -A month_seen
months_kept=0
for ((i=${#archives[@]}-1; i>=0; i--)); do
  a="${archives[$i]}"
  # filename: librenotes-YYYYMMDD-HHMMSS.tar.gz -> YYYYMM
  ym="${a:11:6}"
  if [ -z "${month_seen[$ym]:-}" ] && [ "$months_kept" -lt "$MONTHLY_KEEP" ]; then
    keep["$a"]=1
    month_seen[$ym]=1
    months_kept=$((months_kept + 1))
  fi
done

removed=0
for a in "${archives[@]}"; do
  if [ -z "${keep[$a]:-}" ]; then
    rm -f "$a"
    removed=$((removed + 1))
  fi
done

echo "kept ${#keep[@]} archives, removed $removed"