#!/usr/bin/env bash
# backup.sh — daily backup of librenotes state.
#
# Produces $BACKUP_DIR/librenotes-YYYYMMDD-HHMMSS.tar.gz containing:
#   - librenotes.db        (consistent SQLite .backup snapshot)
#   - notes.tar.gz         (per-tenant note files)
#   - info.txt             (timestamp, hostname, version)
#
# Required env:
#   LIBRENOTES_DB        path to the SQLite database
#   LIBRENOTES_DATA_DIR  path to the per-tenant note directory
#
# Optional env:
#   BACKUP_DIR           where to write archives (default /var/backups/librenotes)
#   BACKUP_REMOTE        rclone target for off-site copy (e.g. s3:bucket/path)
#   BACKUP_REMOTE_RSYNC  rsync destination for hard-link-deduplicated
#                        off-host copy, e.g. backup@rsync.net:librenotes/
#                        Layout written at the target:
#                          <root>/YYYY-MM-DD/librenotes-<ts>.tar.gz
#                        Each run passes --link-dest=../<previous>/ so
#                        unchanged archives cost zero extra bytes.
#   BACKUP_REMOTE_SSH_KEY path to a private SSH key used for the rsync
#                        leg (passed via -e "ssh -i <key>").
#   BACKUP_VERSION       version string written into info.txt
#
# The script is intentionally a single self-contained file so it
# can run on a minimal host with only sqlite3, tar, gzip, rsync, and
# (optionally) rclone.

set -euo pipefail

: "${LIBRENOTES_DB:?LIBRENOTES_DB is required}"
: "${LIBRENOTES_DATA_DIR:?LIBRENOTES_DATA_DIR is required}"
BACKUP_DIR="${BACKUP_DIR:-/var/backups/librenotes}"
BACKUP_VERSION="${BACKUP_VERSION:-unknown}"

mkdir -p "$BACKUP_DIR"

ts="$(date -u +%Y%m%d-%H%M%S)"
work="$(mktemp -d)"
trap 'rm -rf "$work"' EXIT

# Online SQLite snapshot. .backup is atomic from the application's
# perspective even while writes are happening.
sqlite3 "$LIBRENOTES_DB" ".backup '$work/librenotes.db'"

# Notes archive. Use --warning=no-file-changed because per-user
# files may be touched concurrently; we still get a consistent
# point-in-time view per file thanks to tar's read semantics.
tar --warning=no-file-changed -C "$LIBRENOTES_DATA_DIR" -czf "$work/notes.tar.gz" .

cat > "$work/info.txt" <<EOF
backup_at: $ts UTC
host:      $(hostname)
version:   $BACKUP_VERSION
db_size:   $(stat -c%s "$work/librenotes.db" 2>/dev/null || stat -f%z "$work/librenotes.db")
notes_size:$(stat -c%s "$work/notes.tar.gz" 2>/dev/null || stat -f%z "$work/notes.tar.gz")
EOF

archive="$BACKUP_DIR/librenotes-$ts.tar.gz"
tar -C "$work" -czf "$archive" librenotes.db notes.tar.gz info.txt

echo "wrote $archive ($(stat -c%s "$archive" 2>/dev/null || stat -f%z "$archive") bytes)"

if [ -n "${BACKUP_REMOTE:-}" ]; then
  rclone copy "$archive" "$BACKUP_REMOTE" --quiet
  echo "uploaded to $BACKUP_REMOTE"
fi

if [ -n "${BACKUP_REMOTE_RSYNC:-}" ]; then
  # Compute today / previous-day directory names. Layout at the
  # remote target is <root>/YYYY-MM-DD/. We pass --link-dest pointing
  # at yesterday's dir so unchanged archives become hard links —
  # ~free for daily snapshots that are mostly identical.
  today="$(date -u +%Y-%m-%d)"
  yesterday="$(date -u -d 'yesterday' +%Y-%m-%d 2>/dev/null \
              || date -u -v-1d +%Y-%m-%d)"
  ssh_opts=()
  if [ -n "${BACKUP_REMOTE_SSH_KEY:-}" ]; then
    ssh_opts=(-e "ssh -i $BACKUP_REMOTE_SSH_KEY -o StrictHostKeyChecking=accept-new")
  fi
  # Strip any trailing slash so we control the join.
  remote="${BACKUP_REMOTE_RSYNC%/}"
  rsync -a --link-dest="../$yesterday/" "${ssh_opts[@]}" \
        "$archive" "$remote/$today/"
  echo "rsync'd $archive -> $remote/$today/"
fi