#!/usr/bin/env bash
# Back up a student's Uno Q before reflashing it for the APESS workshop.
#
#   ./backup-uno-q.sh <adb-serial> [team-label] [outdir]
#
# Students arrive having spent a week doing their own sensor work on these
# boards. THAT WORK IS IRREPLACEABLE — this runs before provision-uno-q.sh and
# must succeed before anything is overwritten.
#
# Strategy: DENYLIST, not allowlist. We do not know where a given team put
# their data (App Lab project dir, a loose CSV, a sketch folder), so we capture
# all of /home/arduino and exclude only what we can reproduce ourselves:
# the GGUF models, the Arduino core cache, our llama/zeroclaw binaries, the
# embedded SPA, and build output. On a reference board that leaves ~1-2 MB;
# a board with a week of logged data will be larger but still quick.
#
# The archive is VERIFIED READABLE before the script reports success — an
# unverified backup is not a backup.
set -euo pipefail

SERIAL="${1:?usage: backup-uno-q.sh <adb-serial> [team-label] [outdir]}"
LABEL="${2:-$SERIAL}"
OUTDIR="${3:-./backups}"

a() { adb -s "$SERIAL" "$@"; }

STAMP="$(date -u +%Y%m%dT%H%M%SZ)"
NAME="unoq-${LABEL}-${STAMP}"
REMOTE_TAR="/tmp/${NAME}.tar.gz"
LOCAL_TAR="${OUTDIR}/${NAME}.tar.gz"
LOCAL_MANIFEST="${OUTDIR}/${NAME}.manifest.txt"

# Reproducible — ours, or regenerable. Everything else is theirs and is kept.
#
# DELIBERATELY NOT EXCLUDED: ~/.local/share/arduino-app-cli/examples (~37M).
# Those are Arduino's stock App Lab examples, so in principle reproducible —
# but several of them (real-time-accelerometer, anomaly-detection,
# air-quality-monitoring) are exactly what a student doing sensor work would
# open and then edit IN PLACE. Excluding them would silently discard a week of
# work to save 25MB. We keep them. A backup is insurance, not a size contest.
EXCLUDES=(
  '--exclude=./models'           # 1.5G of GGUF weights — we push these
  '--exclude=./.arduino15'       # ~570M Arduino cores/index — arduino-cli refetches
  '--exclude=./llama'            # llama.cpp binaries — we push these
  '--exclude=./web-dist'         # embedded SPA build — we push this
  '--exclude=./.cache'           # regenerable
  '--exclude=./lost+found'
  '--exclude=./zeroclaw'         # the daemon binary...
  '--exclude=./zeroclaw.*'       # ...and its .bak copies
  '--exclude=./llama8083.log'
  '--exclude=./zc-daemon.log'
  '--exclude=./zc-supervisor.log'
  '--exclude=*/build'            # sketch build output — recompiled on demand
)

mkdir -p "$OUTDIR"

echo "==> [1/5] board reachable?"
a shell 'echo ok' >/dev/null 2>&1 || { echo "    FAIL: board $SERIAL not reachable over adb"; exit 1; }
a shell 'test -d /home/arduino' >/dev/null 2>&1 || { echo "    FAIL: /home/arduino missing"; exit 1; }
echo "    $SERIAL ok"

echo "==> [2/5] inventory what will be captured"
a shell '
  cd /home/arduino || exit 1
  echo "    user-work directories:"
  for d in sketches Arduino ArduinoApps .arduino-bricks; do
    if [ -e "$d" ]; then printf "      %-18s %s\n" "$d" "$(du -sh "$d" 2>/dev/null | cut -f1)"; fi
  done
  echo "    data-shaped files (top 10 by size):"
  find . -maxdepth 4 \( -name "*.csv" -o -name "*.tsv" -o -name "*.dat" -o -name "*.json" -o -name "*.txt" -o -name "*.py" \) \
    -not -path "./.arduino15/*" -not -path "./.cache/*" -not -path "*/build/*" -not -path "./.zeroclaw/*" \
    -printf "      %s\t%p\n" 2>/dev/null | sort -rn | head -10
  echo "      (none found)"
' 2>/dev/null || true

echo "==> [3/5] archive on board"
a shell "cd /home/arduino && tar czf '$REMOTE_TAR' ${EXCLUDES[*]} . 2>/dev/null; echo done" >/dev/null
SIZE="$(a shell "du -h '$REMOTE_TAR' 2>/dev/null | cut -f1" | tr -d '\r\n ')"
echo "    archive: $SIZE"

echo "==> [4/5] pull + verify"
a pull "$REMOTE_TAR" "$LOCAL_TAR" >/dev/null 2>&1 || { echo "    FAIL: could not pull archive"; exit 1; }

# An unverified backup is not a backup: list the archive and require real content.
if ! tar tzf "$LOCAL_TAR" > "$LOCAL_MANIFEST" 2>/dev/null; then
  echo "    FAIL: archive is not readable — DO NOT REFLASH THIS BOARD"
  exit 1
fi
ENTRIES="$(wc -l < "$LOCAL_MANIFEST" | tr -d ' ')"
if [ "$ENTRIES" -lt 5 ]; then
  echo "    FAIL: archive has only $ENTRIES entries — suspiciously empty, DO NOT REFLASH"
  exit 1
fi
echo "    verified: $ENTRIES entries, manifest at $LOCAL_MANIFEST"

echo "==> [5/5] clean up board temp"
a shell "rm -f '$REMOTE_TAR'" >/dev/null 2>&1 || true

cat <<EOF

    BACKUP OK — safe to reflash $SERIAL
    archive : $LOCAL_TAR ($SIZE)
    manifest: $LOCAL_MANIFEST

    restore (after reflash):
      adb -s $SERIAL push $LOCAL_TAR /tmp/restore.tar.gz
      adb -s $SERIAL shell 'cd /home/arduino && tar xzf /tmp/restore.tar.gz && rm /tmp/restore.tar.gz'
EOF