#!/usr/bin/env bash
# DVC pull → decompress .dvc-store/ back into data/.
#
# Counterpart: scripts/data-push.sh
#
# Usage:
#   ./scripts/data-pull.sh           # pull + decompress all
#   ./scripts/data-pull.sh --local   # decompress only (skip dvc pull, use existing cache)

set -euo pipefail

REPO_ROOT="$(cd "$(dirname "$0")/.." && pwd)"
DATA_DIR="$REPO_ROOT/data"
STORE_DIR="$REPO_ROOT/.dvc-store"
SKIP_PULL=false
[[ "${1:-}" == "--local" ]] && SKIP_PULL=true

THREADS=$(nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || echo 4)

if ! $SKIP_PULL; then
  echo "=== DVC pull ==="
  cd "$REPO_ROOT"
  # Pull from public HTTP remote (no credentials needed)
  uvx --with 'dvc[s3]' dvc pull -r public
  echo ""
fi

if [[ ! -d "$STORE_DIR" ]]; then
  echo "Error: .dvc-store/ not found — run dvc pull first or check .dvc-store.dvc exists" >&2
  exit 1
fi

echo "=== Decompressing .dvc-store/ → data/ ==="
echo "Threads: $THREADS"
echo ""

count=0

while IFS= read -r -d '' zstfile; do
  relpath="${zstfile#$STORE_DIR/}"
  relpath="${relpath%.zst}"  # strip .zst to get original relative path
  dstfile="$DATA_DIR/$relpath"
  dstdir="$(dirname "$dstfile")"

  # Skip if destination exists and is newer than compressed source
  if [[ -f "$dstfile" && "$dstfile" -nt "$zstfile" ]]; then
    continue
  fi

  mkdir -p "$dstdir"
  zstd -d -T"$THREADS" -q --force "$zstfile" -o "$dstfile"
  count=$((count + 1))
done < <(find "$STORE_DIR" -name '*.zst' -type f -print0)

echo "Decompressed $count files into data/"
echo ""
echo "=== Done ==="