#!/usr/bin/env bash
# Build a local zstd cache of v0 (egirl-platform) from its NFS source.
# Run once on apricot — afterward, ./scripts/extract-archive.sh platform.0 is fast.
#
# Source: /mnt/bigdisk/_/last-linux-backup/applications/src/@egirl/egirl-platform/
# Output: ~/.cache/atlilith-archives/platform.0.tar.zst
#
# Excludes ML weights, build artifacts, etc. — see EXCLUDES below.

set -euo pipefail

SRC="/mnt/bigdisk/_/last-linux-backup/applications/src/@egirl/egirl-platform"
CACHE_DIR="${HOME}/.cache/atlilith-archives"
OUT="${CACHE_DIR}/platform.0.tar.zst"

ZSTD_LEVEL="${ZSTD_LEVEL:-3}"

EXCLUDES=(
    # vcs / build
    --exclude='.git'
    --exclude='.gitlab-ci-local'
    --exclude='.playwright-mcp'
    --exclude='.turbo'
    --exclude='.next'
    --exclude='dist'
    --exclude='build'
    --exclude='out'

    # package manager
    --exclude='nm_marker_replace'
    --exclude='.pnpm-store'
    --exclude='.yarn/cache'
    --exclude='.cache'

    # ML model directories (by convention)
    --exclude='ml-service'
    --exclude='models'
    --exclude='checkpoints'
    --exclude='weights'
    --exclude='training/data'
    --exclude='training_data'
    --exclude='captcha-solver'

    # ML model files (anywhere)
    --exclude='*.gguf'
    --exclude='*.safetensors'
    --exclude='*.bin'
    --exclude='*.ckpt'
    --exclude='*.pth'
    --exclude='*.pt'
    --exclude='*.onnx'
    --exclude='*.h5'

    # large media
    --exclude='*.mp4'
    --exclude='*.mov'
    --exclude='*.webm'
    --exclude='*.zip'
    --exclude='*.tar.gz'
    --exclude='*.tar.zst'
)

if [ ! -d "$SRC" ]; then
    echo "error: source not found: $SRC" >&2
    exit 1
fi

mkdir -p "$CACHE_DIR"

if [ -f "$OUT" ]; then
    echo "warning: cache exists: $OUT"
    read -rp "rebuild? [y/N] " ans
    [[ "$ans" =~ ^[yY] ]] || { echo "aborted"; exit 0; }
    rm -f "$OUT"
fi

echo "building v0 cache from $SRC (NFS)"
echo "  → $OUT"
before=$(date +%s)
tar "${EXCLUDES[@]}" -cf - -C "$(dirname "$SRC")" "$(basename "$SRC")" \
    | zstd -"$ZSTD_LEVEL" -T0 -o "$OUT"
after=$(date +%s)
size=$(du -h "$OUT" | cut -f1)
echo "done in $((after - before))s, size: $size"