#!/usr/bin/env bash
# 외부 GPU 서버 최초 1회 셋업
# 가정: NVIDIA GPU + CUDA 11.8 (다른 CUDA면 paddle wheel URL 수정)
# 실행 위치: ~/workspace/kr_lp_pgnet/

set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
KR_LP_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
WORKSPACE="${WORKSPACE:-$(cd "$KR_LP_DIR/.." && pwd)}"
PADDLEOCR_DIR="$WORKSPACE/PaddleOCR"
PRETRAIN_DIR="$PADDLEOCR_DIR/pretrain_models"

echo "[1/4] PaddlePaddle GPU 설치 (CUDA 11.8 기준)"
python3 -m pip install --upgrade pip
python3 -m pip install paddlepaddle-gpu==2.6.1.post118 \
    -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html

echo "[2/4] PaddleOCR clone"
if [ ! -d "$PADDLEOCR_DIR" ]; then
    git clone --depth 1 -b release/2.7 https://github.com/PaddlePaddle/PaddleOCR.git "$PADDLEOCR_DIR"
fi
cd "$PADDLEOCR_DIR"
python3 -m pip install -r requirements.txt

echo "[3/4] PGNet Step1 pretrain weight 다운로드"
mkdir -p "$PRETRAIN_DIR"
cd "$PRETRAIN_DIR"
if [ ! -d "train_step1" ]; then
    wget -q https://paddleocr.bj.bcebos.com/dygraph_v2.0/pgnet/train_step1.tar
    tar xf train_step1.tar
    rm train_step1.tar
fi

echo "[4/5] kr_lp_dict 및 config를 PaddleOCR 트리에 symlink"
ln -sf "$KR_LP_DIR/dict/kr_lp_dict.txt" "$PADDLEOCR_DIR/ppocr/utils/kr_lp_dict.txt"
mkdir -p "$PADDLEOCR_DIR/configs/e2e"
ln -sf "$KR_LP_DIR/configs/kr_lp_pgnet.yml" "$PADDLEOCR_DIR/configs/e2e/kr_lp_pgnet.yml"

echo "[5/5] GPU/Paddle 동작 확인"
python3 -c "import paddle; print('paddle:', paddle.__version__); print('CUDA available:', paddle.is_compiled_with_cuda()); print('GPU count:', paddle.device.cuda.device_count())"

echo
echo "셋업 완료. 다음 단계:"
echo "  python data_gen/generate_synthetic.py ..."
echo "  bash scripts/run_step1.sh"