scripts/setup_paddleocr.sh

#!/usr/bin/env bash
set -euo pipefail

ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
VENV="$ROOT/.venv-ocr"
PYTHON_BIN="${PYTHON_BIN:-python3.10}"

if [ ! -d "$VENV" ]; then
  "$PYTHON_BIN" -m venv "$VENV"
fi

"$VENV/bin/python" -m pip install --upgrade pip
"$VENV/bin/python" -m pip install -r "$ROOT/requirements-paddleocr.txt"

echo "PaddleOCR Arabic PP-OCRv5 sidecar is ready at $VENV"
echo "Use OCR_ENGINE=paddleocr only as a fallback; the website's readable default is Tesseract Arabic."