#!/usr/bin/env bash
# Installs everything the job needs in a FRESH container (node:20-bookworm). Safe to run twice.
set -euo pipefail
export DEBIAN_FRONTEND=noninteractive
apt-get update -qq
apt-get install -y -qq --no-install-recommends ffmpeg poppler-utils tesseract-ocr tesseract-ocr-eng ocrmypdf ghostscript fonts-urw-base35 \
  python3 python3-venv python3-pip git curl ca-certificates
python3 -m venv .venv
.venv/bin/pip install -q --disable-pip-version-check -r _pipeline/requirements.txt
echo "--- tool versions"
python3 --version; ffmpeg -version | head -1; tesseract --version 2>&1 | head -1; ocrmypdf --version; pdftotext -v 2>&1 | head -1