tests.yml

name: Integration test with benchmark

on: [push]

env:
  TESSDATA_PREFIX: "/usr/share/tesseract-ocr/4.00/tessdata"
  TORCH_DEVICE: "cpu"
  OCR_ENGINE: "tesseract" # So we don't have to install ghostscript, which takes a long time

jobs:
  build:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3
      - name: Set up Python 3.11
        uses: actions/setup-python@v4
        with:
          python-version: 3.11
      - name: Install system dependencies
        run: cat scripts/install/apt-requirements.txt | xargs sudo apt-get install -y
      - name: Show tessdata folders
        run: ls /usr/share/tesseract-ocr/
      - name: Install python dependencies
        run: |
          pip install poetry
          poetry install
          poetry remove torch
          poetry run pip install torch --index-url https://download.pytorch.org/whl/cpu
      - name: Download benchmark data
        run: |
          wget -O benchmark_data.zip "https://drive.google.com/uc?export=download&id=1ktVDYPEeyHlKLaF56FnHjI5VjVnYa1xL"
          unzip benchmark_data.zip
      - name: Run benchmark test
        run: |
          poetry run python benchmark.py benchmark_data/pdfs benchmark_data/references report.json
          poetry run python scripts/verify_benchmark_scores.py report.json