name: Run Common Crawl Tests

on:
  push:
    branches: [master]
  workflow_dispatch:
  workflow_call:

jobs:
  build:
    runs-on: ubuntu-latest
    strategy:
      fail-fast: false
      matrix:
        pair: ["0000-0001", "0002-0003", "0004-0005", "0006-0007"]

    steps:
      - uses: actions/checkout@v2

      - name: Set up dotnet core
        uses: actions/setup-dotnet@v3
        with:
          dotnet-version: |
            8.0.x
            9.0.x
          
      - name: Restore corpus cache
        id: restore-corpus
        uses: actions/cache@v4
        with:
          path: corpus/
          key: ${{ runner.os }}-pdf-corpus-${{ matrix.pair }}

      - name: Download corpus if cache missed
        if: steps.restore-corpus.outputs.cache-hit != 'true'
        run: |
          mkdir -p corpus/zipfiles
          cd corpus/zipfiles
          for file in $(echo "${{ matrix.pair }}" | tr '-' ' '); do
            echo "Downloading $file.zip"
            wget -nv "https://digitalcorpora.s3.amazonaws.com/corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/0000-0999/$file.zip" -O "$file.zip"
          done
          cd ..
          unzip 'zipfiles/*.zip' -d extracted
          # run: rm -f zipfiles/*.zip

      - name: Remove unwanted test files
        run: |
          while read f || [ -n "$f" ]; do
            full="corpus/extracted/$f"
            if [ -f "$full" ]; then
              echo "Removing $full"
              rm "$full"
            fi
          done < tools/common-crawl-ignore.txt

      - name: Run tests against corpus
        run: dotnet run --project tools/UglyToad.PdfPig.ConsoleRunner/UglyToad.PdfPig.ConsoleRunner.csproj "corpus/extracted"