extract-pdf-text.yaml

name: Extract PDF text for search index

on:
  push:
    branches: [main]
    paths:
      - "corpus/**/*.pdf"
      - "corpus/MANIFEST.yaml"
      - "scripts/extract_pdf_text.py"
  workflow_dispatch: {}

permissions:
  contents: write

jobs:
  extract:
    runs-on: ubuntu-latest
    steps:
      - name: Check out repo
        uses: actions/checkout@v4

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: "3.11"

      - name: Install dependencies
        run: pip install -r scripts/requirements.txt

      - name: Extract text from corpus PDFs
        run: python scripts/extract_pdf_text.py --repo-root .

      - name: Commit updated extracted text
        run: |
          git config user.name "corpus-extraction-bot"
          git config user.email "actions@users.noreply.github.com"
          git add corpus/_extracted/
          if git diff --cached --quiet; then
            echo "No changes to commit."
          else
            git commit -m "Extract PDF text for search index ($(date -u +%Y-%m-%d))"
            git push
          fi