get_text.yml

name: Dump out PDF text

on:
  push:
    branches:
      - 'master'
  workflow_dispatch:

jobs:
  scheduled:
    runs-on: ubuntu-latest
    steps:
      -
        name: "Check out this repo"
        uses: actions/checkout@v3
        with:
          fetch-depth: 0
      - name: Install dependencies
        run: |
          sudo apt-get update
          sudo apt-get install -y libpoppler-cpp-dev libpoppler-dev poppler-utils rename
      - name: Get changed files
        id: changed-files
        uses: tj-actions/changed-files@v23.2
      - name: Fix changed file names
        run: |
          cd input && rename -v 's/ \(.*\)\./\./' ./*.pdf
          for f in *\ *; do mv "$f" "${f// /_}"; done
      - name: Dump out text
        run: |
          cd input && for file in *.pdf; do pdftotext "$file" "$GITHUB_WORKSPACE/output/${file%.*}.txt"; done
      -
        name: "Commit and push if it changed"
        run: |-
            git config user.name "Automated"
            git config user.email "actions@users.noreply.github.com"
            git add -A
            timestamp=$(date -u)
            git commit -m "Latest data: ${timestamp}" || exit 0
            git push