unicode-detector.yaml

name: Unicode Detector

on:
  pull_request:
    types:
      - opened
      - reopened
      - synchronize
  workflow_dispatch:

permissions:
  contents: read

concurrency:
  group: ${{ github.workflow }}-${{ github.ref || github.run_id }}
  cancel-in-progress: ${{ github.ref_name != github.event.repository.default_branch }}

jobs:
  unicode-detector:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout repository
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          fetch-depth: 0

      - name: Setup uv
        uses: astral-sh/setup-uv@e06108dd0aef18192324c70427afc47652e63a82 # v7.5.0
        with:
          enable-cache: false

      - name: Collect added and modified files
        id: changed-files
        shell: bash
        run: |
          if [ "${{ github.event_name }}" = "pull_request" ]; then
            # Scan the full current PR diff, not just the most recent push.
            # This keeps the file list correct for batched commits and force-pushes.
            BASE_SHA=$(git merge-base "${{ github.event.pull_request.base.sha }}" "${{ github.event.pull_request.head.sha }}")
            HEAD_SHA="${{ github.event.pull_request.head.sha }}"
            git diff --name-only --diff-filter=AMR "$BASE_SHA" "$HEAD_SHA" > changed_unicode_files.txt
          else
            echo "Unsupported event: ${{ github.event_name }}" >&2
            exit 1
          fi

          if [ -s changed_unicode_files.txt ]; then
            echo "has_files=true" >> "$GITHUB_OUTPUT"
            echo "Scanning these paths:"
            cat changed_unicode_files.txt
          else
            echo "has_files=false" >> "$GITHUB_OUTPUT"
            echo "No added or modified files to scan."
          fi

      - name: Run unicode detector on changed files
        if: steps.changed-files.outputs.has_files == 'true'
        run: uv run unicode-detector --files-from changed_unicode_files.txt