checks.yml

name: checks
on: [push, pull_request]

jobs:
  hygiene:
    name: repo hygiene
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - name: Required files present
        run: |
          for f in LICENSE README.md CONTRIBUTING.md CODE_OF_CONDUCT.md GOVERNANCE.md SECURITY.md; do
            [ -f "$f" ] || { echo "::error::missing $f"; exit 1; }
          done
      - name: Markdown links resolve
        uses: lycheeverse/lychee-action@v2
        with: { args: "--no-progress ." }

  schema:
    name: records validate against schema
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - run: pip install jsonschema
      - name: Validate fixtures
        run: |
          python -m jsonschema -i fixtures/sample.json schema/record.schema.json \
            || { echo "::error::fixture does not match schema"; exit 1; }

  normalisation:
    name: unicode form is consistent
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - name: Assert single normalisation form
        run: python scripts/check_normalisation.py

  duplicates:
    name: no duplicate pairs
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - run: python scripts/check_duplicates.py

  # ---- Not yet implemented. Visible on purpose: honest status, published roadmap. ----

  language-identity:
    name: language identity (planned — year 1)
    if: false
    runs-on: ubuntu-latest
    steps:
      - run: echo "Off-the-shelf language ID is unreliable for yor/swa/pcm. Needs a team-defined approach."

  benchmark-leakage:
    name: benchmark leakage (planned — needs holdout list)
    if: false
    runs-on: ubuntu-latest
    steps:
      - run: echo "Blocked on the benchmark holdout ID list."

  provenance-gate:
    name: provenance and rights gate (planned — vocabulary not yet defined)
    if: false
    runs-on: ubuntu-latest
    steps:
      - run: echo "Blocked on rights_status vocabulary."