# The converters against real documents.
#
# `ci.yml` proves the filters on documents built to be easy (`test_raw_derive.py`,
# `test_raw_derive_binary.py`). This workflow derives the real ones: the test corpus and its
# harness live in the private repository `torben/chemenu-testfiles`, cloned into `testfiles/`
# (gitignored in this repository) and run with this checkout's `tools/.venv`. The corpus is large
# (some 76 MB, one book needs 48 s per derivation) and holds material that may not sit in a public
# repository, which is why none of it runs in the standard CI.
#
# When it runs:
# - on a push to `main` that touches the converter surface (the `paths:` list below). Gitea
#   evaluates `paths:` the way GitHub does - observed for `paths-ignore` in `ci.yml` and in use for
#   `paths:` in `release.yml`; do not re-derive it;
# - by hand (`workflow_dispatch`), which is the way to run it after a change in the private
#   repository alone: a push there starts nothing here, and a commit that reaches the converters
#   only indirectly is not in the list;
# - before a release without suffix: `release.yml` carries the same steps as its job `converters`
#   and the release job waits for it. A candidate (`-beta.N`) does not run it.
#
# It always tests `main` of the private repository. A converter change that alters an expected
# output (`.expect`) is therefore two commits, one per repository, the private one first.
#
# Runner shape: identical to ci.yml, and for the same reason - see its header for `nodejs`.
#
# Access to the private repository: the per-job token (`${{ gitea.token }}`), as `release.yml`
# uses it for this repository. It can read `chemenu-testfiles` only because that repository's own
# Actions settings grant `torben/chemenu` access - a grant set in this repository does nothing.
# Without it the second checkout fails with "Determining the default branch ... not found", which
# reads like a missing repository rather than a missing permission (Gitea #232, runs 699 and 701).

name: Converters

on:
  push:
    branches: [main]
    paths:
      - 'tools/chemenu/filters/**'
      - 'tools/chemenu/commands/raw/derive.py'
      - 'tools/chemenu/commands/raw/accept.py'
      - 'tools/chemenu/tests/test_raw_derive*.py'
      - 'tools/chemenu/tests/binary_formats.py'
      - 'tools/requirements.txt'
      - '.gitea/workflows/converters.yml'
  workflow_dispatch:

jobs:
  converters:
    runs-on: linux-docker
    timeout-minutes: 30
    container:
      image: debian:trixie-slim
    env:
      WIKITOOL_SESSION_ID: converters-${{ github.run_id }}
      WIKI_TRACE_DIR: /tmp/wikitool-trace

    steps:
      - name: System dependencies
        run: |
          set -eu
          apt-get update -qq
          apt-get install -y --no-install-recommends \
            python3 python3-venv git nodejs ripgrep ca-certificates
          rm -rf /var/lib/apt/lists/*

      - uses: actions/checkout@v7

      - name: The private test corpus
        uses: actions/checkout@v7
        with:
          repository: torben/chemenu-testfiles
          token: ${{ gitea.token }}
          path: testfiles

      - name: Tool environment
        run: |
          set -eu
          git config --global --add safe.directory "$GITHUB_WORKSPACE"
          tools/preflight.sh
          tools/.venv/bin/python -m pip install --quiet pytest

      - name: Real documents
        # `-c pytest.ini` applies the suite's own configuration to a harness that lives outside
        # `tools/`; the harness conftest pulls in the suite's conftest (testfiles/README.md).
        run: |
          set -eu
          cd tools
          .venv/bin/python -m pytest -c pytest.ini ../testfiles/harness -q --durations=5