feat(accent): ship OpenJTalk as the sole accent backend (commercial) #11
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| --- | |
| name: Docker Build Check | |
| # Build the image on PRs (no push) so a broken Dockerfile — most importantly | |
| # the dict-bake layers that make the runtime self-contained/offline | |
| # (open_jtalk_dic via pyopenjtalk, and the UniDic dict — ~700 MB compressed | |
| # download, ~1.3 GB installed — from scripts/download_unidic.sh) — fails the | |
| # PR instead of the release build. | |
| # The smoke-test step then runs the built image with `--network none` and | |
| # exercises BOTH baked dictionaries: the OpenJTalk open_jtalk_dic (via | |
| # pyopenjtalk) AND the fugashi/UniDic dicdir (via the tokeniser). A broken | |
| # or missing download of either dict fails the gate offline. | |
| on: # yamllint disable-line rule:truthy | |
| workflow_call: | |
| pull_request: | |
| branches: ["main", "dev"] | |
| workflow_dispatch: | |
| permissions: | |
| contents: read | |
| concurrency: | |
| group: docker-build-${{ github.ref }} | |
| cancel-in-progress: true | |
| jobs: | |
| build: | |
| name: Build image (no push) | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v6 | |
| - name: Set up Docker Buildx | |
| uses: docker/setup-buildx-action@v4 | |
| - name: Build image | |
| uses: docker/build-push-action@v7 | |
| with: | |
| context: . | |
| file: ./Dockerfile | |
| platforms: linux/amd64 | |
| push: false | |
| load: true | |
| tags: api-tools:pr-${{ github.event.pull_request.number || github.run_id }} | |
| cache-from: type=gha | |
| cache-to: type=gha,mode=max | |
| - name: Smoke-test the accent pipeline in the built image | |
| run: | | |
| image=api-tools:pr-${{ github.event.pull_request.number || github.run_id }} | |
| container=api-tools-smoke-${{ github.run_id }} | |
| trap 'docker rm -f "$container" >/dev/null 2>&1 || true' EXIT | |
| docker run -d --name "$container" --network none --read-only --tmpfs /tmp \ | |
| -e PYTHONDONTWRITEBYTECODE=1 \ | |
| "$image" | |
| for attempt in $(seq 1 30); do | |
| if docker exec "$container" python -c \ | |
| "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/openapi.json', timeout=2)"; then | |
| break | |
| fi | |
| if [[ "$attempt" == 30 ]]; then | |
| docker logs "$container" | |
| exit 1 | |
| fi | |
| sleep 1 | |
| done | |
| docker exec "$container" python -c \ | |
| "import json, urllib.request; request=urllib.request.Request('http://127.0.0.1:8000/api/MarkAccent/', data=json.dumps({'text':'東京'}).encode(), headers={'Content-Type':'application/json'}); response=json.load(urllib.request.urlopen(request, timeout=30)); assert response['status'] == 200 and response['result']" |