schema_diff.yml

name: Schema Diff  # If this is changed, need to update `schema_diff_comment.yml` as well

on:
  pull_request:
    paths:
      - synapse/storage/schema/*/delta/**
      - synapse/storage/schema/*/full_schemas/**
      - .github/workflows/schema_diff.yml

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

permissions:
  contents: read

jobs:
  # Posts a GitHub PR comment that shows what the effective change to the schema is.
  # Provides an excuse to run the `make_full_schema.sh` script in CI (so we keep it working)
  # and can act as a review aid for schema changes, letting you easily see the diff of the
  # end result, even when background updates or complex schema deltas are present.
  show-schema-diff:
    name: Show schema diff
    runs-on: ubuntu-latest

    permissions:
      pull-requests: write

    steps:
      - name: Start postgres with a faked clock
        background: true
        id: postgres
        # Use faketime here for schema deltas that are wall-clock sensitive under Postgres
        # For SQLite, faketime is used when invoking `make_full_schema.sh` within the script
        run: |
          # Build a docker image with faketime
          mkdir /tmp/postgres-faketime
          cat > /tmp/postgres-faketime/Dockerfile <<'EOF'
            FROM postgres:14-alpine
            RUN apk add --no-cache libfaketime

            # It seems like it could be harmful to fake the monotonic timer
            # as it might prevent deadlock detection, etc.
            # But not sure, just doing out of precaution.
            ENV FAKETIME_DONT_FAKE_MONOTONIC=1
            ENTRYPOINT ["faketime", "-f", "2001-05-25 12:42:42", "docker-entrypoint.sh"]
            CMD ["postgres"]
          EOF
          docker build -t localhost/postgres-faketime /tmp/postgres-faketime

          # Run it in the background
          docker run -d --name postgres -p 5432:5432 \
            -e POSTGRES_PASSWORD=postgres \
            -e POSTGRES_INITDB_ARGS="--lc-collate C --lc-ctype C --encoding UTF8" \
            --health-cmd pg_isready --health-interval 10s \
            --health-timeout 5s --health-retries 5 \
            localhost/postgres-faketime

      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          fetch-depth: 0

      - name: Install PostgreSQL client and faketime
        run: sudo apt-get -qq install postgresql-client faketime

      - uses: matrix-org/setup-python-poetry@5bbf6603c5c930615ec8a29f1b5d7d258d905aa4 # v2.0.0
        with:
          poetry-version: "2.4.1"
          extras: "postgres"
          python-version: "3.x"

      - name: Wait for Postgres to be up
        run: |
          until [ "$(docker inspect -f '{{.State.Health.Status}}' postgres)" = healthy ]; do sleep 2; done

      - name: Generate schema diff
        id: schema_diff
        env:
          PGHOST: localhost
          PGUSER: postgres
          PGPASSWORD: postgres
        run: |
          poetry run python .ci/scripts/schema_diff.py \
            --base origin/develop \
            > "${{ runner.temp }}/schema_diff.md"

      - name: Stop postgres
        cancel: postgres

      # If the generation step failed, write an error message so the sticky
      # comment step still has a file to read.
      - name: Ensure output file exists on failure
        if: always() && steps.schema_diff.outcome == 'failure'
        run: |
          echo "⚠️ Schema diff generation failed. See job logs for details." \
            > "${{ runner.temp }}/schema_diff.md"

      # Post a comment.
      #
      # For same-repo PRs, we can do this directly and we are done.
      - name: Post sticky PR comment
        uses: marocchino/sticky-pull-request-comment@28ad303d6acb4ccfc50f20c0044188e7e294b8c4 # v3
        # Only run for same-repo PRs
        if: always() && github.event.pull_request.head.repo.full_name == github.repository
        with:
          header: schema-diff
          path: ${{ runner.temp }}/schema_diff.md

      # For PRs from forks, we only have a read-only `GITHUB_TOKEN` here and need to work around
      # by triggering a `workflow_run` onto the main repo.
      #
      # We upload an artifact and the `schema_diff_comment.yml` workflow will be triggered
      # on the main repo by this workflow exiting.
      - name: Save PR number for forked PRs
        # Only run for fork PRs
        if: always() && github.event.pull_request.head.repo.full_name != github.repository
        run: echo "${{ github.event.pull_request.number }}" > "${{ runner.temp }}/pr_number"

      - name: Upload schema diff artifact for forked PRs
        # Only run for fork PRs
        if: always() && github.event.pull_request.head.repo.full_name != github.repository
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
        with:
          name: schema-diff
          path: |
            ${{ runner.temp }}/schema_diff.md
            ${{ runner.temp }}/pr_number
          retention-days: 1