docker-build.yml

name: Build and Push Docker Image

on:
  push:
    branches: [master]
    tags: ["v*"]
  pull_request:
    branches: [master]
  workflow_dispatch:

concurrency:
  # Serialize every publishing event because both master and version tags can
  # update registry state. PR checks remain independently supersedable.
  group: ${{ github.workflow }}-${{ github.event_name == 'pull_request' && github.ref || 'publish' }}
  cancel-in-progress: ${{ github.event_name == 'pull_request' }}

env:
  DOCKERHUB_IMAGE: aethersailor/rule-bot
  GHCR_IMAGE: ghcr.io/aethersailor/rule-bot
  MAX_COMPRESSED_PLATFORM_SIZE: 40000000

permissions:
  contents: read

jobs:
  validate:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout repository
        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7

      - name: Set up Python
        uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7
        with:
          python-version: "3.14"
          cache: pip

      - name: Install dependencies
        run: pip install -r requirements.txt -r requirements-dev.txt

      - name: Run static checks
        run: |
          python -m compileall -q src tests
          ruff check src tests
          pip check

      - name: Run unit tests
        run: python -m unittest discover -s tests -v

      - name: Audit Python dependencies
        run: pip-audit -r requirements.txt

  build-and-push:
    needs: validate
    runs-on: ubuntu-latest
    permissions:
      contents: read
      packages: write
    steps:
      - name: Checkout repository
        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
        with:
          fetch-depth: 0

      - name: Set up QEMU
        uses: docker/setup-qemu-action@96fe6ef7f33517b61c61be40b68a1882f3264fb8 # v4

      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4

      - name: Log in to Docker Hub
        if: github.event_name != 'pull_request'
        uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f # v4
        with:
          username: ${{ secrets.DOCKERHUB_USERNAME }}
          password: ${{ secrets.DOCKERHUB_TOKEN }}

      - name: Log in to GitHub Container Registry
        if: github.event_name != 'pull_request'
        uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f # v4
        with:
          registry: ghcr.io
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}

      - name: Verify publish source
        if: github.event_name != 'pull_request'
        shell: bash
        env:
          EXPECTED_SHA: ${{ github.sha }}
        run: |
          set -euo pipefail
          case "$GITHUB_REF" in
            refs/heads/master)
              remote_sha="$(git ls-remote origin refs/heads/master | awk '{print $1}')"
              test -n "$remote_sha"
              if [[ "$remote_sha" != "$EXPECTED_SHA" ]]; then
                echo "refusing to publish stale source: expected $EXPECTED_SHA, master is $remote_sha" >&2
                exit 1
              fi
              ;;
            refs/tags/v*)
              if [[ ! "$GITHUB_REF_NAME" =~ ^v[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
                echo "release tags must use vMAJOR.MINOR.PATCH" >&2
                exit 1
              fi
              remote_sha="$(git ls-remote origin "refs/tags/${GITHUB_REF_NAME}^{}" | awk '{print $1}')"
              if [[ -z "$remote_sha" ]]; then
                remote_sha="$(git ls-remote origin "refs/tags/${GITHUB_REF_NAME}" | awk '{print $1}')"
              fi
              if [[ "$remote_sha" != "$EXPECTED_SHA" ]]; then
                echo "refusing to publish mismatched tag: expected $EXPECTED_SHA, tag resolves to $remote_sha" >&2
                exit 1
              fi
              ;;
            *)
              echo "publishing is limited to master and vMAJOR.MINOR.PATCH tags" >&2
              exit 1
              ;;
          esac

      - name: Extract image metadata
        id: meta
        uses: docker/metadata-action@dc802804100637a589fabce1cb79ff13a1411302 # v6
        with:
          images: |
            ${{ env.DOCKERHUB_IMAGE }}
            ${{ env.GHCR_IMAGE }}
          flavor: latest=false
          tags: |
            type=raw,value=latest,enable=${{ github.ref == 'refs/heads/master' }}
            type=semver,pattern={{version}},enable=${{ startsWith(github.ref, 'refs/tags/v') }}
          labels: |
            org.opencontainers.image.title=Rule Bot
            org.opencontainers.image.description=Telegram bot for rule management
            org.opencontainers.image.vendor=AetherSailor
            org.opencontainers.image.source=${{ github.server_url }}/${{ github.repository }}
            org.opencontainers.image.revision=${{ github.sha }}

      - name: Build and optionally publish multi-arch image
        uses: docker/build-push-action@53b7df96c91f9c12dcc8a07bcb9ccacbed38856a # v7
        with:
          context: .
          platforms: linux/amd64,linux/arm64
          push: ${{ github.event_name != 'pull_request' }}
          tags: ${{ steps.meta.outputs.tags }}
          labels: ${{ steps.meta.outputs.labels }}
          cache-from: type=gha
          cache-to: type=gha,mode=max
          provenance: mode=max
          sbom: true

      - name: Smoke test both published architectures
        if: github.event_name != 'pull_request'
        shell: bash
        env:
          PUBLISHED_TAGS: ${{ steps.meta.outputs.tags }}
        run: |
          set -euo pipefail
          image="$(sed -n '1p' <<<"$PUBLISHED_TAGS")"
          test -n "$image"
          for platform in linux/amd64 linux/arm64; do
            docker run --rm --pull always --platform "$platform" \
              --entrypoint python "$image" \
              -c 'import aiohttp, github, maxminddb, telegram; import src.main'
          done

      - name: Verify published images
        if: github.event_name != 'pull_request'
        shell: bash
        env:
          EXPECTED_SHA: ${{ github.sha }}
          PUBLISHED_TAGS: ${{ steps.meta.outputs.tags }}
        run: |
          set -euo pipefail
          expected_index_digest=""
          while IFS= read -r image; do
            [[ -n "$image" ]] || continue
            published=false
            for attempt in {1..12}; do
              manifest="$(docker buildx imagetools inspect "$image" \
                --format '{{json .Manifest}}' 2>/dev/null || true)"
              if jq -e '
                ([.manifests[]?.platform | select(.os == "linux") | .architecture] | index("amd64")) != null
                and
                ([.manifests[]?.platform | select(.os == "linux") | .architecture] | index("arm64")) != null
              ' <<<"$manifest" >/dev/null 2>&1; then
                verified=true
                for arch in amd64 arm64; do
                  repository="${image%:*}"
                  digest="$(jq -er --arg arch "$arch" '
                    .manifests[]
                    | select(.platform.os == "linux" and .platform.architecture == $arch)
                    | .digest
                  ' <<<"$manifest")"
                  image_config="$(docker buildx imagetools inspect \
                    "${repository}@${digest}" --format '{{json .Image}}')"
                  revision="$(jq -r '.config.Labels["org.opencontainers.image.revision"] // empty' \
                    <<<"$image_config")"
                  if [[ "$revision" != "$EXPECTED_SHA" ]]; then
                    verified=false
                    break
                  fi
                  if jq -e '
                    any(.history[]?; (.created_by // "") | contains("COPY /wheels"))
                  ' <<<"$image_config" >/dev/null; then
                    echo "$repository@$digest contains a copied wheelhouse layer" >&2
                    exit 1
                  fi
                  platform_manifest="$(docker buildx imagetools inspect \
                    "${repository}@${digest}" --raw)"
                  compressed_size="$(jq -er '[.layers[].size] | add' \
                    <<<"$platform_manifest")"
                  if (( compressed_size > MAX_COMPRESSED_PLATFORM_SIZE )); then
                    echo "$repository@$digest is $compressed_size bytes; limit is $MAX_COMPRESSED_PLATFORM_SIZE" >&2
                    exit 1
                  fi
                  echo "$repository@$digest compressed size: $compressed_size bytes"
                done
                if [[ "$verified" == true ]]; then
                  raw_manifest="$(docker buildx imagetools inspect "$image" --raw)"
                  index_digest="sha256:$(printf '%s' "$raw_manifest" | sha256sum | awk '{print $1}')"
                  if [[ -z "$expected_index_digest" ]]; then
                    expected_index_digest="$index_digest"
                  elif [[ "$index_digest" != "$expected_index_digest" ]]; then
                    echo "registry digest mismatch for $image: $index_digest != $expected_index_digest" >&2
                    exit 1
                  fi
                  published=true
                  break
                fi
              fi
              sleep 10
            done
            if [[ "$published" != true ]]; then
              echo "$image does not contain verified amd64/arm64 images for $EXPECTED_SHA" >&2
              exit 1
            fi
          done <<<"$PUBLISHED_TAGS"
          test -n "$expected_index_digest"

      - name: Remove obsolete Docker Hub tags
        if: github.event_name != 'pull_request'
        shell: bash
        env:
          DOCKERHUB_USERNAME: ${{ secrets.DOCKERHUB_USERNAME }}
          DOCKERHUB_TOKEN: ${{ secrets.DOCKERHUB_TOKEN }}
        run: |
          set -euo pipefail
          payload="$(jq -n \
            --arg username "$DOCKERHUB_USERNAME" \
            --arg password "$DOCKERHUB_TOKEN" \
            '{username: $username, password: $password}')"
          jwt="$(curl --fail --silent --show-error \
            -H 'Content-Type: application/json' \
            -d "$payload" \
            https://hub.docker.com/v2/users/login/ | jq -er '.token // .access_token')"
          tags_url='https://hub.docker.com/v2/repositories/aethersailor/rule-bot/tags?page_size=100'
          tags="$(curl --fail --silent --show-error \
            -H "Authorization: JWT $jwt" \
            "$tags_url" | jq -r '.results[].name')"
          while IFS= read -r tag; do
            if [[ -n "$tag" && "$tag" != "latest" \
              && ! "$tag" =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
              curl --fail --silent --show-error -X DELETE \
                -H "Authorization: JWT $jwt" \
                "https://hub.docker.com/v2/repositories/aethersailor/rule-bot/tags/$tag/"
            fi
          done <<<"$tags"
          for attempt in {1..12}; do
            remaining="$(curl --fail --silent --show-error \
              -H 'Cache-Control: no-cache' \
              -H "Authorization: JWT $jwt" \
              "$tags_url")"
            if jq -e '[.results[].name | select(
              . != "latest" and (test("^[0-9]+\\.[0-9]+\\.[0-9]+$") | not)
            )] | length == 0' \
              <<<"$remaining" >/dev/null; then
              break
            fi
            sleep 10
          done
          if ! jq -e '[.results[].name | select(
            . != "latest" and (test("^[0-9]+\\.[0-9]+\\.[0-9]+$") | not)
          )] | length == 0' <<<"$remaining" >/dev/null; then
            echo "Docker Hub still contains obsolete tags" >&2
            exit 1
          fi

      - name: Remove unreferenced GHCR versions
        if: github.event_name != 'pull_request'
        shell: bash
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: |
          set -euo pipefail
          package="rule-bot"
          versions_api="/users/${GITHUB_REPOSITORY_OWNER}/packages/container/${package}/versions?per_page=100"
          versions="$(gh api --paginate --slurp "$versions_api" | jq 'add')"
          tagged_roots="$(mktemp)"
          protected="$(mktemp)"
          jq -r '.[] | select((.metadata.container.tags // []) | length > 0) | .name' \
            <<<"$versions" >"$tagged_roots"
          cp "$tagged_roots" "$protected"

          while IFS= read -r root_digest; do
            [[ -n "$root_digest" ]] || continue
            docker buildx imagetools inspect "${GHCR_IMAGE}@${root_digest}" \
              --format '{{json .Manifest}}' \
              | jq -r '.manifests[]?.digest' >>"$protected"
          done <"$tagged_roots"
          sort -u -o "$protected" "$protected"

          mapfile -t obsolete_ids < <(jq -r --rawfile protected "$protected" '
            ($protected | split("\n") | map(select(length > 0))) as $protected_digests
            | .[]
            | select(((.metadata.container.tags // []) | length) == 0)
            | .name as $digest
            | select(($protected_digests | index($digest)) == null)
            | .id
          ' <<<"$versions")
          for version_id in "${obsolete_ids[@]}"; do
            gh api --method DELETE \
              "/users/${GITHUB_REPOSITORY_OWNER}/packages/container/${package}/versions/${version_id}"
          done

          for attempt in {1..12}; do
            remaining_ids="$(gh api --paginate --slurp "$versions_api" \
              | jq -r 'add[] | .id')"
            stale=false
            for version_id in "${obsolete_ids[@]}"; do
              if grep -Fxq "$version_id" <<<"$remaining_ids"; then
                stale=true
                break
              fi
            done
            if [[ "$stale" == false ]]; then
              exit 0
            fi
            sleep 10
          done
          echo "GHCR still contains unreferenced package versions" >&2
          exit 1