ArchiveBox/.github/workflows/docker.yml

name: Build Docker image

on:
  workflow_dispatch:
  workflow_call:
  push:
    branches:
      - dev
    tags:
      - 'v*'
  # pull_request:

env:
  DOCKERHUB_IMAGE: archivebox/archivebox
  GHCR_IMAGE: ghcr.io/archivebox/archivebox

permissions:
  contents: read
  packages: write

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

jobs:
  build:
    name: build ${{ matrix.platform }}
    runs-on: ${{ matrix.runner }}
    strategy:
      fail-fast: false
      matrix:
        include:
          - platform: linux/amd64
            runner: ubuntu-24.04
            cache_scope: docker-amd64
            artifact_name: digest-linux-amd64
          - platform: linux/arm64
            runner: ubuntu-24.04-arm
            cache_scope: docker-arm64
            artifact_name: digest-linux-arm64
    steps:
      - name: Checkout
        uses: actions/checkout@v4
        # with:
        #   submodules: true
        #   fetch-depth: 1

      - name: Set up Docker Buildx
        id: buildx
        uses: docker/setup-buildx-action@v3
        with:
          version: latest
          install: true

      - name: Builder instance name
        run: echo ${{ steps.buildx.outputs.name }}

      - name: Available platforms
        run: echo ${{ steps.buildx.outputs.platforms }}

      - name: Login to Docker Hub
        uses: docker/login-action@v3
        if: github.event_name != 'pull_request'
        with:
          username: ${{ secrets.DOCKER_USERNAME }}
          password: ${{ secrets.DOCKER_PASSWORD }}

      - name: Login to GitHub Container Registry
        uses: docker/login-action@v3
        with:
          registry: ghcr.io
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}

      - name: Collect Docker labels
        id: docker_meta
        shell: bash
        run: |
          set -Eeuo pipefail
          VERSION="$(python3 - <<'PY'
          from pathlib import Path
          import re

          match = re.search(r'^version = "([^"]+)"$', Path("pyproject.toml").read_text(), re.MULTILINE)
          if not match:
              raise SystemExit("Failed to read version from pyproject.toml")
          print(match.group(1))
          PY
          )"

          {
            echo 'labels<<EOF'
            echo "org.opencontainers.image.version=${VERSION}"
            echo "org.opencontainers.image.revision=${GITHUB_SHA}"
            echo 'org.opencontainers.image.source=https://github.com/ArchiveBox/ArchiveBox'
            echo 'EOF'
            echo "version=${VERSION}"
          } >> "$GITHUB_OUTPUT"

          echo "[+] Building ${{ matrix.platform }} for ${VERSION}"          

      - name: Build and push digest
        id: docker_build
        uses: docker/build-push-action@v6
        with:
          context: ./
          file: ./Dockerfile
          builder: ${{ steps.buildx.outputs.name }}
          push: ${{ github.event_name != 'pull_request' }}
          tags: |
            ${{ env.DOCKERHUB_IMAGE }}
            ${{ env.GHCR_IMAGE }}            
          labels: ${{ steps.docker_meta.outputs.labels }}
          cache-from: type=gha,scope=${{ matrix.cache_scope }}
          cache-to: type=gha,mode=max,scope=${{ matrix.cache_scope }}
          platforms: ${{ matrix.platform }}
          outputs: type=image,push-by-digest=true,name-canonical=true,push=true

      - name: Image digest
        run: echo ${{ steps.docker_build.outputs.digest }}

      - name: Export digest
        shell: bash
        run: |
          set -Eeuo pipefail
          mkdir -p /tmp/digests
          digest="${{ steps.docker_build.outputs.digest }}"
          touch "/tmp/digests/${digest#sha256:}"          

      - name: Upload digest
        uses: actions/upload-artifact@v4
        with:
          name: ${{ matrix.artifact_name }}
          path: /tmp/digests/*
          if-no-files-found: error
          retention-days: 1

  publish:
    name: publish multiarch tags
    runs-on: ubuntu-24.04
    needs:
      - build
    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@v3
        with:
          version: latest
          install: true

      - name: Login to Docker Hub
        uses: docker/login-action@v3
        if: github.event_name != 'pull_request'
        with:
          username: ${{ secrets.DOCKER_USERNAME }}
          password: ${{ secrets.DOCKER_PASSWORD }}

      - name: Login to GitHub Container Registry
        uses: docker/login-action@v3
        with:
          registry: ghcr.io
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}

      - name: Download digests
        uses: actions/download-artifact@v4
        with:
          path: /tmp/digests
          pattern: digest-*
          merge-multiple: true

      - name: Collect Docker tags
        id: docker_meta
        shell: bash
        run: |
          set -Eeuo pipefail
          VERSION="$(python3 - <<'PY'
          from pathlib import Path
          import re

          match = re.search(r'^version = "([^"]+)"$', Path("pyproject.toml").read_text(), re.MULTILINE)
          if not match:
              raise SystemExit("Failed to read version from pyproject.toml")
          print(match.group(1))
          PY
          )"
          SHORT_SHA="${GITHUB_SHA::8}"

          {
            echo 'dockerhub_tags<<EOF'
            echo "${DOCKERHUB_IMAGE}:dev"
            echo "${DOCKERHUB_IMAGE}:${VERSION}"
            echo "${DOCKERHUB_IMAGE}:sha-${SHORT_SHA}"
            echo 'EOF'
            echo 'ghcr_tags<<EOF'
            echo "${GHCR_IMAGE}:dev"
            echo "${GHCR_IMAGE}:${VERSION}"
            echo "${GHCR_IMAGE}:sha-${SHORT_SHA}"
            echo 'EOF'
            echo "version=${VERSION}"
            echo "short_sha=${SHORT_SHA}"
          } >> "$GITHUB_OUTPUT"

          echo "[+] Publishing Docker Hub tags:"
          printf '%s\n' "${DOCKERHUB_IMAGE}:dev" "${DOCKERHUB_IMAGE}:${VERSION}" "${DOCKERHUB_IMAGE}:sha-${SHORT_SHA}"
          echo "[+] Publishing GHCR tags:"
          printf '%s\n' "${GHCR_IMAGE}:dev" "${GHCR_IMAGE}:${VERSION}" "${GHCR_IMAGE}:sha-${SHORT_SHA}"          

      - name: Create Docker Hub manifest
        shell: bash
        run: |
          set -Eeuo pipefail
          mapfile -t DIGESTS < <(find /tmp/digests -maxdepth 1 -type f -printf '%f\n' | sort)
          [[ "${#DIGESTS[@]}" -gt 0 ]]

          TAG_ARGS=()
          while IFS= read -r tag; do
            [[ -n "$tag" ]] && TAG_ARGS+=(--tag "$tag")
          done <<< "${{ steps.docker_meta.outputs.dockerhub_tags }}"

          REFS=()
          for digest in "${DIGESTS[@]}"; do
            REFS+=("${DOCKERHUB_IMAGE}@sha256:${digest}")
          done

          docker buildx imagetools create "${TAG_ARGS[@]}" "${REFS[@]}"          

      - name: Create GHCR manifest
        shell: bash
        run: |
          set -Eeuo pipefail
          mapfile -t DIGESTS < <(find /tmp/digests -maxdepth 1 -type f -printf '%f\n' | sort)
          [[ "${#DIGESTS[@]}" -gt 0 ]]

          TAG_ARGS=()
          while IFS= read -r tag; do
            [[ -n "$tag" ]] && TAG_ARGS+=(--tag "$tag")
          done <<< "${{ steps.docker_meta.outputs.ghcr_tags }}"

          REFS=()
          for digest in "${DIGESTS[@]}"; do
            REFS+=("${GHCR_IMAGE}@sha256:${digest}")
          done

          docker buildx imagetools create "${TAG_ARGS[@]}" "${REFS[@]}"          

      - name: Inspect published images
        shell: bash
        run: |
          set -Eeuo pipefail
          docker buildx imagetools inspect "${DOCKERHUB_IMAGE}:sha-${{ steps.docker_meta.outputs.short_sha }}"
          docker buildx imagetools inspect "${GHCR_IMAGE}:sha-${{ steps.docker_meta.outputs.short_sha }}"          

      - name: Update README
        uses: peter-evans/dockerhub-description@v4
        with:
          username: ${{ secrets.DOCKER_USERNAME }}
          password: ${{ secrets.DOCKER_PASSWORD }}
          repository: archivebox/archivebox