build.yml

name: "Build and Push"

on:
  push:
    branches:
      - master

jobs:
  build-image:
    name: Build image
    needs: calculate_matrix
    runs-on: ubuntu-latest
    timeout-minutes: 30
    strategy:
      fail-fast: false
      matrix: ${{fromJSON(needs.calculate_matrix.outputs.matrix)}}
    env:
      IMAGE_NAME: heartexlabs/label-studio-ml-backend
      examples_dir: label_studio_ml/examples
      backend_dir_name: ${{ matrix.ml_backend.backend_dir_name }}
      backend_tag_prefix: ${{ matrix.ml_backend.backend_tag_prefix }}
    steps:
      - uses: hmarr/debug-action@v3.0.0

      - name: Free Disk Space (Ubuntu)
        uses: jlumbroso/free-disk-space@main
        with:
          # this might remove tools that are actually needed,
          # if set to "true" but frees about 6 GB
          tool-cache: false
          # all of these default to true, but feel free to set to
          # "false" if necessary for your workflow
          android: true
          dotnet: true
          haskell: true
          large-packages: true
          docker-images: true
          swap-storage: true

      - uses: actions/checkout@v4
        with:
          ref: "${{ env.GITHUB_SHA }}"
          fetch-depth: 0

      - name: Calculate version
        id: version
        env:
          BRANCH_NAME: "${{ github.event.pull_request.head.ref || github.ref_name }}"
          PREFIX: "${{ env.backend_tag_prefix }}"
        run: |
          set -xueo pipefail
          MAX_TAG_LENGTH=50
          pretty_branch_name="$(echo -n "${BRANCH_NAME#refs/heads/}" | sed 's#/#-#g' | sed 's#_#-#g'| sed 's#\.#-#g' | tr '[:upper:]' '[:lower:]')"
          echo "pretty_branch_name=$pretty_branch_name" >> $GITHUB_OUTPUT
          timestamp="$(date +'%Y%m%d.%H%M%S')"
          echo "timestamp=$timestamp" >> $GITHUB_OUTPUT
          short_sha="$(git rev-parse --short HEAD)"
          echo "short_sha=$short_sha" >> $GITHUB_OUTPUT
          long_sha="$(git rev-parse HEAD)"
          echo "sha=$long_sha" >> $GITHUB_OUTPUT
          short_sha_length="$(echo $short_sha | awk '{print length}')"
          timestamp_length="$(echo $timestamp | awk '{print length}')"
          prefix_length="$(echo $PREFIX | awk '{print length}')"
          short_branch="$(echo $pretty_branch_name | cut -c1-$((MAX_TAG_LENGTH - 2 - short_sha_length - timestamp_length - prefix_length)))"
          echo "short_branch=$short_branch" >> $GITHUB_OUTPUT
          image_version="${PREFIX}${timestamp}-${short_branch}-${short_sha}"
          echo "image_version=$image_version" >> $GITHUB_OUTPUT
          image_branch_version="${PREFIX}${short_branch}"
          echo "image_branch_version=$image_branch_version" >> $GITHUB_OUTPUT

      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@v3.3.0

      - name: Login to DockerHub
        if: ${{ !github.event.pull_request.head.repo.fork }}
        uses: docker/login-action@v3.2.0
        with:
          username: ${{ vars.DOCKERHUB_USERNAME }}
          password: ${{ secrets.DOCKERHUB_TOKEN }}

      - name: Calculate Docker tags
        id: calculate-docker-tags
        uses: actions/github-script@v7
        env:
          IMAGE_NAME: "${{ env.IMAGE_NAME }}"
          TAGS: "${{ steps.version.outputs.image_version }},${{ steps.version.outputs.image_branch_version }},latest"
        with:
          script: |
            const raw_tags_input = process.env.TAGS;
            const image_name = process.env.IMAGE_NAME;
            
            const tags = raw_tags_input
              .split(',')
              .map(x => x.trim())
              .map(x => `${image_name}:${x}`)
              .join(',');
            core.notice(`tags='${tags}'`)
            core.setOutput("tags", tags);


      - name: Push Docker image
        uses: docker/build-push-action@v5.4.0
        id: docker_build_and_push
        with:
          context: "${{ env.examples_dir }}/${{ env.backend_dir_name }}"
          push: true
          tags: "${{ steps.calculate-docker-tags.outputs.tags }}"
          cache-from: type=gha
          cache-to: type=gha,mode=max

  calculate_matrix:
    name: "Calculate build matrix"
    runs-on: ubuntu-latest
    outputs:
      matrix: ${{ steps.set-matrix.outputs.matrix }}
    steps:
      - uses: hmarr/debug-action@v3.0.0

      - name: Checkout
        uses: actions/checkout@v4
        with:
          ref: "${{ env.GITHUB_SHA }}"
          fetch-depth: 2

      - name: Build matrix
        id: set-matrix
        shell: bash
        env:
          BASE_SHA: ${{ github.event.pull_request.base.sha || github.event.before }}
          CONFIG: .github/docker-build-config.yml
        run: |
          set -xuo pipefail
          set +e
          CHANGED=$(git diff --name-only $BASE_SHA ${{ github.sha }} -- label_studio_ml/ | xargs -L1 dirname | uniq | cut -d'/' -f2-)
          CHANGED_EXAMPLES=$(echo "$CHANGED" | grep examples )
          set -e
          echo "Finding examples to test"
          if [[ $(echo "$CHANGED" | grep -c -v ^$) == 0 ]]; then
            echo "matrix={\"ml_backend\":[]}" >> $GITHUB_OUTPUT
          else
            ALL_EXAMPLES=$(ls -1d label_studio_ml/examples/*/ | cut -d'/' -f3- | cut -d'/' -f1)
            echo "Reading configuration from $CONFIG"
            MATRIX="{\"ml_backend\": ["
            while IFS= read -r line; do
              FOLDER=$(echo $line | awk '{print $1}')
              TAG_PREFIX=$(echo $line | awk '{print $2}')
              if egrep -q $FOLDER <<< "${CHANGED_EXAMPLES}"; then
                MATRIX+="{\"backend_dir_name\":\"$FOLDER\", \"backend_tag_prefix\":\"$TAG_PREFIX\"},"
              fi
            done < <(yq '.[] | .backend_dir_name + " " + .backend_tag_prefix' $CONFIG)
            MATRIX=$(echo "$MATRIX" | sed 's/,$//')
            MATRIX+="]}"
            echo "matrix=$MATRIX" >> $GITHUB_OUTPUT
          fi