j40-cejst-2/.github/workflows/deploy_backend_main.yml

name: Deploy Backend Main
on:
  push:
    branches: [main]
    paths:
      - "data/**"
      - ".github/workflows/deploy_backend_main.yml"
concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true
env:
  CENSUS_API_KEY: ${{ secrets.CENSUS_API_KEY }}
  J40_VERSION_LABEL_STRING: ${{ vars.SCORE_VERSION }}

jobs:
  generate-score-tiles:
    runs-on: ubuntu-latest
    defaults:
      run:
        working-directory: data/data-pipeline
    strategy:
      matrix:
        python-version: ['3.10']
    environment: Staging
    steps:
      - name: Checkout source
        uses: actions/checkout@v4
      - name: Print variables to help debug
        uses: hmarr/debug-action@v3
      - name: Set up Python ${{ matrix.python-version }}
        uses: actions/setup-python@v5
        with:
          python-version: ${{ matrix.python-version }}
      - name: Load cached Poetry installation
        id: cached-poetry-dependencies
        uses: actions/cache@v4
        with:
          path: ~/.cache/pypoetry/virtualenvs
          key: env-${{ runner.os }}-${{ matrix.python-version }}-${{ hashFiles('**/poetry.lock') }}-${{ hashFiles('.github/workflows/deploy_backend_main.yml') }}
      - name: Install poetry
        uses: snok/install-poetry@v1
      - name: Print Poetry settings
        run: poetry show -v
      - name: Install dependencies
        run: poetry add s4cmd && poetry install
        if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
      - name: Configure AWS Credentials
        uses: aws-actions/configure-aws-credentials@v4
        with:
          aws-access-key-id: ${{ secrets.DATA_DEV_AWS_ACCESS_KEY_ID }}
          aws-secret-access-key: ${{ secrets.DATA_DEV_AWS_SECRET_ACCESS_KEY }}
          aws-region: us-east-1
      - name: Cleanup Data
        run: |
          poetry run python3 -m data_pipeline.application data-cleanup
      - name: Cache Census Data
        id: cache-census
        uses: actions/cache@v4
        with:
          path: data/data-pipeline/data_pipeline/data/census
          key: data-census
      - name: Get Census Data
        if: steps.cache-census.outputs.cache-hit != 'true'
        run: |
          poetry run python3 -m data_pipeline.application census-data-download
      - name: Run ETL
        run: |
          poetry run python3 -m data_pipeline.application etl-run
      - name: Generate Score
        run: |
          poetry run python3 -m data_pipeline.application score-run
      - name: Score Compare
        run: |
          poetry run python3 -m data_pipeline.comparator compare-score
      - name: Generate Score Post
        run: |
          poetry run python3 -m data_pipeline.application generate-score-post
      - name: Confirm we generated the version of the score we think we did
        if: ${{ env.J40_VERSION_LABEL_STRING == '2.0' || env.J40_VERSION_LABEL_STRING == 'beta' }}
        run: |
          grep -v "Identified as disadvantaged due to tribal overlap" data_pipeline/data/score/downloadable/* > /dev/null
      - name: Generate Score Geo
        run: |
          poetry run python3 -m data_pipeline.application geo-score
      - name: Set timezone for tippecanoe
        uses: szenius/set-timezone@v2.0
        with:
          timezoneLinux: "America/Los_Angeles"
      - name: Get tippecanoe
        run: |
          sudo apt-get install -y software-properties-common libsqlite3-dev zlib1g-dev
          sudo apt-add-repository -y ppa:git-core/ppa
          sudo mkdir -p /tmp/tippecanoe-src
          sudo git clone https://github.com/mapbox/tippecanoe.git /tmp/tippecanoe-src
      - name: Make tippecanoe
        working-directory: /tmp/tippecanoe-src
        run: |
          sudo /usr/bin/bash -c make
          mkdir -p /usr/local/bin
          cp tippecanoe /usr/local/bin/tippecanoe
          tippecanoe -v
      - name: Generate Tiles
        run: |
          poetry run python3 -m data_pipeline.application generate-map-tiles
          poetry run python3 -m data_pipeline.application generate-map-tiles --generate-tribal-layer
      - name: Deploy Score and Map to Geoplatform AWS
        if: ${{ env.J40_VERSION_LABEL_STRING == '2.0' }}
        run: |
          poetry run s4cmd put ./data_pipeline/data/score/* s3://${{secrets.S3_DATA_BUCKET}}/data-versions/${{env.J40_VERSION_LABEL_STRING}}/data/score/ --recursive --force --API-ACL=public-read --num-threads=250
          poetry run s4cmd put ./data_pipeline/files/* s3://${{secrets.S3_DATA_BUCKET}}/data-versions/${{env.J40_VERSION_LABEL_STRING}}/data/score/downloadable/ --recursive --force --API-ACL=public-read
          poetry run s4cmd put ./data_pipeline/data/tribal/* s3://${{secrets.S3_DATA_BUCKET}}/data-versions/${{env.J40_VERSION_LABEL_STRING}}/data/tribal/ --recursive --force --API-ACL=public-read --num-threads=250
      - name: 2.0 Post-deploy Score Check
        run: |
          curl "${{secrets.DATA_URL}}/data-versions/2.0/data/score/downloadable/2.0-data-documentation.zip" -s -f -I -o /dev/null && \
          curl "${{secrets.DATA_URL}}/data-versions/2.0/data/score/downloadable/2.0-shapefile-codebook.zip" -s -f -I -o /dev/null
          curl "${{secrets.DATA_URL}}/data-versions/2.0/data/score/downloadable/2.0-communities.xlsx" -s -f -I -o /dev/null && \
          curl "${{secrets.DATA_URL}}/data-versions/2.0/data/score/downloadable/2.0-communities.csv" -s -f -I -o /dev/null && \
          curl "${{secrets.DATA_URL}}/data-versions/2.0/data/score/downloadable/cejst-technical-support-document.pdf" -s -f -I -o /dev/null && \
          curl "${{secrets.DATA_URL}}/data-versions/2.0/data/score/downloadable/draft-communities-list.pdf" -s -f -I -o /dev/null
      - name: Invalidate cache on AWS CDN
        uses: chetan/invalidate-cloudfront-action@master
        env:
          DISTRIBUTION: ${{secrets.DATA_CDN_ID}}
          PATHS: "/*"
          AWS_REGION: "us-east-1"
          AWS_ACCESS_KEY_ID: ${{ secrets.DATA_DEV_AWS_ACCESS_KEY_ID }}
          AWS_SECRET_ACCESS_KEY: ${{ secrets.DATA_DEV_AWS_SECRET_ACCESS_KEY }}