From a38caf7b75b949643629924dc8c317d9b9e4c36c Mon Sep 17 00:00:00 2001
From: ericiwamoto <100735505+ericiwamoto@users.noreply.github.com>
Date: Thu, 5 Dec 2024 08:54:40 -0800
Subject: [PATCH] Add PR build checks, disable deploy concurrency

---
 .github/workflows/deploy_backend_main.yml  |  25 ++++-
 .github/workflows/deploy_frontend_main.yml |   3 +
 .github/workflows/pr_backend.yml           | 103 +++++++++++++++++++++
 .github/workflows/pr_frontend.yml          |  44 +++++++++
 4 files changed, 170 insertions(+), 5 deletions(-)
 create mode 100644 .github/workflows/pr_backend.yml
 create mode 100644 .github/workflows/pr_frontend.yml

diff --git a/.github/workflows/deploy_backend_main.yml b/.github/workflows/deploy_backend_main.yml
index 1a420687..a3be4576 100644
--- a/.github/workflows/deploy_backend_main.yml
+++ b/.github/workflows/deploy_backend_main.yml
@@ -4,6 +4,9 @@ on:
     branches: [main]
     paths:
       - "data/**"
+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 }}
@@ -51,15 +54,27 @@ jobs:
           sudo apt-get update
           sudo apt-get -y install gdal-bin
           ogrinfo --version
+      - name: Cleanup Data
+        run: |
+          poetry run python3 -m data_pipeline.application data-cleanup
       - name: Get Census Data
         run: |
-          poetry run python3 data_pipeline/application.py pull-census-data -s aws
+          poetry run python3 -m data_pipeline.application census-data-download
+          - name: Extract Data Sources
+          run: |
+            poetry run python3 -m data_pipeline.application extract-data-sources
+      - name: Run ETL
+        run: |
+            poetry run python3 -m data_pipeline.application etl-run
       - name: Generate Score
         run: |
-          poetry run python3 data_pipeline/application.py score-full-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 data_pipeline/application.py generate-score-post -s aws
+          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 == '1.0' || env.J40_VERSION_LABEL_STRING == 'test' }}
         run: |
@@ -70,7 +85,7 @@ jobs:
           grep -v "Identified as disadvantaged due to tribal overlap" data_pipeline/data/score/downloadable/* > /dev/null
       - name: Generate Score Geo
         run: |
-          poetry run python3 data_pipeline/application.py geo-score
+          poetry run python3 -m data_pipeline.application geo-score
       - name: Run smoketest for 1.0
         if: ${{ env.J40_VERSION_LABEL_STRING == '1.0' }}
         run: |
@@ -116,7 +131,7 @@ jobs:
           tippecanoe -v
       - name: Generate Tiles
         run: |
-          poetry run python3 data_pipeline/application.py generate-map-tiles
+          poetry run python3 -m data_pipeline.application generate-map-tiles
       - name: Deploy Map to Geoplatform AWS
         run: |
           poetry run s4cmd put ./data_pipeline/data/score/geojson/ s3://${{secrets.S3_DATA_BUCKET}}/data-versions/${{env.J40_VERSION_LABEL_STRING}}/data/score/geojson --sync-check --recursive --force --delete-removed --num-threads=250
diff --git a/.github/workflows/deploy_frontend_main.yml b/.github/workflows/deploy_frontend_main.yml
index 662edeaa..c94a3c15 100644
--- a/.github/workflows/deploy_frontend_main.yml
+++ b/.github/workflows/deploy_frontend_main.yml
@@ -4,6 +4,9 @@ on:
     branches: [main]
     paths:
       - "client/**/*"
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
 jobs:
   build:
     runs-on: ubuntu-latest
diff --git a/.github/workflows/pr_backend.yml b/.github/workflows/pr_backend.yml
new file mode 100644
index 00000000..f7a13009
--- /dev/null
+++ b/.github/workflows/pr_backend.yml
@@ -0,0 +1,103 @@
+name: Pull Request Backend 
+on:
+  pull_request:
+    paths:
+      - "data/**"
+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: Install GDAL/ogr2ogr
+        run: |
+          sudo apt-get update
+          sudo apt-get -y install gdal-bin
+          ogrinfo --version
+      - name: Cleanup Data
+        run: |
+          poetry run python3 -m data_pipeline.application data-cleanup
+      - name: Get Census Data
+        run: |
+          poetry run python3 -m data_pipeline.application census-data-download
+      - name: Extract Data Sources
+        run: |
+          poetry run python3 -m data_pipeline.application extract-data-sources
+      - 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 == '1.0' || env.J40_VERSION_LABEL_STRING == 'test' }}
+        run: |
+          grep "Identified as disadvantaged due to tribal overlap" data_pipeline/data/score/downloadable/* > /dev/null
+      - 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: Run smoketest for 1.0
+        if: ${{ env.J40_VERSION_LABEL_STRING == '1.0' }}
+        run: |
+          poetry run pytest data_pipeline/ -m smoketest
+      - 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
+
diff --git a/.github/workflows/pr_frontend.yml b/.github/workflows/pr_frontend.yml
new file mode 100644
index 00000000..4b7fb3a0
--- /dev/null
+++ b/.github/workflows/pr_frontend.yml
@@ -0,0 +1,44 @@
+name: Pull Request Frontend
+on:
+  push:
+    branches: [main]
+    paths:
+      - "client/**/*"
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    environment: Staging
+    defaults:
+      run:
+        working-directory: client
+    strategy:
+      matrix:
+        node-version: [14.x]
+    steps:
+      - uses: actions/checkout@v4
+      - name: Use Node.js ${{ matrix.node-version }}
+        uses: actions/setup-node@v2
+        with:
+          node-version: ${{ matrix.node-version }}
+      - name: Install
+        run: npm ci
+      - name: Build
+        run: npm run build --if-present
+        env:
+          # See the client readme for more info on environment variables:
+          # https://github.com/usds/justice40-tool/blob/main/client/README.md
+          DATA_SOURCE: cdn
+          # TODO: Update main URL when either is back up
+          SITE_URL: "${{ secrets.SITE_URL }}"
+          MAPBOX_STYLES_READ_TOKEN: "${{ secrets.MAPBOX_STYLES_READ_TOKEN }}"
+      - name: Get directory contents
+        run: ls -la public
+      - name: Lint
+        run: npm run lint
+        # Disabling for now due to jsonlint - TODO: put this back
+      # - name: License Check
+      #   run: npm run licenses
+      - name: Test
+        run: npm test
+      # - name: Check for security vulnerabilities
+      #   run: npm audit --production
\ No newline at end of file