Skip to content

Add workflow to gen data (#329) #119

Add workflow to gen data (#329)

Add workflow to gen data (#329) #119

Workflow file for this run

name: "Generate Website Data"
on:
workflow_dispatch:
push:
env:
POSTGRES_USER: app_user
POSTGRES_DB: disclosure-backend
POSTGRES_PASSWORD: app_password
jobs:
build:
runs-on: ubuntu-latest
outputs:
devcontainer: ${{ steps.filter.outputs.devcontainer }}
noncontainer: ${{ steps.filter.outputs.noncontainer }}
steps:
- name: Login to GitHub Container Registry
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{github.actor}}
password: ${{secrets.GITHUB_TOKEN}}
- uses: actions/checkout@v3
- name: Get changed files
id: changed-files
uses: tj-actions/changed-files@v40
- name: List all changed files
id: filter
run: |
echo ${{github.event_name}}
noncontainer=true
if docker pull ghcr.io/caciviclab/disclosure-backend-static/${{github.ref_name}}:latest; then
devcontainer=false
else
devcontainer=true
fi
for file in ${{ steps.changed-files.outputs.all_changed_files }}; do
echo "$file was changed"
if [[ ${{github.event_name}} = push ]]; then
if [[ $file = .devcontainer* ]]; then
devcontainer=true
elif [[ $file = *requirements.txt* ]]; then
devcontainer=true
elif [[ $file = Gemfile* ]]; then
devcontainer=true
fi
fi
done
echo "devcontainer=$devcontainer" >> $GITHUB_OUTPUT
echo "noncontainer=$noncontainer" >> $GITHUB_OUTPUT
- name: Build dev container
if: steps.filter.outputs.devcontainer == 'true'
run: |
docker build --no-cache --tag ghcr.io/caciviclab/disclosure-backend-static/${{github.ref_name}}:latest -f ./.devcontainer/Dockerfile .
docker push ghcr.io/caciviclab/disclosure-backend-static/${{github.ref_name}}:latest
- name: Check code changes
if: steps.filter.outputs.noncontainer == 'true'
run: |
echo "TODO: run test to verify that code changes are good"
generate:
needs: build
if: needs.build.outputs.noncontainer == 'true'
runs-on: ubuntu-latest
container:
image: ghcr.io/caciviclab/disclosure-backend-static/${{github.ref_name}}:latest
credentials:
username: ${{ github.actor }}
password: ${{ secrets.github_token }}
env:
REPO_OWNER: ${{ github.repository_owner}}
REPO_BRANCH: ${{ github.ref_name }}
SERVICE_ACCOUNT_KEY_JSON: ${{ secrets.SERVICE_ACCOUNT_KEY_JSON }}
GDRIVE_FOLDER: ${{ vars.GDRIVE_FOLDER }}
PGHOST: postgres
PGDATABASE: ${{ env.POSTGRES_DB }}
PGUSER: ${{ env.POSTGRES_USER }}
PGPASSWORD: ${{ env.POSTGRES_PASSWORD }}
services:
postgres:
image: postgres:15.6-bullseye
env:
POSTGRES_USER: ${{ env.POSTGRES_USER }}
POSTGRES_DB: ${{ env.POSTGRES_DB }}
POSTGRES_PASSWORD: ${{ env.POSTGRES_PASSWORD }}
steps:
- uses: actions/checkout@v4
- name: Check setup
run: |
git -v
# This keeps git from thinking that the current dir is not a repo even though a .git dir exists
git config --global --add safe.directory "$GITHUB_WORKSPACE"
psql -l
echo "c1,c2" > test.csv
echo "a,b" >> test.csv
cat test.csv
csvsql -v --db postgresql:///disclosure-backend --insert test.csv
echo "List tables"
psql -c "SELECT * FROM pg_catalog.pg_tables WHERE schemaname != 'pg_catalog' AND schemaname != 'information_schema';"
pip show sqlalchemy
- name: Create csv files
run: |
make clean
make download
make import
make process
- name: Summarize results
run: |
echo "List tables"
psql -c "SELECT * FROM pg_catalog.pg_tables WHERE schemaname != 'pg_catalog' AND schemaname != 'information_schema';"