Added github actions workflows files and first glue job for data ingestion.

Author: johnathon-smith

.github/workflows/ci-cd.yml

@@ -0,0 +1,82 @@
+name: CI/CD - AWS Glue Delta Lake Project
+
+on:
+  pull_request:
+    branches:
+      - main
+
+  push:
+    branches:
+      - main
+
+  workflow_dispatch:
+    inputs:
+      force_deploy:
+        description: "Deploy Glue scripts even if validation fails"
+        required: true
+        default: "false"
+        type: choice
+        options:
+          - "false"
+          - "true"
+
+permissions:
+  id-token: write
+  contents: read
+
+env:
+  AWS_REGION: us-east-1
+  GLUE_SCRIPT_BUCKET: wistia-data-bucket-001
+  GLUE_SCRIPT_PREFIX: scripts/glue_jobs
+
+jobs:
+  validate-python:
+    name: Validate Python code
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install development dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements-dev.txt
+
+      - name: Run Ruff checks
+        run: |
+          ruff check glue_jobs streamlit_app
+
+  deploy-glue-scripts:
+    name: Deploy Glue scripts to S3
+    runs-on: ubuntu-latest
+    needs: validate-python
+
+    if: |
+      always() &&
+      (
+        (github.event_name == 'push' && github.ref == 'refs/heads/main' && needs.validate-python.result == 'success') ||
+        (github.event_name == 'workflow_dispatch' && inputs.force_deploy == 'true')
+      )
+
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v4
+
+      - name: Configure AWS credentials
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          role-to-assume: arn:aws:iam::778277577883:role/wistia-github-actions-glue-deploy-role
+          aws-region: ${{ env.AWS_REGION }}
+
+      - name: Upload Glue job scripts to S3
+        run: |
+          aws s3 sync glue_jobs/ s3://${GLUE_SCRIPT_BUCKET}/${GLUE_SCRIPT_PREFIX}/ \
+            --delete \
+            --exclude "__pycache__/*" \
+            --exclude "*.pyc"