lint_and_unit.yaml

name: Lint and unit checks

on:
  pull_request:
    branches: [ main ]
  push:
    branches: [ main ]

permissions:
  contents: read

jobs:
  lint:
    name: Python lint with pre-commit
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-python@v5
        with:
          python-version: '3.11'
          cache: 'pip'
          cache-dependency-path: |
            requirements-dev.txt
            requirements.txt
      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
          pip install -r requirements-dev.txt
      - name: Run pre-commit hooks
        run: |
          pre-commit run --all-files

  unit:
    name: Unit tests (${{ matrix.arch }})
    runs-on: ${{ matrix.runner }}
    needs: lint
    strategy:
      matrix:
        include:
          - arch: amd64
            runner: ubuntu-latest
            platform: linux/amd64
          - arch: arm64
            runner: ubuntu-24.04-arm
            platform: linux/arm64
    env:
      PLATFORM: ${{ matrix.platform }}
    services:
      postgres:
        image: postgres:11
        env:
          POSTGRES_PASSWORD: queridodiario
          POSTGRES_USER: queridodiario
          POSTGRES_DB: queridodiariodb
        options: >-
          --health-cmd pg_isready
          --health-interval 10s
          --health-timeout 5s
          --health-retries 5
        ports:
          - 5432:5432

      opensearch:
        image: opensearchproject/opensearch:2.9.0
        env:
          discovery.type: single-node
          plugins.security.ssl.http.enabled: false
          plugins.security.disabled: true
          OPENSEARCH_INITIAL_ADMIN_PASSWORD: admin
        options: >-
          --health-cmd "curl -s http://localhost:9200 >/dev/null || exit 1"
          --health-interval 15s
          --health-timeout 10s
          --health-retries 20
        ports:
          - 9200:9200

      apache-tika:
        image: ghcr.io/${{ github.repository }}/apache-tika:latest
        ports:
          - 9998:9998

    steps:
      - uses: actions/checkout@v4

      - name: Start MinIO
        run: |
          docker run -d \
            --name minio \
            --network host \
            --health-cmd "curl -f http://localhost:9000/minio/health/live || exit 1" \
            --health-interval 10s \
            --health-timeout 5s \
            --health-retries 5 \
            -e MINIO_ROOT_USER=minio-access-key \
            -e MINIO_ROOT_PASSWORD=minio-secret-key \
            quay.io/minio/minio:RELEASE.2025-09-07T16-13-09Z \
            server /data --console-address :9001

          # Wait for MinIO to be ready
          echo "Waiting for MinIO to be ready..."
          timeout 60 bash -c 'until curl -sf http://localhost:9000/minio/health/live > /dev/null 2>&1; do sleep 2; done'
          echo "MinIO is ready"

      - uses: actions/setup-python@v5
        with:
          python-version: '3.11'
          cache: 'pip'
          cache-dependency-path: requirements.txt
      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
          pip install -r requirements.txt

      - name: Create MinIO bucket
        run: |
          # Wait for MinIO to be ready
          for i in {1..30}; do
            if curl -sf http://localhost:9000/minio/health/live > /dev/null 2>&1; then
              echo "MinIO is ready"
              break
            fi
            echo "Waiting for MinIO... ($i/30)"
            sleep 2
          done

          # Detect architecture and download appropriate MinIO client
          ARCH=$(uname -m)
          if [ "$ARCH" = "aarch64" ] || [ "$ARCH" = "arm64" ]; then
            MC_URL="https://dl.min.io/client/mc/release/linux-arm64/mc"
          else
            MC_URL="https://dl.min.io/client/mc/release/linux-amd64/mc"
          fi

          echo "Downloading MinIO client for architecture: $ARCH"
          curl -sLo /tmp/mc "$MC_URL"
          chmod +x /tmp/mc

          # Configure MinIO client
          /tmp/mc alias set minio http://localhost:9000 minio-access-key minio-secret-key

          # Create bucket if it doesn't exist
          /tmp/mc mb minio/queridodiariobucket --ignore-existing || true

          echo "MinIO bucket created successfully"

      - name: Create OpenSearch index
        timeout-minutes: 2
        run: |
          echo "=== Creating OpenSearch index ==="
          echo "OpenSearch host: http://localhost:9200"
          echo "Testing connectivity..."
          curl -v http://localhost:9200/_cluster/health || echo "OpenSearch not responding"
          echo "Running init script..."
          chmod +x init-scripts/opensearch/create-opensearch-index.sh
          OPENSEARCH_HOST=http://localhost:9200 \
          OPENSEARCH_USER=admin \
          OPENSEARCH_PASSWORD=admin \
          INDEX_NAME=querido-diario \
          ./init-scripts/opensearch/create-opensearch-index.sh
          echo "=== OpenSearch index creation completed ==="

      - name: Run unit tests
        timeout-minutes: 5
        env:
          PYTHONPATH: ${{ github.workspace }}
          PYTHONUNBUFFERED: 1
          POSTGRES_PASSWORD: queridodiario
          POSTGRES_USER: queridodiario
          POSTGRES_DB: queridodiariodb
          POSTGRES_HOST: localhost
          POSTGRES_PORT: 5432
          STORAGE_REGION: us-east-1
          STORAGE_ENDPOINT: http://localhost:9000
          STORAGE_ACCESS_KEY: minio-access-key
          STORAGE_ACCESS_SECRET: minio-secret-key
          STORAGE_BUCKET: queridodiariobucket
          OPENSEARCH_HOST: http://localhost:9200
          OPENSEARCH_INDEX: querido-diario
          OPENSEARCH_USER: admin
          OPENSEARCH_PASSWORD: admin
          APACHE_TIKA_SERVER: http://localhost:9998
          DEBUG: 1
          HF_HUB_OFFLINE: 1
          TRANSFORMERS_OFFLINE: 1
          SENTENCE_TRANSFORMERS_HOME: /tmp/sentence_transformers
        run: |
          echo "========================================="
          echo "🧪 STARTING INSTRUMENTED TEST RUN"
          echo "========================================="
          echo "Working directory: $(pwd)"
          echo "Python: $(which python)"
          echo "Python version: $(python --version)"
          echo "Time: $(date)"
          echo ""
          
          # Make runner executable
          chmod +x instrumented_test_runner.py
          
          # Run with our instrumented runner
          python instrumented_test_runner.py
          
          echo ""
          echo "========================================="
          echo "Test run completed at: $(date)"
          echo "========================================="