pne-workflow.yml

# CI for NVIP

name: Product Name Extractor Workflow

on:
  pull_request:
    branches:
      - main
      - dev
  push:
    branches:
      - main
      - dev
      - 'cicd/**'
    paths-ignore:
      - 'crawler/**'
      - 'exploitfinder/**'
      - 'patchfinder/**'
      - 'reconciler/**'

env:
  AWS_REGION: 'us-east-1'
  DB_TYPE: 'mysql'
  HIKARI_URL: 'jdbc:mysql://localhost:3306/nvip?useSSL=false&allowPublicKeyRetrieval=true'
  HIKARI_USER: 'root'
  HIKARI_PASSWORD: 'root'
  RESOURCE_DIR: 'nvip_data'
  DATA_DIR: 'data'
  NLP_DIR: 'nlp'
  CHAR_2_VEC_CONFIG: 'c2v_model_config_50.json'
  CHAR_2_VEC_WEIGHTS: 'c2v_model_weights_50.h5'
  WORD_2_VEC: 'w2v_model_250.bin'
  NER_MODEL: 'NERallModel.bin'
  NER_MODEL_NORMALIZER: 'NERallNorm.bin'
  SENTENCE_MODEL: 'en-sent.bin'
  PRODUCT_DETECTOR_MODEL: 'en-pos-perceptron.bin'

jobs:
  # Build and Test Product Extraction Component
  build-test-product-extractor:
    runs-on: ubuntu-latest
    steps:
      - name: checkout
        uses: actions/checkout@v3
        with:
          lfs: 'true'
      - name: Set up JDK 17
        uses: actions/setup-java@v3
        with:
          java-version: '17'
          distribution: 'temurin'

      - name: Configure AWS credentials
        uses: aws-actions/configure-aws-credentials@v2
        with:
          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
          aws-region: ${{ env.AWS_REGION }}

      # Grab large files (w2v model) from S3 bucket
      - name: Pull file from S3 bucket
        run: |
          cd productnameextractor/nvip_data/data
          aws s3 cp s3://binaries-for-crawler/w2v_model_250.bin .

      # Setup MySQL DB for tests that require connection (Might not need this)
      - name: Start MySQL Service
        run: sudo /etc/init.d/mysql start
        # run: |
        #   sudo /etc/init.d/mysql start
        #   mysql -e 'CREATE DATABASE nvip;' -uroot -proot
        #   mysql -e 'SHOW DATABASES;' -uroot -proot
        #   mysql -e 'source nvip_data/mysql-database/CreateAndInitializeDb.sql' -uroot -proot

      - name: Initialize DB
        env:
          LIQUIBASE_COMMAND_URL: ${{ env.HIKARI_URL }}
          LIQUIBASE_COMMAND_USERNAME: ${{ env.HIKARI_USER }}
          LIQUIBASE_COMMAND_PASSWORD: ${{ env.HIKARI_PASSWORD }}
        run: |
          mysql -e 'CREATE DATABASE nvip;' -u${{ env.HIKARI_USER }} -p${{ env.HIKARI_PASSWORD }} 
          mvn liquibase:update --no-transfer-progress --projects=productnameextractor

      - name: Test and Build Product Extractor with Maven
        run: |
          cd productnameextractor
          mvn dependency:go-offline
          mvn package

      - name: Publish Test Report
        if: success() || failure()
        uses: scacap/action-surefire-report@v1
        with:
          check_name: PNE Test Report

  # Deploy product extractor component project to container registry
  staging-deploy:
    runs-on: ubuntu-latest
    needs: build-test-product-extractor
    if: ${{ success() && github.ref == 'refs/heads/main' }}
    steps:
      - uses: actions/checkout@v3

      - name: Configure AWS credentials
        uses: aws-actions/configure-aws-credentials@v2
        with:
          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
          aws-region: ${{ env.AWS_REGION }}

      # Pull large files (w2v model) so they're in the container
      - name: Pull file from S3 bucket
        run: |
          cd productnameextractor/nvip_data/data
          aws s3 cp s3://binaries-for-crawler/w2v_model_250.bin . 

      - name: Login to GitHub Container Registry
        uses: docker/login-action@v2
        with:
          registry: ghcr.io
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}

      - name: Build and Push Docker Image for Product Extractor
        run: |
          docker build . -f productnameextractor/Dockerfile -t nvip-productnameextractor:staging -t ghcr.io/softwaredesignlab/nvip-productnameextractor:staging
          docker push ghcr.io/softwaredesignlab/nvip-productnameextractor:staging

  # Deploy product extractor component project to container registry
  production-deploy:
    runs-on: ubuntu-latest
    environment: production
    needs: staging-deploy
    steps:
      - uses: actions/checkout@v3

      - name: Configure AWS credentials
        uses: aws-actions/configure-aws-credentials@v2
        with:
          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
          aws-region: ${{ env.AWS_REGION }}

      # Pull large files (w2v model) so they're in the container
      - name: Pull file from S3 bucket
        run: |
          cd productnameextractor/nvip_data/data
          aws s3 cp s3://binaries-for-crawler/w2v_model_250.bin . 

      - name: Login to GitHub Container Registry
        uses: docker/login-action@v2
        with:
          registry: ghcr.io
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}

      - name: Build and Push Docker Image for Product Extractor
        run: |
          docker build . -f productnameextractor/Dockerfile -t nvip-productnameextractor -t ghcr.io/softwaredesignlab/nvip-productnameextractor
          docker push ghcr.io/softwaredesignlab/nvip-productnameextractor