doc-exports/.gitea/workflows/convert-html-docs.yaml

name: Install Pandoc from Source
on:
  pull_request:
    types: [opened, reopened, synchronize, edited]

jobs:
  install-pandoc:
    runs-on: ubuntu-latest  # adjust to your runner label
    steps:
      - name: Checkout Code
        uses: actions/checkout@v3

      - name: Download Pandoc 2.19.2
        run: |
          curl -L -o pandoc.tar.gz \
            https://github.com/jgm/pandoc/releases/download/2.19.2/pandoc-2.19.2-linux-amd64.tar.gz

      - name: Extract and Install Pandoc
        run: |
          tar xvzf pandoc.tar.gz --strip-components 1 -C /usr/local/
          chmod +x /usr/local/bin/pandoc

      - name: Verify Installation
        run: pandoc --version

  install-convertor:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout Code
        uses: actions/checkout@v3

      - name: Set up Python
        uses: actions/setup-python@v4
        with:
          python-version: '3.10'  # adjust version as needed

      - name: Clone doc-convertor from Gitea
        env:
          GITEA_TOKEN: ${{ secrets.TEST_TOKEN }}
          GITEA_SERVER_URL: ${{ gitea.server_url }}
        run: |
          git clone https://${GITEA_TOKEN}@gitea.eco.tsi-dev.otc-service.com/docs/doc-convertor.git

      - name: Create virtualenv and install package in editable mode
        run: |
          python -m venv ~/.venv
          source ~/.venv/bin/activate
          pip install --upgrade pip
          pip install -e ./doc-convertor

  parse-metadata-yaml:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3

      - name: Set up Python
        uses: actions/setup-python@v4
        with:
          python-version: '3.10'  # adjust version as needed

      - name: Install PyYAML
        run: pip install pyyaml

      - name: Load YAML and set outputs
        id: metadata
        shell: python
        run: |
          # python3 <<EOF > parsed.env
          import yaml, os
          with open("metadata.yaml") as f:
              data = yaml.safe_load(f)
              print(f"SERVICE_TITLE={data['categories']['security-services'][0]['service_title']}")
              print(f"SERVICE_TYPE={data['categories']['security-services'][0]['service_type']}")
              print(f"SERVICE_CATEGORY={data['categories']['security-services'][0]['service_category']}")
          # EOF
          # cat parsed.env >> $GITHUB_ENV

      - name: Use config values
        run: |
          echo "SERVICE_TITLE: $SERVICE_TITLE"
          echo "SERVICE_TYPE: $SERVICE_TYPE"
          echo "SERVICE_CATEGORY: $SERVICE_CATEGORY"


  generate-docs:
    runs-on: ubuntu-latest
    env:
      DOCS_UPDATE_DATA_FILE: metadata.yaml
      PROJECT_SRC_DIR: ./docs

    steps:
      - name: Checkout source repo
        uses: actions/checkout@v3

      - name: Install Python and dependencies
        uses: actions/setup-python@v4
        with:
          python-version: 3.10

      - name: Install PyYAML (to parse YAML files)
        run: pip install pyyaml

      - name: Read project docs configuration and extract needed vars
        id: read_docs_config
        run: |
          python3 <<EOF
          import yaml
          import os
          import json
          from pathlib import Path
          
          data_file = os.getenv('DOCS_UPDATE_DATA_FILE')
          with open(data_file) as f:
              data = yaml.safe_load(f)
          
          # Simulate categories[docs_service_category] defaulting to {}
          # docs_service_category = data.get('categories', '')  
          docs_service_category = "application"
          print(docs_service_category)
          categories = data.get('categories', {})
          print(categories)
          
          doc_exports_var = categories.get(docs_service_category, {})
          print(doc_exports_var)
          json_str = json.dumps(doc_exports_var, indent=4)
          json_str = "doc_exports_var=" + json_str
          print(json_str)
          with open(os.environ['GITHUB_OUTPUT'], 'a') as fh:
              fh.write(json_str)
 
          # Write doc_exports_var to output & env file, serialized as JSON for easy later processing
          with open('doc_exports_var.json', 'w') as jf:
              json.dump(doc_exports_var, jf)
          EOF
          sleep 5
          echo "Loaded doc_exports_var and saved to doc_exports_var.json"
          ls -la ./doc_exports_var.json
          cat ./doc_exports_var.json
          
#      - name: Get last git changed files
#        id: git_log
#        run: |
#          cd $PROJECT_SRC_DIR
#          ls
#          echo > ../changed_files.txt
#          git branch
#          git status
#          git log -1 --name-only --pretty= > ../changed_files.txt || true
#          cat ../changed_files.txt
#          cat ../doc_exports_var.json


      - name: Install jq
        run: sudo apt-get update && sudo apt-get install -y jq

      - name: Debug event file
        run: |
          echo "Gitea event file path: $GITEA_EVENT_PATH"
          cat "$GITEA_EVENT_PATH"

      - name: List changed files in PR
        id: changed_files
        run: |
          PR_NUMBER=$(jq -r .pull_request.number "$GITEA_EVENT_PATH")
          REPO=$(jq -r .repository.full_name "$GITEA_EVENT_PATH")

          echo "PR #$PR_NUMBER from repo $REPO"

          # Extract owner and repo name
          OWNER=$(echo "$REPO" | cut -d'/' -f1)
          REPO_NAME=$(echo "$REPO" | cut -d'/' -f2)

          # Use Gitea API to get changed files
          # Requires an API token with repo read access
          curl -s -H "Authorization: token ${{ secrets.TEST_TOKEN }}" \
            "https://gitea.eco.tsi-dev.otc-service.com/api/v1/repos/$OWNER/$REPO_NAME/pulls/$PR_NUMBER/files" \
            | jq -r '.[].filename' > changed_files.txt

          echo "Changed files:"
          cat changed_files.txt

      - name: Generate RST docs
        run: |
          python3 <<EOF
          import json
          import os
          import re
          from subprocess import run
          
          # Load doc_exports_var from JSON
          with open('doc_exports_var.json') as f:
              doc_exports_var = json.load(f)
          
          # Read changed files
          with open('changed_files.txt') as f:
              changed_files = f.read()
          
          def file_changed(pattern):
              return re.search(pattern, changed_files) is not None
          
          # Loop through docs (assuming structure similar to ansible)
          for doc0 in doc_exports_var.get('docs', []):
              # Here doc0 = {service_type:..., repository:..., service_title:..., ...}
              # We expect doc0 to contain a 'docs' list (per your subelements('docs'))
              for doc1 in doc0.get('docs', []):
                  html_loc = doc1.get('html_location')
                  rst_loc = doc1.get('rst_location')
          
                  # Skip if html location or rst location is not defined
                  if not (html_loc and rst_loc):
                      continue
          
                  # Check if changed_files contain relevant paths
                  if (file_changed(html_loc) or
                      file_changed('metadata.yaml') or
                      file_changed('playbooks') or
                      file_changed('templates')):
          
                      # Build variables for convert_doc role
                      env_vars = {
                          "DOC_LABEL": f"{doc0.get('service_type')}_{doc1.get('type')}",
                          "DEST": os.path.expanduser(f"{doc0.get('repository')}/{doc1.get('rst_location')}"),
                          "SOURCE": os.path.join(os.getenv('PROJECT_SRC_DIR'), doc1.get('html_location')),
                          "DOC_TITLE": f"{doc0.get('service_title')} - {doc1.get('title')}",
                          "DOC_SHORT_TITLE": doc1.get('title'),
                          "DOC_ENVIRONMENT": doc0.get('service_environment'),
                          "DOC_LINK": doc1.get('link'),
                          "DOC_TYPE": doc1.get('type'),
                          "DOC_SERVICE": doc0.get('service_title'),
                          "DOC_SERVICE_CATEGORY": doc0.get('service_category'),
                          "DOC_SERVICE_TYPE": doc0.get('service_type'),
                          "DOC_REPO_NAME": doc0.get('repository'),
                          "DOC_PDF_NAME": doc1.get('pdf_name'),
                      }
          
                      # Export env vars for convert_doc command
                      env_str = " ".join([f'{k}="{v}"' for k, v in env_vars.items() if v])
          
                      print(f"Generating docs for {env_vars['DOC_LABEL']}")
          
                      # Convert the respective doc with metadata parameters
                      result = run(f"otc-doc-convertor {env_str}", shell=True)
                      if result.returncode != 0:
                          print(f"Error running convert_doc for {env_vars['DOC_LABEL']}")
                          exit(result.returncode)
          EOF