Initial .gitlab-ci.yml file

stages:

  - preprocessing

  - build_html

  - build_docx

  - deploy

workflow:

  rules:

    - changes:

      - API.docx

    - if: $CI_PIPELINE_SOURCE == "manual"

variables:

  DOCKER_DRIVER: overlay2

generate_temp_docx:

  stage: preprocessing

  image: python:3.10-slim

  before_script:

    - pip3 install python-docx #install dependances

  script:

    - python3 preprocessing.py "./API.docx"

  artifacts:

    paths:

      - temp.docx

      - API.css

      - background_highlight.css

images_extraction:

  stage: preprocessing

  image:

    name: ubuntu:latest

  before_script:

    - apt-get update && apt-get install pandoc -y && apt-get install imagemagick -y && apt-get --no-install-recommends install libreoffice -y #install tools

  script:

    - pandoc --extract-media ./ -f docx -t html -s API.docx -o API.html

  after_script:

    - cd media

    - libreoffice --headless --convert-to png *.emf

    - mogrify -trim *.png

  artifacts:

    paths:

      - media

html:

  stage: build_html

  image: 

    name: pandoc/latex:3.1

    entrypoint: ["/bin/sh", "-c"]

  script:

    - pandoc --extract-media ./ -f docx -t html -L filter_1.lua -L filter_2.lua  --css=styling.css --css=API.css -s temp.docx -o API.html --toc --toc-depth 4 --template=template.html

  artifacts:

    paths:

      - API.html

docx:

  stage: build_docx

  image: python:3.10-slim

  dependencies:

    - "html"

  before_script:

    - apt update && apt-get install p7zip-full -y

    - pip3 install python-docx && pip3 install cssutils && pip3 install beautifulsoup4 #install dependances

  script:

    - python3 html_to_docx.py API.html API.css

    - python3 postprocessing.py html_to_docx_output.docx ./media

  artifacts:

    paths:

      - html_to_docx_output_fixed.docx

pages:

  stage: deploy

  image: bitnami/git

  dependencies:

    - "docx"

  script:

    - cp API.html public/index.html

    - cp API.css background_highlight.css public/

    - cp html_to_docx_output_fixed.docx public/output_API.docx

    - cp media/* public/media/

    - echo "The site will be deployed to $CI_PAGES_URL"

  artifacts:

    paths:

      # The folder that contains the files to be exposed at the Page URL

      - public