#!/usr/bin/env ruby
# frozen_string_literal: true

require 'word-to-markdown'
require 'reverse_asciidoctor'

def scrub_whitespace(string)
  string = string.dup
  string.gsub!(' ', ' ')       # HTML encoded spaces
  string.sub!(/\A[[:space:]]+/, '') # document leading whitespace
  string.sub!(/[[:space:]]+\z/, '') # document trailing whitespace
  string.gsub!(/([ ]+)$/, '')       # line trailing whitespace
  string.gsub!(/\n\n\n\n/, "\n\n")  # Quadruple line breaks
  string.delete!(' ')               # Unicode non-breaking spaces, injected as tabs
  # following added by me
  string.gsub!(%r{<h[1-9][^>]*></h1>}, " ") # I don't know why Libre Office is inserting them, but they need to go
  string.gsub!(%r{<h1[^>]* style="vertical-align: super;[^>]*>([^<]+)</h1>},
              "<sup>\\1</sup>")         # I absolutely don't know why Libre Office is rendering superscripts as h1
  string
end

if ARGV.size != 1 && ARGV[0] != "--mathml2asciimath" || ARGV[0] == '--help'
  puts 'Usage: bundle exec w2m path/to/document.docx'
  exit 1
end

if ARGV[0] == "--mathml2asciimath" && ARGV[1]
  ReverseAsciidoctor.config.mathml2asciimath = true
  ARGV[0] = ARGV[1]
end

if ARGV[0] == '--version'
  puts "WordToMarkdown v#{WordToMarkdown::VERSION}"
  puts "LibreOffice v#{WordToMarkdown.soffice.version}" unless Gem.win_platform?
else
  doc = WordToMarkdown.new ARGV[0]
  # puts scrub_whitespace(doc.document.html)
  puts ReverseAsciidoctor.convert(scrub_whitespace(doc.document.html), WordToMarkdown::REVERSE_MARKDOWN_OPTIONS)
end