word_cleanup.rb

# F MS Word
# This will cleanup 95% of the issues of copying from Word into a textarea.
# Notes:
#  - This would be run on text already saved to the database
#  - I am using Markdown convention for the bullets
#  - I am being very lazy with em/en dashes - I could use Smarty Pants, but that opens up other issues

class WordCleanup
  def self.clean(text)
    unless text.nil?
      # single quote
      text = text.gsub('’', "'")
      # em or en dash
      text = text.gsub('–', "-")
      # opening quote
      text = text.gsub('“', '"')
      # closing quote
      text = text.gsub('”', '"')
      # bullet point - convert to line break and Markdown bullet
      text = text.gsub('•', "\r\n- ")
      # colon
      text = text.gsub("…", ":")
    end
  end
end