handle messy word html

# This function cleans up messy HTML that was pasted by a user to a WYSIWYG editor.
# Specifically it also handles messy Word\Outlook generated HTML while keeping its original formattings.
 
require 'rubygems'
require 'sanitize'
 
  def clean_up_document(html)
    elements = %w[p b h1 h2 h3 h4 h5 h6 strong li ul ol i br div pre p]
    attributes = {
                  'a' => ['href', 'title'], 
                  'pre' => ['class'],
                  'p' => ['style']
                  }
    protocols = {'a' => {'href' => ['http', 'https', 'mailto', :relative]}}
                  
    email_regex = /<p>Email:\s+((\w|\-|\_|\.)+\@((\w|\-|\_)+\.)+[a-zA-Z]{2,})/i
 
    html.gsub! /<style>(.|\s)*?<\/style>/, ''
    html.gsub! /<!--(.|\s)*?-->/  , ''
    html.gsub! /[\n|\r]/          , ''
    
 
    # keep only the things we want.
    html = Sanitize.clean( html, :elements => elements, :attributes => attributes, :protocols => protocols )
 
    # butt up any tags
    html.gsub! /&nbsp;/                 , ' '
    html.gsub! />\s+</                  , '><'
    
    #remove email address lines
    html.gsub! email_regex              , '<p>'
    
    # post sanitize cleanup of empty blocks
    # the order of removal is import - this is the way word stacks these elements
    html.gsub! /<i><\/i>/               , ''
    html.gsub! /<b><\/b>/               , ''
    html.gsub! /<\/b><b>/               , ''
    html.gsub! /<p><\/p>/               , ''
    html.gsub! /<p><b><\/b><\/p>/       , ''
    
    # misc - fix butted times
    html.gsub! /(\d)am /          , '\1 am '
    html.gsub! /(\d)pm /          , '\1 pm '
    # misc - remove multiple space that may cause doc specific regexs to fail (in dates for example)
    html.gsub! /\s+/                  , ' '
    
    # add new lines at the end of lines
    html.gsub! /<\/(p|h\d|dt|dd|dl)>/, '</\1>' + "\n"
    html.gsub! /<dl>/             , '<dl>' + "\n"
 
    html
  end