require 'rexml/parsers/pullparser'
require 'htmlentities'

class String
  # Truncate strings containing HTML code
  # Usage example: "string".truncate_html(50, :word_cut => false, :tail => '[+]')
  def truncate_html(len = 30, opts = {})
    opts = {:word_cut => true, :tail => '…'}.merge(opts)
    p = REXML::Parsers::PullParser.new(self)
    coder = HTMLEntities.new
    tags = []
    new_len = len
    results = ''
    while p.has_next? && new_len > 0
      p_e = p.pull
      case p_e.event_type
      when :start_element
        tags.push p_e[0]
        results << "<#{tags.last} #{attrs_to_s(p_e[1])}>"
      when :end_element
        results << "</#{tags.pop}>"
      when :text
        text = coder.decode(p_e[0])
        if (text.length > new_len) and !opts[:word_cut]
          piece = text.first(text.index(' ', new_len))
        else
          piece = text.first(new_len)
        end
        results << coder.encode(piece)
        new_len -= text.length
      else
        results << "<!-- #{p_e.inspect} -->"
      end
    end
    tags.reverse.each do |tag|
      results << "</#{tag}>"
    end
    results << opts[:tail]

    if html_safe? then
      results.html_safe
    else
      results
    end
  end

  private

  def attrs_to_s(attrs)
    if attrs.empty?
      ''
    else
      attrs.to_a.map { |attr| %{#{attr[0]}="#{attr[1]}"} }.join(' ')
    end
  end
end

require 'nokogiri'
require 'htmlentities'

class String
  def truncate_html(num_words = 30, opts = {})
    opts = {:word_cut => true, :tail => "…"}.merge(opts)
    tail = HTMLEntities.new.decode(opts[:tail])

    doc = Nokogiri::HTML(self)

    current = doc.children.first
    count = 0

    while true
      # we found a text node
      if current.is_a?(Nokogiri::XML::Text)
        count += current.text.split.length
        # we reached our limit, let's get outta here!
        break if count > num_words
        previous = current
      end

      if current.children.length > 0
        # this node has children, can't be a text node,
        # lets descend and look for text nodes
        current = current.children.first
      elsif !current.next.nil?
        #this has no children, but has a sibling, let's check it out
        current = current.next
      else
        # we are the last child, we need to ascend until we are
        # either done or find a sibling to continue on to
        n = current
        while !n.is_a?(Nokogiri::HTML::Document) and n.parent.next.nil?
          n = n.parent
        end

        # we've reached the top and found no more text nodes, break
        if n.is_a?(Nokogiri::HTML::Document)
          break;
        else
          current = n.parent.next
        end
      end
    end

    if count >= num_words
      unless count == num_words
      new_content = current.text.split

      # If we're here, the last text node we counted eclipsed the number of words
      # that we want, so we need to cut down on words.  The easiest way to think about
      # this is that without this node we'd have fewer words than the limit, so all
      # the previous words plus a limited number of words from this node are needed.
      # We simply need to figure out how many words are needed and grab that many.
      # Then we need to -subtract- an index, because the first word would be index zero.

      # For example, given:
      # <p>Testing this HTML truncater.</p><p>To see if its working.</p>
      # Let's say I want 6 words.  The correct returned string would be:
      # <p>Testing this HTML truncater.</p><p>To see...</p>
      # All the words in both paragraphs = 9
      # The last paragraph is the one that breaks the limit.  How many words would we
      # have without it? 4.  But we want up to 6, so we might as well get that many.
      # 6 - 4 = 2, so we get 2 words from this node, but words #1-2 are indices #0-1, so
      # we subtract 1.  If this gives us -1, we want nothing from this node. So go back to
      # the previous node instead.
      index = num_words-(count-new_content.length)-1
      if index >= 0
      new_content = new_content[0..index]
        current.content = new_content.join(' ') + tail
        else
        current = previous
        current.content = current.content + tail
      end
      end

      # remove everything else
      while !current.is_a?(Nokogiri::HTML::Document)
        while !current.next.nil?
          current.next.remove
        end
        current = current.parent
      end
    end

    # now we grab the html and not the text.
    # we do first because nokogiri adds html and body tags
    # which we don't want
    truncated = doc.root.children.first.children.first.inner_html

    if html_safe?
      truncated.html_safe
    else
      truncated
    end
  end
end