gistfile1.rb

require 'rubygems'
require 'hpricot'

module HpricotTruncator
  module NodeWithChildren
    def truncate(max_length)
      return self if inner_text.length <= max_length
      truncated_node = self.dup
      truncated_node.children = []
      each_child do |node|
        remaining_length = max_length - truncated_node.inner_text.length
        break if remaining_length == 0
        truncated_node.children << node.truncate(remaining_length)
      end
      truncated_node
    end
  end
end

Hpricot::Doc.send(:include, HpricotTruncator::NodeWithChildren)

doc = Hpricot("Pākistānī, Hindustāni")
puts doc.truncate(5).inner_html