umlauts and encoding in nokogiri

fragment.rb

require 'rubygems'
require 'nokogiri'

doc = Nokogiri::HTML::Document.new
doc.encoding = 'UTF-8'

# We added a contextual fragment method for the 1.4.2 release.  This *might*
# work in 1.4.1.  If you want to mess with 1.4.2, build from my github, or
# grab one of our nightly builds:
#
#   $ sudo gem install nokogiri -s http://tenderlovemaking.com/
#
# Also, libxml2 had a bug with encoding when handling UTF-8 fragments, so I
# suggest you also upgrade to libxml2 2.7.7.
#
# Hope that helps!
puts doc.fragment('<p>ö</p>')

output.txt

<p>ö</p>