jpmckinney

# blog post: http://blog.slashpoundbang.com/post/12938588984/google-refine-fingerprint-clustering-algorithm-in-ruby

# coding: utf-8
require 'unicode_utils/downcase'

class String
  # Normalize spaces and fingerprint.
  # http://code.google.com/p/google-refine/wiki/ClusteringInDepth
  # http://code.google.com/p/google-refine/source/browse/trunk/main/src/com/google/refine/clustering/binning/FingerprintKeyer.java
  def fingerprint