12345678910111213141516171819202122232425262728293031323334 |
- # example-1
- # Illustrates creating an instance of uhferret and
- # finding the similarity of some sample documents.
- require "uhferret"
- # Construct an instance of ferret and add some documents to it.
- ferret = UHFerret::Ferret.new
- ferret.add "text-eg/ruby.txt"
- ferret.add "text-eg/cobra.txt"
- ferret.add "text-eg/fantom.txt"
- # Run ferret to compute similarities.
- # This step can take a long time, if there are many documents.
- ferret.run
- # Print out information for every document.
- ferret.each do |doc|
- puts "Document name: #{doc.filename}"
- end
- # Print out some information for every pair of documents.
- ferret.each_pair do |i, j|
- puts "For document #{i} - #{ferret[i].filename}"
- puts "and document #{j} - #{ferret[j].filename}"
- puts "Resemblance is #{ferret.resemblance(i, j)}"
- puts "Containment of #{i} in #{j} is #{ferret.containment(i, j)}"
- puts "Containment of #{j} in #{i} is #{ferret.containment(j, i)}"
- puts "Doc #{i} has #{ferret.trigram_count(i)} trigrams, \
- doc #{j} has #{ferret.trigram_count(j)} trigrams, and \
- they share #{ferret.trigram_matches(i, j)} trigrams"
- end
|