Playing with tire analyzer for french language

gistfile1.rb

#encoding: utf-8
require 'rubygems'
require 'tire'

#
# Playing with analyzers and its parameters.
# Witch fits best for the french language?
#
# $ rvm use 1.9.2
# $ gem install tire
# $ ruby test.rb
#

class Hash #compatibility hacks for rails stuffs
  def to_param
    self.map{|k,v| "#{k}=#{v}"}.join('&')
  end
end

tire = Tire::Index.new 'analyzers'
tire.delete
conf = {
  settings: {
    analysis: {
      analyzer: {
        francais: {
          type: 'custom',
          tokenizer: 'standard',
          filter: %w{lowercase stop_francais asciifolding elision}
        },
        francais_boule: {
          type: 'snowball',
          language: 'French'
        }
      },
      filter: {
        stop_francais: {
          type: 'stop',
          stopwords: %w{je tu il nous vous ils le la les un une des a ai et est ayons ça}
        }
      }
    }
  }
}
tire.create conf

%w{ whitespace standard simple french francais francais_boule}.each do |analyzer|
  p analyzer
  a = tire.analyze("Je mange des carottes, des petits pois et des pèches (bien que ça coule sur les doigts). J'aime ça.", :analyzer => analyzer)
  print "    "
  p a['tokens'].map{ |t| t['token']}
end