Question

I have a Rails application that is now set up with ElasticSearch and the Tire gem to do searching on a model and I was wondering how I should set up my application to do fuzzy string matching on certain indexes in the model. I have my model set up to index on things like title, description, etc. but I want to do fuzzy string matching on some of those and I’m not sure where to do this at. I will include my code below if you would like to comment! Thanks!

In the controller:

    def search
      @resource = Resource.search(params[:q], :page => (params[:page] || 1),
                                 :per_page =>15, load: true )
   end

In the Model:

class Resource < ActiveRecord::Base
  include Tire::Model::Search
  include Tire::Model::Callbacks

  belongs_to :user
  has_many :resource_views, :class_name => 'UserResourceView'

  has_reputation :votes, source: :user, aggregated_by: :sum

  attr_accessible :title, :description, :link, :tag_list, :user_id, :youtubeID
  acts_as_taggable

  mapping do 
      indexes :id,  :index => :not_analyzed
      indexes :title, :analyzer => 'snowball', :boost => 40
      indexes :tag_list, :analyzer => 'snowball', :boost => 8
      indexes :description, :analyzer => 'snowball', :boost => 2
      indexes :user_id, :analyzer => 'snowball'
  end
end

Answer 1

Try creating custom analyzers to achieve other stemming features, etc.
Check out my example (this example also uses Mongoid & attachments, don’t look at it if you don’t need it):

class Document
      include Mongoid::Document
      include Mongoid::Timestamps
      include Tire::Model::Search
      include Tire::Model::Callbacks

      field :filename, type: String
      field :md5, type: String
      field :tags, type: String
      field :size, type: String

      index({md5: 1}, {unique: true})
      validates_uniqueness_of :md5


      DEFAULT_PAGE_SIZE = 10

      settings :analysis => {
          :filter => {
              :ngram_filter => {
                  :type => "edgeNGram",
                  :min_gram => 2,
                  :max_gram => 12
              },
              :custom_word_delimiter => {
                  :type => "word_delimiter",
                  :preserve_original => "true",
                  :catenate_all => "true",
              }
          }, :analyzer => {
              :index_ngram_analyzer => {
                  :type => "custom",
                  :tokenizer => "standard",
                  :filter => ["lowercase", "ngram_filter", "asciifolding", "custom_word_delimiter"]
              },
              :search_ngram_analyzer => {
                  :type => "custom",
                  :tokenizer => "standard",
                  :filter => ["standard", "lowercase", "ngram_filter", "custom_word_delimiter"]
              },
              :suggestions => {
                  :tokenizer => "standard",
                  :filter => ["suggestions_shingle"]
              }
          }
      } do
        mapping {
          indexes :id, index: :not_analyzed
          indexes :filename, :type => 'string', :store => 'yes', :boost => 100, :search_analyzer => :search_ngram_analyzer, :index_analyzer => :index_ngram_analyzer
          indexes :tags, :type => 'string', :store => 'yes', :search_analyzer => :search_ngram_analyzer, :index_analyzer => :index_ngram_analyzer
          indexes :attachment, :type => 'attachment',
                  :fields => {
                      :content_type => {:store => 'yes'},
                      :author => {:store => 'yes', :analyzer => 'keyword'},
                      :title => {:store => 'yes'},
                      :attachment => {:term_vector => 'with_positions_offsets', :boost => 90, :store => 'yes', :search_analyzer => :search_ngram_analyzer, :index_analyzer => :index_ngram_analyzer},
                      :date => {:store => 'yes'}
                  }
        }
      end


      def to_indexed_json
        self.to_json(:methods => [:attachment])
      end

      def attachment        
          path_to_file = "#{Rails.application.config.document_library}#{path}/#{filename}"
          Base64.encode64(open(path_to_file) { |file| file.read })
      end

      def self.search(query, options)
        tire.search do
          query { string "#{query}", :default_operator => :AND, :default_field => 'attachment', :fields => ['filename', 'attachment', 'tags'] }
          highlight :attachment
          page = (options[:page] || 1).to_i
          search_size = options[:per_page] || DEFAULT_PAGE_SIZE
          from (page -1) * search_size
          size search_size
          sort { by :_score, :desc }
          if (options[:facet])
            filter :terms, :tags => [options[:facet]]
            facet 'global-tags', :global => true do
              terms :tags
            end
            facet 'current-tags' do
              terms :tags
            end
          end
        end
      end
    end

Hope it helps,