# encoding: utf-8 module XapianDb # The indexer creates a Xapian::Document from an object. They object must be an instance # of a class that has a blueprint configuration. # @author Gernot Kogler class Indexer # Constructor # @param [XapianDb::Database] database The database to use (needed to build a spelling index) # @param [XapianDb::DocumentBlueprint] document_blueprint The blueprint to use def initialize(database, document_blueprint) @database, @document_blueprint = database, document_blueprint end # Build the document for an object. The object must respond to 'xapian_id'. # The configured adapter should implement this method. # @return [Xapian::Document] The xapian document (see http://xapian.org/docs/sourcedoc/html/classXapian_1_1Document.html) def build_document_for(obj) @obj = obj @blueprint = DocumentBlueprint.blueprint_for(@obj.class) @xapian_doc = Xapian::Document.new @xapian_doc.data = @obj.xapian_id store_fields index_text @xapian_doc end private # Store all configured fields def store_fields # We store the class name of the object at position 0 @xapian_doc.add_value(0, @obj.class.name) @blueprint.attribute_names.each do |attribute| block = @blueprint.block_for_attribute attribute if block value = @obj.instance_eval(&block) else value = @obj.send(attribute) end @xapian_doc.add_value(@blueprint.value_index_for(attribute), value.to_yaml) end end # Index all configured text methods def index_text setup_language_helpers term_generator = Xapian::TermGenerator.new term_generator.database = @database.writer term_generator.document = @xapian_doc if @stemmer term_generator.stemmer = @stemmer term_generator.stopper = @stopper unless @stopper.nil? # Enable the creation of a spelling dictionary if the database is not in memory term_generator.set_flags Xapian::TermGenerator::FLAG_SPELLING if @database.is_a? XapianDb::PersistentDatabase end # Index the primary key as a unique term @xapian_doc.add_term("Q#{@obj.xapian_id}") # Index the class with the field name term_generator.index_text("#{@obj.class}".downcase, 1, "XINDEXED_CLASS") @xapian_doc.add_term("C#{@obj.class}") # @blueprint.indexed_methods_hash.keys.sort.each do |method| # options = @blueprint.indexed_methods_hash[method] # if options.block # obj = @obj.instance_eval(&options.block) # else # obj = @obj.send(method) # end # unless obj.nil? # values = get_values_to_index_from obj # values.each do |value| # # Add value with field name # term_generator.index_text(value.to_s.downcase, options.weight, "X#{method.upcase}") # # Add value without field name # term_generator.index_text(value.to_s.downcase) # end # end # end @blueprint.indexed_method_names.each do |method| options = @blueprint.options_for_indexed_method method if options.block obj = @obj.instance_eval(&options.block) else obj = @obj.send(method) end unless obj.nil? values = get_values_to_index_from obj values.each do |value| # Add value with field name term_generator.index_text(value.to_s.downcase, options.weight, "X#{method.upcase}") # Add value without field name term_generator.index_text(value.to_s.downcase) end end end end private # Configure the stemmer and stopper to use def setup_language_helpers # Do we have a language config on the blueprint? if @blueprint.lang_method lang = @obj.send(@blueprint.lang_method) if lang && LANGUAGE_MAP.has_key?(lang.to_sym) @stemmer = XapianDb::Repositories::Stemmer.stemmer_for lang.to_sym @stopper = XapianDb::Repositories::Stopper.stopper_for lang.to_sym return end end # Use the global config @stemmer = XapianDb::Config.stemmer @stopper = XapianDb::Config.stopper end # Get the values to index from an object def get_values_to_index_from(obj) # if it's an array, that's fine return obj if obj.is_a? Array # if the object responds to attributes and attributes is a hash, # we use the attributes values (works well for active_record and datamapper objects) return obj.attributes.values if obj.respond_to?(:attributes) && obj.attributes.is_a?(Hash) # The object is unkown and will be indexed by its to_s method return [obj] end end end