xapian_db 1.2.4.7 → 1.2.5

data/CHANGELOG.md

@@ -1,4 +1,15 @@
-##1.2.4.7 (Decmber 17th, 2012)
+##1.2.5 (January 4th, 2013)
+
+Changes:
+
+  - Define the min length a term must have to make it into the index (see README)
+  - define if a method should be indexed with its method name so you can do field searches (e.g. name:kogler); defaults to true
+
+Fixes:
+
+  - query result creation optimized (lower memory footprint, better performance)
+
+##1.2.4.7 (December 17th, 2012)
 
 Fixes:
 

data/README.rdoc

@@ -69,6 +69,7 @@ You can override these defaults by placing a config file named 'xapian_db.yml' i
   defaults: &defaults
     adapter: datamapper # Avaliable adapters: :active_record, :datamapper
     language: de        # Global language; can be overridden for specific blueprints
+    term_min_length: 2  # Ignore single character terms
 
   development:
     database: db/xapian_db/development
@@ -139,6 +140,12 @@ You can add a type information to an attribute. As of now the special types :str
       blueprint.attribute :updated_at,    :as => :date_time
     end
 
+If you don't need field searches for an attribute, turn off the prefixed option (makes your index smaller and more efficient):
+
+    XapianDb::DocumentBlueprint.setup(:Person) do |blueprint|
+      blueprint.attribute :complex_object, prefixed: false
+    end
+
 You can override the global adapter configuration in a specific blueprint. Let's say you use ActiveRecord, but you have
 one more class that is not stored in the database, but you want it to be indexed:
 

data/lib/xapian_db/config.rb

@@ -48,13 +48,18 @@ module XapianDb
       def resque_queue
         @config.instance_variable_get("@_resque_queue") || 'xapian_db'
       end
+
+      def term_min_length
+        @config.instance_variable_get("@_term_min_length") || 1
+      end
+
     end
 
     # ---------------------------------------------------------------------------------
     # DSL methods
     # ---------------------------------------------------------------------------------
 
-    attr_reader :_database, :_adapter, :_writer, :_beanstalk_daemon, :_resque_queue, :_stemmer, :_stopper
+    attr_reader :_database, :_adapter, :_writer, :_beanstalk_daemon, :_resque_queue, :_stemmer, :_stopper, :_term_min_length
 
     # Set the global database to use
     # @param [String] path The path to the database. Either apply a file sytem path or :memory
@@ -134,6 +139,11 @@ module XapianDb
       @_stopper = lang == :none ? nil : XapianDb::Repositories::Stopper.stopper_for(lang)
     end
 
+    # Set minimum length a term must have to get indexed; 2 is a good value to start
+    # @param [Integer] length The minimum length
+    def term_min_length(length)
+      @_term_min_length = length
+    end
   end
 
 end

data/lib/xapian_db/document_blueprint.rb

@@ -357,7 +357,7 @@ module XapianDb
           # Is it a method name with options?
           if args.last.is_a? Hash
             options = args.last
-            assert_valid_keys options, :weight
+            assert_valid_keys options, :weight, :prefixed
             @indexed_methods_hash[args.first] = IndexOptions.new(options.merge(:block => block))
           else
             add_indexes_from args
@@ -398,14 +398,15 @@ module XapianDb
     # Options for an indexed method
     class IndexOptions
 
-      attr_reader :weight, :block
+      attr_reader :weight, :prefixed, :block
 
       # Constructor
       # @param [Hash] options
       # @option options [Integer] :weight (1) The weight for the indexed value
       def initialize(options = {})
-        @weight = options[:weight] || 1
-        @block  = options[:block]
+        @weight   = options[:weight] || 1
+        @prefixed = options[:prefixed].nil? ? true : options[:prefixed]
+        @block    = options[:block]
       end
 
     end

data/lib/xapian_db/indexer.rb

@@ -85,13 +85,17 @@ module XapianDb
         unless obj.nil?
           values = get_values_to_index_from obj
           values.each do |value|
+            terms = value.to_s.downcase
             # Add value with field name
-            term_generator.index_text(value.to_s.downcase, options.weight, "X#{method.upcase}")
+            term_generator.index_text(terms, options.weight, "X#{method.upcase}") if options.prefixed
             # Add value without field name
-            term_generator.index_text(value.to_s.downcase, options.weight)
+            term_generator.index_text(terms, options.weight)
           end
         end
       end
+
+      terms_to_ignore = @xapian_doc.terms.select{ |term| term.term.length < XapianDb::Config.term_min_length }
+      terms_to_ignore.each { |term| @xapian_doc.remove_term term.term }
     end
 
     # Get the values to index from an object

data/lib/xapian_db/railtie.rb

@@ -50,6 +50,7 @@ module XapianDb
         config.beanstalk_daemon_url @beanstalk_daemon
         config.resque_queue @resque_queue
         config.language @language.try(:to_sym)
+        config.term_min_length @term_min_length
       end
 
     end
@@ -71,6 +72,7 @@ module XapianDb
       @beanstalk_daemon = env_config["beanstalk_daemon"]
       @resque_queue     = env_config["resque_queue"]
       @language         = env_config["language"]
+      @term_min_length  = env_config["term_min_length"]
     end
 
     # set default config options
@@ -79,6 +81,7 @@ module XapianDb
       @adapter          = :active_record
       @writer           = :direct
       @beanstalk_daemon = nil
+      @term_min_length  = 1
     end
 
   end

data/lib/xapian_db/resultset.rb

@@ -54,8 +54,6 @@ module XapianDb
       return build_empty_resultset if enquiry.nil?
       db_size              = options.delete :db_size
       @spelling_suggestion = options.delete :spelling_suggestion
-      @hits                = enquiry.mset(0, db_size).matches_estimated
-      return build_empty_resultset if @hits == 0
 
       limit                = options.delete :limit
       page                 = options.delete :page
@@ -63,18 +61,21 @@ module XapianDb
       raise ArgumentError.new "unsupported options for resultset: #{options}" if options.size > 0
       raise ArgumentError.new "db_size option is required" unless db_size
 
-      limit    = limit.nil? ? @hits : limit.to_i
+      limit    = limit.nil? ? db_size : limit.to_i
       per_page = per_page.nil? ? limit : per_page.to_i
       page     = page.nil? ? 1 : page.to_i
       offset   = (page - 1) * per_page
-      @total_pages  = (limit / per_page.to_f).ceil
       count  = offset + per_page < limit ? per_page : limit - offset
-      raise ArgumentError.new "page #{@page} does not exist" if @hits > 0 && offset >= limit
 
       result_window = enquiry.mset(offset, count)
+      @hits = result_window.matches_estimated
+      return build_empty_resultset if @hits == 0
+      raise ArgumentError.new "page #{@page} does not exist" if @hits > 0 && offset >= limit
+
       self.replace result_window.matches.map{|match| decorate(match).document}
+      @total_pages  = (limit / per_page.to_f).ceil
       @current_page = page
-      @limit_value = per_page
+      @limit_value  = per_page
     end
 
     # The previous page number
@@ -111,4 +112,4 @@ module XapianDb
 
   end
 
-end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: xapian_db
 version: !ruby/object:Gem::Version
-  version: 1.2.4.7
+  version: 1.2.5
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-12-17 00:00:00.000000000 Z
+date: 2013-01-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: daemons
@@ -244,9 +244,6 @@ required_ruby_version: !ruby/object:Gem::Requirement
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
-      segments:
-      - 0
-      hash: 1251927671395109686
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements: