xapian_db 0.5.15 → 1.0

data/CHANGELOG.md

@@ -1,8 +1,14 @@
+##1.0 (August 17th, 2011)
+
+Features:
+
+  - find similar documents based on one or more reference documents
+
 ##0.5.15 (July 8th, 2011)
 
 Features:
 
-  - faster installation if the new, dependent gem containig xapian (xapian-ruby) is already installed
+  - faster install if the new, dependent gem containig xapian (xapian-ruby) is already installed
 
 ##0.5.14 (July 7th, 2011)
 

data/README.rdoc

@@ -232,7 +232,19 @@ A global facet search always groups the results by the class of the indexed obje
     puts "#{name}: #{count} hits"
   end
 
-At the class level, any attribute can be used for a facet query.
+At the class level, any attribute can be used for a facet query. Use facet queries on attributes that store atomic values like strings, numbers or dates.
+If you use it on attributes that contain collections (like an array of strings), you might get unexpected results.
+
+=== Find similar documents
+
+If you have a rearch result, you can search for similar documents by selecting one or more documents from your result and passing them to the find_similar_to method:
+
+  results = XapianDb.search("moose")
+  similar = XapianDb.find_similar_to results.first
+
+It works like this: The xapian engine extracts the most selective terms from the passed documents. Then, a
+new query is executed with the retrieved terms combined with OR operators.
+This method works best if your models contain large amounts of text.
 
 === Transactions
 

data/lib/xapian_db/adapters/base_adapter.rb

@@ -47,6 +47,10 @@ module XapianDb
                result
              end
 
+             define_singleton_method(:find_similar_to) do |reference|
+              return XapianDb.database.find_similar_to reference, :class => klass
+             end
+
              # Add a method to search atribute facets of this class
              define_singleton_method(:facets) do |attr_name, expression|
 

data/lib/xapian_db/database.rb

@@ -92,6 +92,37 @@ module XapianDb
       result
     end
 
+    # Find documents that are similar to one or more reference documents. It is basically
+    # the implementation of this suggestion: http://trac.xapian.org/wiki/FAQ/FindSimilar
+    # @param [Array<Xapian::Document> or Xapian::Document] docs One or more reference docs
+    # @param [Hash] options query options
+    # @option options [Class] :class an indexed class; if a class is passed, the result will
+    #   contain objects of this class only
+    # @return [XapianDb::Resultset] The resultset
+    def find_similar_to(docs, options={})
+      docs = [docs].flatten
+      reference = Xapian::RSet.new
+      docs.each { |doc| reference.add_document doc.docid }
+      pk_terms    = docs.map { |doc| "Q#{doc.data}" }
+      class_terms = docs.map { |doc| "C#{doc.indexed_class}" }
+
+      relevant_terms = Xapian::Enquire.new(reader).eset(40, reference).terms.map {|e| e.name } - pk_terms - class_terms
+      relevant_terms.reject! { |term| term =~ /INDEXED_CLASS/ }
+
+      reference_query = Xapian::Query.new Xapian::Query::OP_OR, pk_terms
+      terms_query     = Xapian::Query.new Xapian::Query::OP_OR, relevant_terms
+      final_query     = Xapian::Query.new Xapian::Query::OP_AND_NOT, terms_query, reference_query
+      if options[:class]
+        class_scope = "indexed_class:#{options[:class].name.downcase}"
+        @query_parser ||= QueryParser.new(self)
+        class_query   = @query_parser.parse(class_scope)
+        final_query   = Xapian::Query.new Xapian::Query::OP_AND, class_query, final_query
+      end
+      enquiry       = Xapian::Enquire.new(reader)
+      enquiry.query = final_query
+      Resultset.new(enquiry, :db_size => self.size)
+    end
+
     # A very simple implementation of facets limited to the class facets.
     # @param [String] expression A valid search expression (see {#search} for examples).
     # @return [Hash<Class, Integer>] A hash containing the classes and the hits per class

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: xapian_db
 version: !ruby/object:Gem::Version
-  version: 0.5.15
+  version: '1.0'
   prerelease: 
 platform: ruby
 authors:
@@ -9,12 +9,12 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2011-07-07 00:00:00.000000000 +02:00
+date: 2011-08-17 00:00:00.000000000 +02:00
 default_executable: 
 dependencies:
 - !ruby/object:Gem::Dependency
   name: daemons
-  requirement: &2153478220 !ruby/object:Gem::Requirement
+  requirement: &70169658679640 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -22,10 +22,10 @@ dependencies:
         version: 1.0.10
   type: :runtime
   prerelease: false
-  version_requirements: *2153478220
+  version_requirements: *70169658679640
 - !ruby/object:Gem::Dependency
   name: xapian-ruby
-  requirement: &2153476060 !ruby/object:Gem::Requirement
+  requirement: &70169658679180 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -33,10 +33,10 @@ dependencies:
         version: 1.2.6
   type: :runtime
   prerelease: false
-  version_requirements: *2153476060
+  version_requirements: *70169658679180
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &2153475460 !ruby/object:Gem::Requirement
+  requirement: &70169658678720 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -44,10 +44,10 @@ dependencies:
         version: 2.3.1
   type: :development
   prerelease: false
-  version_requirements: *2153475460
+  version_requirements: *70169658678720
 - !ruby/object:Gem::Dependency
   name: simplecov
-  requirement: &2153474780 !ruby/object:Gem::Requirement
+  requirement: &70169658678120 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -55,10 +55,10 @@ dependencies:
         version: 0.3.7
   type: :development
   prerelease: false
-  version_requirements: *2153474780
+  version_requirements: *70169658678120
 - !ruby/object:Gem::Dependency
   name: beanstalk-client
-  requirement: &2153474160 !ruby/object:Gem::Requirement
+  requirement: &70169658677520 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -66,7 +66,7 @@ dependencies:
         version: 1.1.0
   type: :development
   prerelease: false
-  version_requirements: *2153474160
+  version_requirements: *70169658677520
 description: XapianDb is a ruby gem that combines features of nosql databases and
   fulltext indexing. It is based on Xapian, an efficient and powerful indexing library
 email: gernot.kogler (at) garaio (dot) com
@@ -112,8 +112,6 @@ files:
 - lib/xapian_db/utilities.rb
 - lib/xapian_db.rb
 - tasks/beanstalk_worker.rake
-- xapian_source/xapian-bindings-1.2.6.tar.gz
-- xapian_source/xapian-core-1.2.6.tar.gz
 - LICENSE
 - README.rdoc
 - CHANGELOG.md
@@ -145,7 +143,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: 1.3.6
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.6.2
+rubygems_version: 1.3.9.2
 signing_key: 
 specification_version: 3
 summary: Ruby library to use a Xapian db as a key/value store with high performance