xapian-fu 1.1.1 → 1.1.2

data/CHANGELOG.rdoc

@@ -0,0 +1,31 @@
+=== 1.1.2 (26th August 2010)
+
+* Spelling correction support
+
+=== 1.1.1 (21st April 2010)
+
+* Support disabling stopping (as per documentation!)
+
+=== 1.1.0 (14th December 2009)
+
+* 64bit support and Ruby 1.9.1 support. On-disk format changed.
+
+=== 1.0.1 (9th September 2009)
+
+* First high quality release. On-disk format changed.
+
+  * Lots more documentation
+  * Ordering
+  *	Result size limiting
+  * Will Paginate support
+  * Stemming support
+  * Stopping support
+  * Field storage improvements
+  * Field tokenization and search support
+  * Query parsing refactor
+  * search options improvements
+
+=== 0.2 (June 2009)
+
+* Initial release
+

data/README.rdoc

@@ -62,6 +62,17 @@ Simple integration with the will_paginate Rails helpers.
   @results = db.search("mountain", :page => 1, :per_page => 5)
   will_paginate @results
 
+== Spelling correction
+
+Spelling suggestions, like Google's "Did you mean..." feature:
+
+  db = XapianDb.new(:dir => 'example.db', :create => true)
+  db << "There is a mouse in this house"
+  @results = db.search "moose house"
+  unless @results.corrected_query.empty?
+    puts "Did you mean '#{@results.corrected_query}'"
+  end
+
 == Transactions support
 
 Ensure that a group of documents are either entirely added to the
@@ -173,7 +184,7 @@ perhaps by reindexing once in a while.
 = More Info
 
 Author::  John Leach  (mailto:john@johnleach.co.uk)
-Copyright:: Copyright (c) 2009 John Leach
+Copyright:: Copyright (c) 2009-2010 John Leach
 License:: MIT (The Xapian library is GPL)
 Mailing list:: http://rubyforge.org/mailman/listinfo/xapian-fu-discuss
 Web page:: http://johnleach.co.uk/documents/xapian-fu

data/lib/xapian_fu/xapian_db.rb

@@ -57,6 +57,17 @@ module XapianFu #:nodoc:
   #
   #   db = XapianDb.new(:language => :italian, :stopper => false)
   #
+  # == Spelling suggestions
+  #
+  # The <tt>:spelling</tt> option controls generation of a spelling
+  # dictionary during indexing and its use during searches. When
+  # enabled, Xapian will build a dictionary of words for the database
+  # whilst indexing documents and will enable spelling suggestion by
+  # default for searches.  Building the dictionary will impact
+  # indexing performance and database size. It is enabled by default.
+  # See the search section for information on getting spelling
+  # correction information during searches.
+  #
   # == Fields and values
   #
   # The <tt>:store</tt> option specifies which document fields should
@@ -101,9 +112,11 @@ module XapianFu #:nodoc:
     attr_reader :fields
     # An array of fields that will not be indexed
     attr_reader :unindexed_fields
+    # Whether this db will generate a spelling dictionary during indexing
+    attr_reader :spelling
 
     def initialize( options = { } )
-      @options = { :index_positions => true }.merge(options)
+      @options = { :index_positions => true, :spelling => true }.merge(options)
       @dir = @options[:dir]
       @index_positions = @options[:index_positions]
       @db_flag = Xapian::DB_OPEN
@@ -118,6 +131,7 @@ module XapianFu #:nodoc:
       @store_values << @options[:sortable]
       @store_values << @options[:collapsible]      
       @store_values = @store_values.flatten.uniq.compact
+      @spelling = @options[:spelling]
     end
 
     # Return a new stemmer object for this database
@@ -130,12 +144,12 @@ module XapianFu #:nodoc:
       StopperFactory.stopper_for(@stopper)
     end
 
-    # The writable Xapian database
+    # The writable Xapian::WritableDatabase
     def rw
       @rw ||= setup_rw_db
     end
 
-    # The read-only Xapian database
+    # The read-only Xapian::Database
     def ro
       @ro ||= setup_ro_db
     end
@@ -157,7 +171,8 @@ module XapianFu #:nodoc:
     alias_method "<<", :add_doc
 
     # Conduct a search on the Xapian database, returning an array of
-    # XapianDoc objects for the matches.  
+    # XapianFu::XapianDoc objects for the matches wrapped in a
+    # XapianFu::ResultSet.
     #
     # The <tt>:limit</tt> option sets how many results to return.  For
     # compatability with the <tt>will_paginate</tt> plugin, the
@@ -178,13 +193,19 @@ module XapianFu #:nodoc:
     # to collapse (group) the results on.  Works a bit like the
     # SQL <tt>GROUP BY</tt> behaviour
     #
+    # The <tt>:spelling</tt> option controls whether spelling
+    # suggestions will be made for queries. It defaults to whatever
+    # the database spelling setting is (true by default).  When
+    # enabled, spelling suggestions are available using the
+    # XapianFu::ResultSet <tt>corrected_query</tt> method.
+    #
     # For additional options on how the query is parsed, see
     # XapianFu::QueryParser
     
     def search(q, options = {})
       defaults = { :page => 1, :reverse => false,
         :boolean => true, :boolean_anycase => true, :wildcards => true,
-        :lovehate => true, :spelling => true, :pure_not => false }
+        :lovehate => true, :spelling => spelling, :pure_not => false }
       options = defaults.merge(options)
       page = options[:page].to_i rescue 1
       page = page > 1 ? page - 1 : 0
@@ -247,6 +268,7 @@ module XapianFu #:nodoc:
         @rw
       else
         # In memory database
+        @spelling = false # inmemory doesn't support spelling
         @rw = Xapian::inmemory_open
       end
     end

data/lib/xapian_fu/xapian_doc.rb

@@ -256,7 +256,8 @@ module XapianFu #:nodoc:
       tg.database = db.rw
       tg.document = xapian_document
       tg.stopper = stopper if stopper
-      tg.stemmer = stemmer      
+      tg.stemmer = stemmer
+      tg.set_flags Xapian::TermGenerator::FLAG_SPELLING if db.spelling
       index_method = db.index_positions ? :index_text : :index_text_without_positions
       fields.each do |k,v|
         next if unindexed_fields.include?(k)

data/spec/xapian_db_spec.rb

@@ -275,15 +275,24 @@ describe XapianDb do
     end
 
     it "should provide a corrected spelling string by default" do
-      pending
-      xdb = XapianDb.new(:dir => tmp_dir + 'corrected_spelling', :create => true)
-      xdb.rw.add_spelling("house mouse louse")
+      xdb = XapianDb.new(:dir => tmp_dir + 'corrected_spelling', :create => true,
+                         :overwrite => true)
+      xdb << "there is a mouse in this house"
+      xdb.flush
+      results = xdb.search("there was a moose at our house")
+      results.corrected_query.should == "there was a mouse at our house"
+    end
+
+    it "should not provide corrected spellings when disabled" do
+      xdb = XapianDb.new(:dir => tmp_dir + 'no_corrected_spelling', :create => true,
+                         :overwrite => true, :spelling => false)
       xdb << "there is a mouse in this house"
       xdb.flush
-      results = xdb.search("moose")
-      results.corrected_query.should == "mouse"
+      results = xdb.search("there was a moose at our house")
+      results.corrected_query.should == ""
     end
 
+
     it "should do phrase matching by default when then :default_op option is :phrase"
 
     it "should do AND_MAYBE matching by default when the :default_op option is :and_maybe"

metadata

@@ -1,7 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: xapian-fu
 version: !ruby/object:Gem::Version 
-  version: 1.1.1
+  hash: 23
+  prerelease: false
+  segments: 
+  - 1
+  - 1
+  - 2
+  version: 1.1.2
 platform: ruby
 authors: 
 - John Leach
@@ -9,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-04-21 00:00:00 +01:00
+date: 2010-08-26 00:00:00 +01:00
 default_executable: 
 dependencies: []
 
@@ -22,6 +28,7 @@ extensions: []
 extra_rdoc_files: 
 - README.rdoc
 - LICENSE
+- CHANGELOG.rdoc
 files: 
 - lib/xapian_fu.rb
 - lib/xapian_fu/xapian_doc_value_accessor.rb
@@ -53,8 +60,68 @@ files:
 - examples/ar_query.rb
 - README.rdoc
 - LICENSE
+- CHANGELOG.rdoc
+- spec/xapian_doc_spec.rb
+- spec/xapian_db_spec.rb
+- spec/stopper_factory_spec.rb
+- spec/fixtures/film_data/x86_64-linux~1.8.7/value.baseA
+- spec/fixtures/film_data/x86_64-linux~1.8.7/position.baseA
+- spec/fixtures/film_data/x86_64-linux~1.8.7/record.baseA
+- spec/fixtures/film_data/x86_64-linux~1.8.7/value.DB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/postlist.baseA
+- spec/fixtures/film_data/x86_64-linux~1.8.7/postlist.DB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/termlist.baseB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/termlist.baseA
+- spec/fixtures/film_data/x86_64-linux~1.8.7/postlist.baseB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/value.baseB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/record.baseB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/flintlock
+- spec/fixtures/film_data/x86_64-linux~1.8.7/termlist.DB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/record.DB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/position.DB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/position.baseB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/iamflint
+- spec/fixtures/film_data/i486-linux~1.8.7/value.baseA
+- spec/fixtures/film_data/i486-linux~1.8.7/position.baseA
+- spec/fixtures/film_data/i486-linux~1.8.7/record.baseA
+- spec/fixtures/film_data/i486-linux~1.8.7/value.DB
+- spec/fixtures/film_data/i486-linux~1.8.7/postlist.baseA
+- spec/fixtures/film_data/i486-linux~1.8.7/postlist.DB
+- spec/fixtures/film_data/i486-linux~1.8.7/termlist.baseB
+- spec/fixtures/film_data/i486-linux~1.8.7/termlist.baseA
+- spec/fixtures/film_data/i486-linux~1.8.7/postlist.baseB
+- spec/fixtures/film_data/i486-linux~1.8.7/value.baseB
+- spec/fixtures/film_data/i486-linux~1.8.7/record.baseB
+- spec/fixtures/film_data/i486-linux~1.8.7/flintlock
+- spec/fixtures/film_data/i486-linux~1.8.7/termlist.DB
+- spec/fixtures/film_data/i486-linux~1.8.7/record.DB
+- spec/fixtures/film_data/i486-linux~1.8.7/position.DB
+- spec/fixtures/film_data/i486-linux~1.8.7/position.baseB
+- spec/fixtures/film_data/i486-linux~1.8.7/iamflint
+- spec/fixtures/film_data/x86_64-linux~1.9.1/value.baseA
+- spec/fixtures/film_data/x86_64-linux~1.9.1/position.baseA
+- spec/fixtures/film_data/x86_64-linux~1.9.1/record.baseA
+- spec/fixtures/film_data/x86_64-linux~1.9.1/value.DB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/postlist.baseA
+- spec/fixtures/film_data/x86_64-linux~1.9.1/postlist.DB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/termlist.baseB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/termlist.baseA
+- spec/fixtures/film_data/x86_64-linux~1.9.1/postlist.baseB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/value.baseB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/record.baseB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/flintlock
+- spec/fixtures/film_data/x86_64-linux~1.9.1/termlist.DB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/record.DB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/position.DB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/position.baseB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/iamflint
+- spec/fixtures/film_data.rb
+- spec/xapian_doc_value_accessor_spec.rb
+- spec/build_db_for_value_testing.rb
+- spec/query_parser_spec.rb
+- spec/spec.opts
 has_rdoc: true
-homepage: http://github.com/johnl/xapian-fu/tree/master
+homepage: http://github.com/johnl/xapian-fu
 licenses: []
 
 post_install_message: 
@@ -67,21 +134,27 @@ rdoc_options:
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
       version: "0"
-  version: 
 required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
       version: "0"
-  version: 
 requirements: []
 
 rubyforge_project: xapian-fu
-rubygems_version: 1.3.5
+rubygems_version: 1.3.7
 signing_key: 
 specification_version: 3
 summary: A Ruby interface to the Xapian search engine