xapian-fu 1.5.0 → 1.5.1

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    MzU5N2ExNTgxZjc3NzlhZjkwMjhiY2UzZDcwMzZhNzQwODk0N2M2ZQ==
+  data.tar.gz: !binary |-
+    YWE3ZDUwYmMyNTdiZjg2NzdhZGNjNTNkYzJhYjg2NzAzNTkyYjg2OA==
+!binary "U0hBNTEy":
+  metadata.gz: !binary |-
+    ZDVmYmQ3YzA4OWUzYTZhNzEzYWU5NmMyMzU0ZDNmOTE2NDUyMDEyMDQwZTZk
+    YTI0MGMwMzNiN2YwMmY0NmNlYzFmOTlhNjIzNTU5ZGZhZWI0MmMwZmNjNGI1
+    MWYwYTQxYWZhMDQ3ZWExOWExM2Q5NGMzY2QyYjZkNmViYTJhMWQ=
+  data.tar.gz: !binary |-
+    NDE1OTM0NmQ2MThiZmVhYWU3YTYyNjEzZTIxNmE3MTRkZjRjYTI0MDhiNjg1
+    MGRmZWM5YmNmY2ZmZmQwZDYyNDYwOWU4NjdiMDY2NWRlMDgwOGRjZjdiMGZi
+    OGM4ZDgyODQ2ZWQxMzc2OTExOWY2ZjNlNWM1M2QyZDQwNTU1NjM=

data/CHANGELOG.rdoc

@@ -1,3 +1,21 @@
+=== 1.5.1 (17th July 2014)
+
+* You can now customize the parsed query by passing `:query_builder` to
+  `XapianDb#search`.
+
+* Add ability to pass a `PostingSource` when searching.
+
+* Add ability to specify how many documents to sample when searching.
+
+  This allows for accurate paging links, facet counts, etc.
+
+* Support a `:weight` option when declaring database fields.
+
+* `XapianDb#search` can now receive a `:ranges` option to disable range
+  parsing.
+
+* Facet values are now correctly marked as UTF-8.
+
 === 1.5.0 (23rd May 2012)
 
 * Support for custom term weights when indexing (Mike Ragalie)

data/lib/xapian_fu/posting_source.rb

@@ -0,0 +1,47 @@
+# A generic <tt>Xapian::PostingSource</tt>.
+class XapianFu::PostingSource < Xapian::PostingSource
+  def init(db)
+    @all = {}
+    @ids = db.postlist("").map(&:docid)
+
+    @ids.each do |id|
+      @all[id] = db.document(id)
+    end
+
+    @iter = @ids.each
+    @current = @iter.next
+    @db = db
+  end
+
+  def next(minweight)
+    @current = @iter.next
+  rescue StopIteration
+    @current = nil
+  end
+
+  def at_end
+    @current.nil?
+  end
+
+  def docid
+    @current
+  end
+
+  def get_termfreq_min
+    0
+  end
+
+  def get_termfreq_max
+    @db.doccount
+  end
+
+  def get_termfreq_est
+    @db.doccount
+  end
+
+  def get_maxweight
+    1
+  end
+end
+
+

data/lib/xapian_fu/query_parser.rb

@@ -97,8 +97,8 @@ module XapianFu #:nodoc:
       else
         qp = Xapian::QueryParser.new
         qp.database = xapian_database if xapian_database
-        qp.stopper = database.stopper if database
-        qp.stemmer = database.stemmer if database
+        qp.stopper = database.stopper if database && database.stopper
+        qp.stemmer = database.stemmer if database && database.stemmer
         qp.default_op = xapian_default_op
         qp.stemming_strategy = xapian_stemming_strategy
 
@@ -127,7 +127,7 @@ module XapianFu #:nodoc:
             string,
             prefix
           ))
-        end if database
+        end if database && @options.fetch(:ranges, true)
 
         @query_parser = qp
       end

data/lib/xapian_fu/result_set.rb

@@ -25,7 +25,9 @@ module XapianFu
 
       options[:spies].each do |name, spy|
         @facets[name] = spy.values.map do |value|
-          [@db.unserialize_value(name, value.term), value.termfreq]
+          term = value.term.force_encoding(Encoding::UTF_8)
+
+          [@db.unserialize_value(name, term), value.termfreq]
         end
       end if options[:spies]
 
@@ -40,7 +42,7 @@ module XapianFu
 
     # The estimated total number of pages of results this search could return
     def total_pages
-      (total_entries / per_page.to_f).round
+      (total_entries / per_page.to_f).ceil
     end
 
     # The previous page number, or nil if there are no previous pages available

data/lib/xapian_fu/version.rb

@@ -1,3 +1,3 @@
 module XapianFu #:nodoc:
-  VERSION = "1.5.0"
+  VERSION = "1.5.1"
 end

data/lib/xapian_fu/xapian_db.rb

@@ -138,6 +138,7 @@ module XapianFu #:nodoc:
     attr_reader :spelling
     attr_reader :sortable_fields
     attr_accessor :weights_function
+    attr :field_weights
 
     def initialize( options = { } )
       @options = { :index_positions => true, :spelling => true }.merge(options)
@@ -237,6 +238,16 @@ module XapianFu #:nodoc:
     # enabled, spelling suggestions are available using the
     # XapianFu::ResultSet <tt>corrected_query</tt> method.
     #
+    # The <tt>:check_at_least</tt> option controls how many documents
+    # will be sampled. This allows for accurate page and facet counts.
+    # Specifying the special value of <tt>:all</tt> will make Xapian
+    # sample every document in the database. Be aware that this can hurt
+    # your query performance.
+    #
+    # The <tt>:query_builder</tt> option allows you to pass a proc that
+    # will return the final query to be run. The proc receives the parsed
+    # query as its only argument.
+    #
     # The first parameter can also be <tt>:all</tt> or
     # <tt>:nothing</tt>, to match all documents or no documents
     # respectively.
@@ -254,9 +265,18 @@ module XapianFu #:nodoc:
       per_page = options[:per_page] || options[:limit] || 10
       per_page = per_page.to_i rescue 10
       offset = page * per_page
+
+      check_at_least = options.include?(:check_at_least) ? options[:check_at_least] : 0
+      check_at_least = self.size if check_at_least == :all
+
       qp = XapianFu::QueryParser.new({ :database => self }.merge(options))
       query = qp.parse_query(q.is_a?(Symbol) ? q : q.to_s)
       query = filter_query(query, options[:filter]) if options[:filter]
+
+      if options.include?(:query_builder)
+        query = options[:query_builder].call(query)
+      end
+
       enquiry = Xapian::Enquire.new(ro)
       setup_ordering(enquiry, options[:order], options[:reverse])
       if options[:collapse]
@@ -269,9 +289,14 @@ module XapianFu #:nodoc:
           accum
         end
       end
+
+      if options.include?(:posting_source)
+        query = Xapian::Query.new(Xapian::Query::OP_AND_MAYBE, query, Xapian::Query.new(options[:posting_source]))
+      end
+
       enquiry.query = query
 
-      ResultSet.new(:mset => enquiry.mset(offset, per_page),
+      ResultSet.new(:mset => enquiry.mset(offset, per_page, check_at_least),
                     :current_page => page + 1,
                     :per_page => per_page,
                     :corrected_query => qp.corrected_query,
@@ -376,6 +401,7 @@ module XapianFu #:nodoc:
       @store_values = []
       @sortable_fields = {}
       @boolean_fields = []
+      @field_weights = Hash.new(1)
       return nil if field_options.nil?
       default_opts = {
         :store => true,
@@ -405,6 +431,7 @@ module XapianFu #:nodoc:
         @unindexed_fields << name if opts[:index] == false
         @boolean_fields << name if opts[:boolean]
         @fields[name] = opts[:type]
+        @field_weights[name] = opts[:weight] if opts.include?(:weight)
       end
       @fields
     end

data/lib/xapian_fu/xapian_doc.rb

@@ -148,7 +148,7 @@ module XapianFu #:nodoc:
     # Compare IDs with another XapianDoc
     def ==(b)
       if b.is_a?(XapianDoc)
-        id == b.id
+        id == b.id && (db == b.db || db.dir == b.db.dir)
       else
         super(b)
       end
@@ -276,7 +276,7 @@ module XapianFu #:nodoc:
           v = v.to_s
         end
         # get the custom term weight if a weights function exists
-        weight = db.weights_function ? db.weights_function.call(k, v, fields).to_i : 1
+        weight = db.weights_function ? db.weights_function.call(k, v, fields).to_i : db.field_weights[k]
         # add value with field name
         tg.send(index_method, v, weight, 'X' + k.to_s.upcase)
         # add value without field name

data/spec/facets_spec.rb

@@ -5,20 +5,23 @@ tmp_dir = '/tmp/xapian_fu_test.db'
 describe "Facets support" do
 
   before do
+    FileUtils.rm_rf(tmp_dir)
+
     @xdb = XapianFu::XapianDb.new(
       :dir => tmp_dir, :create => true, :overwrite => true,
       :fields => {
         :name      => { :index => true },
         :age       => { :type => Integer, :sortable => true },
-        :height    => { :type => Float, :sortable => true }
+        :height    => { :type => Float, :sortable => true },
+        :city      => { :store => true }
       }
     )
 
-    @xdb << {:name => "John A",   :age => 30, :height => 1.8}
-    @xdb << {:name => "John B",   :age => 35, :height => 1.8}
-    @xdb << {:name => "John C",   :age => 40, :height => 1.7}
-    @xdb << {:name => "John D",   :age => 40, :height => 1.7}
-    @xdb << {:name => "Markus",   :age => 35, :height => 1.7}
+    @xdb << {:name => "John A",   :age => 30, :height => 1.8, city: "NY"}
+    @xdb << {:name => "John B",   :age => 35, :height => 1.8, city: "NY"}
+    @xdb << {:name => "John C",   :age => 40, :height => 1.7, city: "SF"}
+    @xdb << {:name => "John D",   :age => 40, :height => 1.7, city: "NY"}
+    @xdb << {:name => "Markus",   :age => 35, :height => 1.7, city: "LA"}
     @xdb.flush
   end
 
@@ -31,4 +34,31 @@ describe "Facets support" do
     results.facets.keys.map(&:to_s).sort == %w(age height)
   end
 
+  it "should allow to set the minimum amount of documents to check" do
+    100.times do |i|
+      @xdb << {:name => "John A #{i}", :age => 30, :height => 1.8}
+      @xdb << {:name => "John B #{i}", :age => 35, :height => 1.8}
+      @xdb << {:name => "John C #{i}", :age => 40, :height => 1.7}
+      @xdb << {:name => "John D #{i}", :age => 40, :height => 1.7}
+      @xdb << {:name => "Markus #{i}", :age => 35, :height => 1.7}
+    end
+
+    @xdb.flush
+
+    results = @xdb.search("john", :facets => [:age, :height], :check_at_least => :all)
+
+    results.facets[:age].map(&:last).inject(0) { |t,i| t + i }.should == 404
+
+    results = @xdb.search(:all, :facets => [:age, :height], :check_at_least => :all)
+
+    results.facets[:age].map(&:last).inject(0) { |t,i| t + i }.should == 505
+  end
+
+  it "should return facet values in UTF-8" do
+    results = @xdb.search("john", {:facets => [:city]})
+
+    results.facets[:city].should == [["NY", 3], ["SF", 1]]
+
+    results.facets[:city].first.first.encoding.should == Encoding::UTF_8
+  end
 end

data/spec/xapian_db_spec.rb

@@ -423,6 +423,8 @@ describe XapianDb do
       results.previous_page.should == 1
       results.next_page.should == nil
       results.offset.should == 16
+      results = xdb.search(content, :page => 1, :per_page => 14)
+      results.total_pages.should == 3
     end
 
     it "should do searches with and without field names" do
@@ -496,6 +498,28 @@ describe XapianDb do
       xdb.search("liverpool").should be_empty
       xdb.search("city:liverpool").map(&:id).should == [2, 3]
     end
+
+    it "allows further refining of the parsed query" do
+      xdb = XapianDb.new(:dir => tmp_dir, :create => true,
+                         :fields => {
+                           :name => { :index => true },
+                           :age => { :boolean => true },
+                         }
+                        )
+
+      xdb << {:name => "John A", :age => 10}
+      xdb << {:name => "John B", :age => 11}
+
+      xdb.flush
+
+      xdb.search("john").size.should == 2
+
+      builder = lambda do |q|
+        Xapian::Query.new(Xapian::Query::OP_AND, Xapian::Query.new("XAGE10"), q)
+      end
+
+      xdb.search("john", :query_builder => builder).map(&:id).should == [1]
+    end
   end
 
   describe "filtering" do
@@ -621,6 +645,25 @@ describe XapianDb do
       docs.map { |d| d.id }.should == [1, 2]
     end
 
+    it "should not parse ranges when no ranges configured" do
+      xdb = XapianDb.new(:fields => {
+        :price => { :type => Integer, :sortable => true, :range_prefix => "$" },
+        :age   => { :type => Integer, :sortable => true }
+      })
+
+      xdb << XapianDoc.new(:price => 10, :age => 40)
+      xdb << XapianDoc.new(:price => 20, :age => 35)
+      xdb << XapianDoc.new(:price => 45, :age => 30)
+
+      docs = xdb.search("$20..40 OR age:40..50", ranges: false)
+
+      docs.should be_empty
+
+      docs = xdb.search("20")
+
+      docs.map { |d| d.id }.should == [2]
+    end
+
     it "should store values declared as to be collapsible" do
       xdb = XapianDb.new(:collapsible => :group_id)
       xdb << XapianDoc.new(:group_id => "666", :author => "Jim Jones")
@@ -758,5 +801,59 @@ describe XapianDb do
     end
   end
 
-end
+  describe "weights per field" do
+    it "should honor the :weight option when declaring fields" do
+      xdb = XapianDb.new(
+        :fields => {
+          :title       => {:weight => 20},
+          :abstract    => {:weight => 10},
+          :description => {:type => String}
+        }
+      )
+
+      xdb << {:id => 1, :title => "Programming Ruby: The Pragmatic Programmer's Guide", :abstract => "The programming language", :description => "This book is a tutorial and reference for the Ruby programming language."}
+      xdb << {:id => 2, :title => "The Ruby Programming Language", :abstract => "A great book", :description => "The Matz book."}
+      xdb << {:id => 3, :title => "The Rails Way", :abstract => "A good Rails book.", :description => "You have to know the language."}
+
+      xdb.search("language").map(&:id).should == [2, 1, 3]
+    end
+  end
+
+  describe "posting sources" do
+    class BoostLatest < Xapian::PostingSource
+      attr :docid
+
+      def init(db)
+        @db = db
+        @iter = db.postlist("").map(&:docid).each
+        @docid = @iter.next
+      end
+
+      def weight
+        @docid * 10
+      end
+
+      def next(minweight)
+        @docid = @iter.next
+      rescue StopIteration
+        @docid = nil
+      end
 
+      def at_end
+        @docid.nil?
+      end
+    end
+
+    it "allows to pass a custom posting source to boost results" do
+      xdb = XapianDb.new
+
+      xdb << {:id => 1, :name => "Foo"}
+      xdb << {:id => 2, :name => "Foo Bar"}
+      xdb << {:id => 3, :name => "Foo Bar Baz"}
+
+      xdb.search("foo").map(&:id).should == [1, 2, 3]
+
+      xdb.search("foo", :posting_source => BoostLatest.new).map(&:id).should == [3, 2, 1]
+    end
+  end
+end

data/spec/xapian_doc_spec.rb

@@ -6,8 +6,16 @@ require 'fileutils'
 
 describe XapianDoc do
 
-  it "should be equal to other XapianDoc objects with the same id" do
-    XapianDoc.new(:id => 666).should == XapianDoc.new(:id => 666)
+  it "should be equal to other XapianDoc objects with the same id belonging to the same database" do
+    xdb1 = XapianDb.new(:dir => "/tmp/foos")
+    xdb2 = XapianDb.new(:dir => "/tmp/foos")
+
+    XapianDoc.new({:id => 666}, :xapian_db => xdb1).should == XapianDoc.new({:id => 666}, :xapian_db => xdb1)
+    XapianDoc.new({:id => 666}, :xapian_db => xdb1).should == XapianDoc.new({:id => 666}, :xapian_db => xdb2)
+
+    xdb3 = XapianDb.new(:dir => "/tmp/bars")
+
+    XapianDoc.new({:id => 666}, :xapian_db => xdb1).should_not == XapianDoc.new({:id => 666}, :xapian_db => xdb3)
   end
 
   it "should not be equal to other XapianDoc objects with different ids" do

metadata

@@ -1,8 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: xapian-fu
 version: !ruby/object:Gem::Version
-  version: 1.5.0
-  prerelease: 
+  version: 1.5.1
 platform: ruby
 authors:
 - John Leach
@@ -14,37 +13,46 @@ date: 2012-05-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &12933040 !ruby/object:Gem::Requirement
-    none: false
+  requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
         version: 2.7.0
   type: :development
   prerelease: false
-  version_requirements: *12933040
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 2.7.0
 - !ruby/object:Gem::Dependency
   name: rake
-  requirement: &12928460 !ruby/object:Gem::Requirement
-    none: false
+  requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *12928460
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rdoc
-  requirement: &12907260 !ruby/object:Gem::Requirement
-    none: false
+  requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *12907260
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 description: A library to provide a more Ruby-like interface to the Xapian search
   engine.
 email: john@johnleach.co.uk
@@ -55,99 +63,99 @@ extra_rdoc_files:
 - LICENSE
 - CHANGELOG.rdoc
 files:
-- lib/xapian_fu.rb
-- lib/xapian_fu/xapian_doc_value_accessor.rb
+- lib/xapian-fu.rb
+- lib/xapian_fu/posting_source.rb
 - lib/xapian_fu/query_parser.rb
-- lib/xapian_fu/version.rb
-- lib/xapian_fu/xapian_db.rb
-- lib/xapian_fu/xapian_documents_accessor.rb
-- lib/xapian_fu/xapian_doc.rb
-- lib/xapian_fu/stopwords/russian.txt
-- lib/xapian_fu/stopwords/spanish.txt
-- lib/xapian_fu/stopwords/README
+- lib/xapian_fu/result_set.rb
+- lib/xapian_fu/stopper_factory.rb
 - lib/xapian_fu/stopwords/danish.txt
-- lib/xapian_fu/stopwords/french.txt
 - lib/xapian_fu/stopwords/dutch.txt
 - lib/xapian_fu/stopwords/english.txt
+- lib/xapian_fu/stopwords/finnish.txt
+- lib/xapian_fu/stopwords/french.txt
 - lib/xapian_fu/stopwords/german.txt
+- lib/xapian_fu/stopwords/hungarian.txt
+- lib/xapian_fu/stopwords/italian.txt
 - lib/xapian_fu/stopwords/norwegian.txt
+- lib/xapian_fu/stopwords/portuguese.txt
+- lib/xapian_fu/stopwords/README
+- lib/xapian_fu/stopwords/russian.txt
+- lib/xapian_fu/stopwords/spanish.txt
 - lib/xapian_fu/stopwords/swedish.txt
 - lib/xapian_fu/stopwords/update.rb
-- lib/xapian_fu/stopwords/italian.txt
-- lib/xapian_fu/stopwords/finnish.txt
-- lib/xapian_fu/stopwords/hungarian.txt
-- lib/xapian_fu/stopwords/portuguese.txt
-- lib/xapian_fu/result_set.rb
-- lib/xapian_fu/stopper_factory.rb
-- lib/xapian-fu.rb
-- examples/spider.rb
-- examples/ar_spider.rb
+- lib/xapian_fu/version.rb
+- lib/xapian_fu/xapian_db.rb
+- lib/xapian_fu/xapian_doc.rb
+- lib/xapian_fu/xapian_doc_value_accessor.rb
+- lib/xapian_fu/xapian_documents_accessor.rb
+- lib/xapian_fu.rb
 - examples/query.rb
-- examples/ar_query.rb
+- examples/spider.rb
 - README.rdoc
 - LICENSE
 - CHANGELOG.rdoc
-- spec/xapian_doc_spec.rb
-- spec/xapian_db_spec.rb
-- spec/stopper_factory_spec.rb
+- spec/build_db_for_value_testing.rb
 - spec/facets_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/flintlock
+- spec/fixtures/film_data/i486-linux~1.8.7/iamflint
 - 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/position.baseB
+- spec/fixtures/film_data/i486-linux~1.8.7/position.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/postlist.DB
+- spec/fixtures/film_data/i486-linux~1.8.7/record.baseA
 - 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/i486-linux~1.8.7/termlist.baseA
+- spec/fixtures/film_data/i486-linux~1.8.7/termlist.baseB
+- spec/fixtures/film_data/i486-linux~1.8.7/termlist.DB
+- spec/fixtures/film_data/i486-linux~1.8.7/value.baseA
+- spec/fixtures/film_data/i486-linux~1.8.7/value.baseB
+- spec/fixtures/film_data/i486-linux~1.8.7/value.DB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/flintlock
+- spec/fixtures/film_data/x86_64-linux~1.8.7/iamflint
+- spec/fixtures/film_data/x86_64-linux~1.8.7/position.baseA
+- spec/fixtures/film_data/x86_64-linux~1.8.7/position.baseB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/position.DB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/postlist.baseA
+- spec/fixtures/film_data/x86_64-linux~1.8.7/postlist.baseB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/postlist.DB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/record.baseA
+- spec/fixtures/film_data/x86_64-linux~1.8.7/record.baseB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/record.DB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/termlist.baseA
+- spec/fixtures/film_data/x86_64-linux~1.8.7/termlist.baseB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/termlist.DB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/value.baseA
+- spec/fixtures/film_data/x86_64-linux~1.8.7/value.baseB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/value.DB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/flintlock
+- spec/fixtures/film_data/x86_64-linux~1.9.1/iamflint
 - 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/position.baseB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/position.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/postlist.DB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/record.baseA
 - 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/x86_64-linux~1.9.1/termlist.baseA
+- spec/fixtures/film_data/x86_64-linux~1.9.1/termlist.baseB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/termlist.DB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/value.baseA
+- spec/fixtures/film_data/x86_64-linux~1.9.1/value.baseB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/value.DB
 - 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/stopper_factory_spec.rb
+- spec/xapian_db_spec.rb
+- spec/xapian_doc_spec.rb
+- spec/xapian_doc_value_accessor_spec.rb
 homepage: http://github.com/johnl/xapian-fu
 licenses: []
+metadata: {}
 post_install_message: 
 rdoc_options:
 - --title
@@ -158,81 +166,78 @@ rdoc_options:
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: xapian-fu
-rubygems_version: 1.8.11
+rubygems_version: 2.0.0
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: A Ruby interface to the Xapian search engine
 test_files:
-- spec/xapian_doc_spec.rb
-- spec/xapian_db_spec.rb
-- spec/stopper_factory_spec.rb
+- spec/build_db_for_value_testing.rb
 - spec/facets_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/flintlock
+- spec/fixtures/film_data/i486-linux~1.8.7/iamflint
 - 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/position.baseB
+- spec/fixtures/film_data/i486-linux~1.8.7/position.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/postlist.DB
+- spec/fixtures/film_data/i486-linux~1.8.7/record.baseA
 - 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/i486-linux~1.8.7/termlist.baseA
+- spec/fixtures/film_data/i486-linux~1.8.7/termlist.baseB
+- spec/fixtures/film_data/i486-linux~1.8.7/termlist.DB
+- spec/fixtures/film_data/i486-linux~1.8.7/value.baseA
+- spec/fixtures/film_data/i486-linux~1.8.7/value.baseB
+- spec/fixtures/film_data/i486-linux~1.8.7/value.DB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/flintlock
+- spec/fixtures/film_data/x86_64-linux~1.8.7/iamflint
+- spec/fixtures/film_data/x86_64-linux~1.8.7/position.baseA
+- spec/fixtures/film_data/x86_64-linux~1.8.7/position.baseB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/position.DB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/postlist.baseA
+- spec/fixtures/film_data/x86_64-linux~1.8.7/postlist.baseB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/postlist.DB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/record.baseA
+- spec/fixtures/film_data/x86_64-linux~1.8.7/record.baseB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/record.DB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/termlist.baseA
+- spec/fixtures/film_data/x86_64-linux~1.8.7/termlist.baseB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/termlist.DB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/value.baseA
+- spec/fixtures/film_data/x86_64-linux~1.8.7/value.baseB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/value.DB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/flintlock
+- spec/fixtures/film_data/x86_64-linux~1.9.1/iamflint
 - 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/position.baseB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/position.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/postlist.DB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/record.baseA
 - 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/x86_64-linux~1.9.1/termlist.baseA
+- spec/fixtures/film_data/x86_64-linux~1.9.1/termlist.baseB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/termlist.DB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/value.baseA
+- spec/fixtures/film_data/x86_64-linux~1.9.1/value.baseB
+- spec/fixtures/film_data/x86_64-linux~1.9.1/value.DB
 - spec/fixtures/film_data.rb
-- spec/xapian_doc_value_accessor_spec.rb
-- spec/build_db_for_value_testing.rb
 - spec/query_parser_spec.rb
-has_rdoc: 
+- spec/stopper_factory_spec.rb
+- spec/xapian_db_spec.rb
+- spec/xapian_doc_spec.rb
+- spec/xapian_doc_value_accessor_spec.rb

data/examples/ar_query.rb

@@ -1,35 +0,0 @@
-#!/usr/bin/ruby
-
-require 'rubygems'
-require 'benchmark'
-require 'lib/xapian_fu'
-include XapianFu
-require 'active_record'
-
-ActiveRecord::Base.establish_connection(
-   :adapter  => "mysql",
-   :host     => "localhost",
-   :username => "john",
-   :password => "john",
-   :database => "john_fametastic_dev" )
-
-class WpPost < ActiveRecord::Base
-  set_primary_key :ID
-end
-
-#puts WpPost.new.attributes.keys.join(' ')
-db = XapianDb.new(:dir => 'ar_spider.db')
-
-results = nil
-bm = Benchmark.measure do
-  results = db.search(ARGV.join(' '))
-end
-
-posts = WpPost.find(results.collect { |r| r.id })
-
-puts "Weight\tTitle"
-posts.each_with_index do |p,i|
-  puts "%.3f\t#{p.post_title}" % results[i].weight
-end
-
-puts "Search took %.5f seconds" % bm.total

data/examples/ar_spider.rb

@@ -1,37 +0,0 @@
-#!/usr/bin/ruby
-
-require 'rubygems'
-require 'benchmark'
-require 'lib/xapian_fu'
-include XapianFu
-require 'active_record'
-
-ActiveRecord::Base.establish_connection(
-   :adapter  => "mysql",
-   :host     => "localhost",
-   :username => "john",
-   :password => "john",
-   :database => "john_fametastic_dev" )
-
-class WpPost < ActiveRecord::Base
-  set_primary_key :ID
-end
-
-#puts WpPost.new.attributes.keys.join(' ')
-db = XapianDb.new(:dir => 'ar_spider.db', :overwrite => true)
-
-count = 0
-indexing_time = 0.0
-WpPost.find_in_batches do |posts|
-  db.transaction do
-    puts "Indexing wp_posts #{count} to #{count += posts.size}"
-    posts.each do |post|
-      bm = Benchmark.measure do
-        db << XapianDoc.new(post.attributes.merge({ :id => post.id }))
-      end
-      indexing_time += bm.total
-    end
-  end
-  indexing_time += Benchmark.measure { db.flush }.total
-end
-puts "%i documents took %.4f seconds. %.2f per second" % [count, indexing_time, count / indexing_time]