dm-lucene-adapter 0.1.0-java

data/MIT-LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2008 Kristian Meier
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/lib/dm-lucene-adapter.rb

@@ -0,0 +1,8 @@
+require 'java'
+begin
+  include_class "de.saumya.lucene.LuceneService"
+rescue
+  require 'dm-lucene-adapter_ext'
+  retry
+end
+require 'dm_lucene_adapter/dm_lucene_adapter'

data/lib/dm_lucene_adapter/dm_lucene_adapter.rb

@@ -0,0 +1,196 @@
+module DataMapper
+  module Adapters
+    class LuceneAdapter < AbstractAdapter
+
+      private
+      def index_directory(model)
+        @path / "#{model.storage_name(name)}"
+      end
+
+      def lucene(model)
+        LuceneService.new(java.io.File.new(index_directory(model).to_s))
+      end
+
+      public
+
+      def initialize(name, options = {})
+        super
+        (@path = Pathname(@options[:path]).freeze).mkpath
+      end
+
+      # @param [Enumerable<Resource>] resources
+      #   The list of resources (model instances) to create
+      #
+      # @return [Integer]
+      #   The number of records that were actually saved into the data-store
+      #
+      # @api semipublic
+      def create(resources)
+        count = 0
+        indexer = lucene(resources.first.model).create_indexer
+        resources.each do |resource|
+          resource.id = indexer.next_id
+          map = {}
+          resource.attributes.each { |k,v| map[k.to_s] = v.to_s}
+          indexer.index(map)
+          count += 1
+        end
+        count
+      ensure
+        indexer.close if indexer
+      end
+
+      # @param [Query] query
+      #   the query to match resources in the datastore
+      #
+      # @return [Enumerable<Hash>]
+      #   an array of hashes to become resources
+      #
+      # @api semipublic
+      def read(query)
+        is_sorting = query.order.size > 1 || query.order[0].target.name != :id || query.order[0].operator != :asc
+        offset, limit = is_sorting ? [0, -1] : [query.offset, query.limit || -1]
+
+        resources = do_read(offset, limit, query)
+        resources.each do |resource|
+          query.fields.each do |field| 
+            attribute = field.name.to_s
+            resource[attribute] = field.typecast(resource[attribute])
+          end
+        end
+        
+        if is_sorting
+          #records = records.uniq if unique?
+          resources = query.sort_records(resources)
+          resources = query.limit_records(resources)
+        end
+        resources
+      end
+
+      private
+
+      def do_read(offset, limit, query)
+        reader = lucene(query.model).create_reader
+        if(query.conditions.nil?)
+          result = []
+          
+#p query
+# TODO set limit, offset to default of sorting is non default
+          reader.read_all(offset, limit).each do |resource|
+            map = {}
+            resource.each do |k,v|
+              map[k] = v
+            end
+            result << map
+          end
+          result
+        else
+          ops = query.conditions.operands
+          if(ops.size == 1 && ops[0].class == DataMapper::Query::Conditions::EqualToComparison && ops[0].subject.name == :id)
+            map = {}
+            reader.read(query.conditions.operands[0].value).each do |k,v|
+              map[k] = v
+            end
+            [map]
+          else
+            op = query.conditions.slug.to_s.upcase
+            lquery = make_query("", ops, op)
+            lquery.sub!(/#{op} $/, '') 
+            result = []
+            reader.read_all(offset, limit, lquery).each do |resource|
+              map = {}
+              resource.each do |k,v|
+                map[k] = v
+              end
+              result << map
+            end
+            result
+          end
+        end
+      ensure
+        reader.close if reader
+      end    
+
+      private
+
+      def make_query(lquery, ops, operator)
+        ops.each do |comp|
+          case comp.slug
+          when :like
+            lquery += "#{comp.subject.name.to_s}:#{comp.value}"
+            unless comp.value =~ /%|_|\?|\*/
+              lquery += "~"
+            end
+            lquery += " #{operator} "
+          when :eql
+            lquery += "#{comp.subject.name.to_s}:\"#{comp.value}\" #{operator} "
+          when :not
+            if lquery.size == 0
+              lquery = "NOT "
+            else
+              lquery.sub!(/#{operator}/, "NOT")
+            end
+            lquery = make_query(lquery, comp.operands, operator)
+          else
+            warn "ignore unsupported operand #{comp.slug}"
+          end
+        end
+        lquery
+      end
+
+      public
+
+      # @param [Hash(Property => Object)] attributes
+      #   hash of attribute values to set, keyed by Property
+      # @param [Collection] collection
+      #   collection of records to be updated
+      #
+      # @return [Integer]
+      #   the number of records updated
+      #
+      # @api semipublic
+      def update(attributes, collection)
+        count = 0
+        service = lucene(collection.model)
+        deleter = service.create_deleter
+        resources = read(collection.query)
+        resources.each do |resource|
+          deleter.delete(resource["id"])
+        end
+        deleter.close
+        deleter = nil
+        indexer = service.create_indexer
+        attributes = attributes_as_fields(attributes)
+        resources.each do |resource|
+          resource.update(attributes)
+          map = {}
+          resource.each { |k,v| map[k.to_s] = v.to_s}
+          indexer.index(map)
+        end
+        count
+      ensure
+        indexer.close if indexer
+        deleter.close if deleter
+      end
+
+      # @param [Collection] collection
+      #   collection of records to be deleted
+      #
+      # @return [Integer]
+      #   the number of records deleted
+      #
+      # @api semipublic
+      def delete(collection)
+        count = 0
+        indexer = lucene(collection.model).create_deleter
+        collection.each do |resource|
+          indexer.delete(resource.id)
+          count += 1
+        end
+        count
+      ensure
+        indexer.close if indexer
+      end
+    end
+  end
+end

data/lib/dm_lucene_adapter/version.rb

@@ -0,0 +1,3 @@
+module DmLuceneAdapter
+  VERSION = '1.0.0'
+end

data/spec/dm_lucene_adapter_spec.rb

@@ -0,0 +1,148 @@
+require File.dirname(__FILE__) +  '/spec_helper'
+
+describe DataMapper::Adapters::LuceneAdapter do
+
+  it "should create" do
+    Book.create(:author => "kristian", :title => "me and the corner").new?.should be_false
+  end
+
+  it "should read all" do
+    size = Book.all.size
+    (1..3).each do
+      Book.create(:author => "kristian", :title => "me and the corner")
+    end
+    b = Book.all 
+    b.size.should == size + 3
+  end
+
+  it "should delete" do
+    books = []
+    (1..4).each do
+      books << Book.create(:author => "kristian", :title => "me and the corner")
+    end
+    id = books.last.id
+    size = Book.all.size
+    books.each do |b| 
+      b.destroy if b.id % 2 == 0
+    end
+    b = Book.all 
+    size.should == b.size + 2
+    book = Book.create(:author => "kristian", :title => "me and the corner")
+    id.should < book.id
+  end
+
+  it 'should read a single' do
+    book = Book.create(:author => "kristian", :title => "me and the corner")
+    b = Book.get(book.id)
+    b.id.should == book.id
+  end
+
+  it 'should update' do
+    book = Book.create(:author => "kristian", :title => "me and the corner")
+    book.author = "sanuka"
+    book.save
+    b = Book.get(book.id)
+    b.author.should == "sanuka"
+  end
+
+  describe "search" do
+
+    before :all do
+      @size = Book.all(:author => "sanuka").size
+      @len = 5
+      (1..@len).each do |i|
+        Book.create(:author => "kristian", :title => "me and the corner #{i}")
+        Book.create(:author => "sanuka", :title => "me and the corner #{i}")
+        Book.create(:author => "#{i}sanuka", :title => "me and the corner")
+        Book.create(:author => "#{i}sanuka#{i}", :title => "me and the corner")
+      end
+    end
+
+    describe "ascending" do
+
+      after :each do        
+        id = 0
+        @books.each do |b|
+          b.id.should > id
+          id = b.id
+        end
+      end
+
+      it 'should find 5 with simple query' do      
+        @books = Book.all(:author => "sanuka")
+        @books.size.should == @size + @len
+        @books.each { |b| b.author.should == "sanuka" }
+      end
+      
+      it 'should find 5 with not query' do      
+        @books = Book.all(:author.not => "sanuka")
+        @books.each { |b| b.author.should_not == "sanuka" }
+        (@books.size + @size + @len).should == Book.all.size
+      end
+      
+      it 'should find nothing with simple query' do
+        @books = Book.all(:author => "saumya")
+        @books.size.should == 0
+      end
+
+      it 'should find 5 with fuzzy query' do
+        @books = Book.all(:author.like => "sanaku")
+        @books.size.should == @size + @len
+        @books.each { |b| b.author.should =~ /sanuka/ }
+      end
+
+      it 'should find 5 with single char wildcards query' do
+        @books = Book.all(:author.like => "san?k?")
+        @books.size.should == @size + @len
+        @books.each { |b| b.author.should =~ /sanuka/ }
+      end
+
+      it 'should find 5 with wildcards query' do
+        @books = Book.all(:author.like => "sa*ka")
+        @books.size.should == @size + @len
+        @books.each { |b| b.author.should =~ /sanuka/ }
+      end
+
+      it 'should obey offset' do
+        @books = Book.all(:author.like => "san?k?", :limit => @size)
+        @books.size.should == @size
+      end
+
+      it 'should obey offset with empty query' do
+        @books = Book.all(:limit => @size)
+        @books.size.should == @size
+      end
+
+      it 'should obey offset and limit' do
+        @books = Book.all(:author.like => "san?k?", :offset => @size, :limit => @len)
+        @books.size.should == @len
+      end
+
+      it 'should obey offset and limit with empty query' do
+        @books = Book.all(:offset => @size, :limit => @len)
+        @books.size.should == @len
+      end
+    end
+    
+    describe "descending" do
+
+      after :each do        
+        id = 12311230123321
+        @books.each do |b|
+          b.id.should < id
+          id = b.id
+        end
+      end
+
+      it 'should obey offset and limit descending order' do
+        @books = Book.all(:author.like => "san?k?", :offset => @size, :limit => @len, :order => [:id.desc])
+        @books.size.should == @len
+      end
+      
+      it 'should obey offset and limit descending order with emtpy query' do
+        @books = Book.all(:offset => @len, :limit => @size, :order => [:id.desc])
+        @books.size.should == @size
+      end
+    end
+  end
+end

data/spec/spec.opts

@@ -0,0 +1,2 @@
+--colour
+--loadby random

data/spec/spec_helper.rb

@@ -0,0 +1,24 @@
+require 'rubygems'
+
+gem 'dm-core', ">0.10.0"
+require 'pathname'
+$LOAD_PATH << Pathname(__FILE__).dirname.parent.expand_path + 'lib'
+
+require 'dm-core'
+require 'dm-lucene-adapter'
+
+class Book
+
+  include DataMapper::Resource
+
+  property :id, Serial
+
+  property :author, String, :length => 128
+
+  property :title, String, :length => 255
+
+  property :published, Boolean, :default => true
+
+end
+
+DataMapper.setup(:default, :adapter => :lucene, :path => "tmp")

metadata

@@ -0,0 +1,81 @@
+--- !ruby/object:Gem::Specification 
+name: dm-lucene-adapter
+version: !ruby/object:Gem::Version 
+  version: 0.1.0
+platform: java
+authors: []
+
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-11-28 00:00:00 +05:30
+default_executable: 
+dependencies: 
+  - !ruby/object:Gem::Dependency 
+    name: dm-core
+    type: :runtime
+    version_requirement: 
+    version_requirements: !ruby/object:Gem::Requirement 
+      requirements: 
+        - - "="
+          - !ruby/object:Gem::Version 
+            version: 0.10.1
+      version: 
+  - !ruby/object:Gem::Dependency 
+    name: rspec
+    type: :development
+    version_requirement: 
+    version_requirements: !ruby/object:Gem::Requirement 
+      requirements: 
+        - - ~>
+          - !ruby/object:Gem::Version 
+            version: "1.2"
+      version: 
+description: datamapper adapter for search index lucene
+email: 
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+  - lib/dm-lucene-adapter.rb
+  - lib/dm-lucene-adapter_ext.jar
+  - lib/dm_lucene_adapter/dm_lucene_adapter.rb
+  - lib/dm_lucene_adapter/version.rb
+  - spec/dm_lucene_adapter_spec.rb
+  - spec/spec_helper.rb
+  - spec/spec.opts
+  - MIT-LICENSE
+has_rdoc: true
+homepage: http://github.com/mkristian/dm-lucene-adapter
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+  - lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.5
+signing_key: 
+specification_version: 3
+summary: dm adapter for lucene
+test_files: []
+