collectiveidea-sunspot_rails 0.10.5

data/lib/sunspot/rails/request_lifecycle.rb

@@ -0,0 +1,18 @@
+module Sunspot #:nodoc:
+  module Rails #:nodoc:
+    # 
+    # This module adds an after_filter to ActionController::Base that commits
+    # the Sunspot session if any documents have been added, changed, or removed
+    # in the course of the request.
+    #
+    module RequestLifecycle
+      class <<self
+        def included(base) #:nodoc:
+          base.after_filter do
+            Sunspot.commit_if_dirty if Sunspot::Rails.configuration.auto_commit_after_request?
+          end
+        end
+      end
+    end
+  end
+end

data/lib/sunspot/rails/searchable.rb

@@ -0,0 +1,305 @@
+module Sunspot #:nodoc:
+  module Rails #:nodoc:
+    # 
+    # This module adds Sunspot functionality to ActiveRecord models. As well as
+    # providing class and instance methods, it optionally adds lifecycle hooks
+    # to automatically add and remove models from the Solr index as they are
+    # created and destroyed.
+    #
+    module Searchable
+      class <<self
+        def included(base) #:nodoc:
+          base.module_eval { extend(ActsAsMethods) }
+        end
+      end
+
+      module ActsAsMethods
+        # 
+        # Makes a class searchable if it is not already, or adds search
+        # configuration if it is. Note that the options passed in are only used
+        # the first time this method is called for a particular class; so,
+        # search should be defined before activating any mixins that extend
+        # search configuration.
+        #
+        # The block passed into this method is evaluated by the
+        # <code>Sunspot.setup</code> method. See the Sunspot documentation for
+        # complete information on the functionality provided by that method.
+        #
+        # ==== Options (+options+)
+        # 
+        # :auto_index<Boolean>::
+        #   Automatically index models in Solr when they are saved.
+        #   Default: true
+        # :auto_remove<Boolean>::
+        #   Automatically remove models from the Solr index when they are
+        #   destroyed. <b>Setting this option to +false+ is not recommended
+        #   </b>(see the README).
+        #
+        # ==== Example
+        #
+        #   class Post < ActiveRecord::Base
+        #     searchable do
+        #       text :title, :body
+        #       string :sort_title do
+        #         title.downcase.sub(/^(an?|the)/, '')
+        #       end
+        #       integer :blog_id
+        #       time :updated_at
+        #     end
+        #   end
+        #
+        def searchable(options = {}, &block)
+          Sunspot.setup(self, &block)
+
+          unless searchable?
+            extend ClassMethods
+            include InstanceMethods
+
+            unless options[:auto_index] == false
+              after_save do |searchable|
+                searchable.index
+              end
+            end
+
+            unless options[:auto_remove] == false
+              after_destroy do |searchable|
+                searchable.remove_from_index
+              end
+            end
+          end
+        end
+
+        # 
+        # This method is defined on all ActiveRecord::Base subclasses. It
+        # is false for classes on which #searchable has not been called, and
+        # true for classes on which #searchable has been called.
+        #
+        # ==== Returns
+        #
+        # +false+
+        #
+        def searchable?
+          false
+        end
+      end
+
+      module ClassMethods
+        # 
+        # Search for instances of this class in Solr. The block is delegated to
+        # the Sunspot.search method - see the Sunspot documentation for the full
+        # API.
+        #
+        # ==== Example
+        #
+        #   Post.search do
+        #     keywords 'best pizza'
+        #     with :blog_id, 1
+        #     order :updated_at, :desc
+        #     facet :category_ids
+        #   end
+        #
+        #
+        # ==== Returns
+        #
+        # Sunspot::Search:: Object containing results, totals, facets, etc.
+        #
+        def search(&block)
+          Sunspot.search(self, &block)
+        end
+
+        # 
+        # Get IDs of matching results without loading the result objects from
+        # the database. This method may be useful if search is used as an
+        # intermediate step in a larger find operation. The block is the same
+        # as the block provided to the #search method.
+        #
+        # ==== Returns
+        #
+        # Array:: Array of IDs, in the order returned by the search
+        #
+        def search_ids(&block)
+          search(&block).raw_results.map { |raw_result| raw_result.primary_key.to_i }
+        end
+
+        # 
+        # Remove instances of this class from the Solr index.
+        #
+        def remove_all_from_index
+          Sunspot.remove_all(self)
+        end
+
+        # 
+        # Remove all instances of this class from the Solr index and immediately
+        # commit.
+        #
+        #---
+        # XXX Sunspot should implement remove_all!()
+        #
+        def remove_all_from_index!
+          Sunspot.remove_all(self)
+          Sunspot.commit
+        end
+
+        # 
+        # Completely rebuild the index for this class. First removes all
+        # instances from the index, then loads records and save them. The
+        # +batch_size+ argument specifies how many records to load out of the
+        # database at a time. The default batch size is 500; if nil is passed,
+        # records will not be indexed in batches. By default, a commit is issued
+        # after each batch; passing +false+ for +batch_commit+ will disable
+        # this, and only issue a commit at the end of the process. If associated
+        # objects need to indexed also, you can specify +include+ in format 
+        # accepted by ActiveRecord to improve your sql select performance
+        #
+        # ==== Options (passed as a hash)
+        #
+        # batch_size<Integer>:: Batch size with which to load records. Passing
+        #                       'nil' will skip batches.  Default is 500.
+        # batch_commit<Boolean>:: Flag signalling if a commit should be done after
+        #                         after each batch is indexed, default is 'true'
+        # include<Mixed>:: include option to be passed to the ActiveRecord find,
+        #                  used for including associated objects that need to be
+        #                  indexed with the parent object, accepts all formats
+        #                  ActiveRecord::Base.find does
+        #
+        # ==== Examples
+        #   
+        #   # reindex in batches of 500, commit after each
+        #   Post.reindex 
+        #
+        #   # index all rows at once, then commit
+        #   Post.reindex(:batch_size => nil) 
+        #
+        #   # reindex in batches of 500, commit when all batches complete
+        #   Post.reindex(:batch_commit => false) 
+        #
+        #   # include the associated +author+ object when loading to index
+        #   Post.reindex(:include => :author) 
+        #
+        def reindex(opts={})
+          options = { :batch_size => 500, :batch_commit => true, :include => []}.merge(opts)
+          remove_all_from_index
+          unless options[:batch_size]
+            Sunspot.index!(all(:include => options[:include]))
+          else
+            record_count = count
+            counter = 1
+            offset = 0
+            while(offset < record_count)
+              benchmark options[:batch_size], counter do
+                Sunspot.index(all(:include => options[:include], :offset => offset, :limit => options[:batch_size], :order => primary_key))
+              end
+              Sunspot.commit if options[:batch_commit]
+              offset += options[:batch_size]
+              counter += 1
+            end
+            Sunspot.commit unless options[:batch_commit]
+          end
+        end
+
+        # 
+        # Return the IDs of records of this class that are indexed in Solr but
+        # do not exist in the database. Under normal circumstances, this should
+        # never happen, but this method is provided in case something goes
+        # wrong. Usually you will want to rectify the situation by calling
+        # #clean_index_orphans or #reindex
+        # 
+        # ==== Returns
+        #
+        # Array:: Collection of IDs that exist in Solr but not in the database
+        def index_orphans
+          count = self.count
+          indexed_ids = search_ids { paginate(:page => 1, :per_page => count) }.to_set
+          all(:select => 'id').each do |object|
+            indexed_ids.delete(object.id)
+          end
+          indexed_ids.to_a
+        end
+
+        # 
+        # Find IDs of records of this class that are indexed in Solr but do not
+        # exist in the database, and remove them from Solr. Under normal
+        # circumstances, this should not be necessary; this method is provided
+        # in case something goes wrong.
+        #
+        def clean_index_orphans
+          index_orphans.each do |id|
+            new do |fake_instance|
+              fake_instance.id = id
+            end.remove_from_index
+          end
+        end
+
+        # 
+        # Classes that have been defined as searchable return +true+ for this
+        # method.
+        #
+        # ==== Returns
+        #
+        # +true+
+        #
+        def searchable?
+          true
+        end
+        
+        protected
+        
+        # 
+        # Does some logging for benchmarking indexing performance
+        #
+        def benchmark(batch_size, counter,  &block)
+          start = Time.now
+          logger.info("[#{Time.now}] Start Indexing")
+          yield
+          elapsed = Time.now-start
+          logger.info("[#{Time.now}] Completed Indexing. Rows indexed #{counter * batch_size}. Rows/sec: #{batch_size/elapsed.to_f} (Elapsed: #{elapsed} sec.)")
+        end
+        
+      end
+
+      module InstanceMethods
+        # 
+        # Index the model in Solr. If the model is already indexed, it will be
+        # updated. Using the defaults, you will usually not need to call this
+        # method, as models are indexed automatically when they are created or
+        # updated. If you have disabled automatic indexing (see
+        # ClassMethods#searchable), this method allows you to manage indexing
+        # manually.
+        #
+        def index
+          Sunspot.index(self)
+        end
+
+        # 
+        # Index the model in Solr and immediately commit. See #index
+        #
+        def index!
+          Sunspot.index!(self)
+        end
+        
+        # 
+        # Remove the model from the Solr index. Using the defaults, this should
+        # not be necessary, as models will automatically be removed from the
+        # index when they are destroyed. If you disable automatic removal
+        # (which is not recommended!), you can use this method to manage removal
+        # manually.
+        #
+        def remove_from_index
+          Sunspot.remove(self)
+        end
+
+        # 
+        # Remove the model from the Solr index and commit immediately. See
+        # #remove_from_index
+        #
+        #---
+        #FIXME Sunspot should implement remove!()
+        #
+        def remove_from_index!
+          Sunspot.remove(self)
+          Sunspot.commit
+        end
+      end
+    end
+  end
+end

data/lib/sunspot/rails/tasks.rb

@@ -0,0 +1,53 @@
+require 'escape'
+
+namespace :sunspot do
+  namespace :solr do
+    desc 'Start the Solr instance'
+    task :start => :environment do
+      if RUBY_PLATFORM =~ /w(in)?32$/
+        abort('This command does not work on Windows. Please use rake sunspot:solr:run to run Solr in the foreground.')
+      end
+      data_path = File.join(::Rails.root, 'solr', 'data', ::Rails.env)
+      pid_path = File.join(::Rails.root, 'solr', 'pids', ::Rails.env)
+      solr_home =
+        if %w(solrconfig schema).all? { |file| File.exist?(File.join(::Rails.root, 'solr', 'conf', "#{file}.xml")) }
+          File.join(::Rails.root, 'solr')
+        end
+      [data_path, pid_path].each { |path| FileUtils.mkdir_p(path) }
+      port = Sunspot::Rails.configuration.port
+      FileUtils.cd(File.join(pid_path)) do
+        command = ['sunspot-solr', 'start', '--', '-p', port.to_s, '-d', data_path]
+        if solr_home
+          command << '-s' << solr_home
+        end
+        system(Escape.shell_command(command))
+      end
+    end
+
+    desc 'Run the Solr instance in the foreground'
+    task :run => :environment do
+      data_path = File.join(::Rails.root, 'solr', 'data', ::Rails.env)
+      solr_home =
+        if %w(solrconfig schema).all? { |file| File.exist?(File.join(::Rails.root, 'solr', 'conf', "#{file}.xml")) }
+          File.join(::Rails.root, 'solr')
+        end
+      FileUtils.mkdir_p(data_path)
+      port = Sunspot::Rails.configuration.port
+      command = ['sunspot-solr', 'run', '--', '-p', port.to_s, '-d', data_path]
+      if RUBY_PLATFORM =~ /w(in)?32$/
+        command.first << '.bat'
+      end
+      if solr_home
+        command << '-s' << solr_home
+      end
+      exec(Escape.shell_command(command))
+    end
+
+    desc 'Stop the Solr instance'
+    task :stop => :environment do
+      FileUtils.cd(File.join(::Rails.root, 'solr', 'pids', ::Rails.env)) do
+        system(Escape.shell_command(['sunspot-solr', 'stop']))
+      end
+    end
+  end
+end

data/rails/init.rb

@@ -0,0 +1,10 @@
+require 'sunspot'
+
+Sunspot.config.solr.url = URI::HTTP.build(:host => Sunspot::Rails.configuration.hostname,
+                                          :port => Sunspot::Rails.configuration.port,
+                                          :path => Sunspot::Rails.configuration.path).to_s
+
+Sunspot::Adapters::InstanceAdapter.register(Sunspot::Rails::Adapters::ActiveRecordInstanceAdapter, ActiveRecord::Base)
+Sunspot::Adapters::DataAccessor.register(Sunspot::Rails::Adapters::ActiveRecordDataAccessor, ActiveRecord::Base)
+ActiveRecord::Base.module_eval { include(Sunspot::Rails::Searchable) }
+ActionController::Base.module_eval { include(Sunspot::Rails::RequestLifecycle) }

data/spec/configuration_spec.rb

@@ -0,0 +1,53 @@
+require File.join(File.dirname(__FILE__), 'spec_helper')
+
+describe Sunspot::Rails::Configuration, "default values" do
+  before(:each) do
+    File.should_receive(:exist?).and_return(false)
+  end
+  
+  it "should handle the 'hostname' property when not set" do
+    config = Sunspot::Rails::Configuration.new
+    config.hostname.should == 'localhost'
+  end  
+  
+  it "should handle the 'path' property when not set" do
+    config = Sunspot::Rails::Configuration.new
+    config.path.should == '/solr'
+  end
+
+  it "should handle the 'port' property when not set" do
+    config = Sunspot::Rails::Configuration.new
+    config.port.should == 8983
+  end
+
+  it "should handle the 'auto_commit_after_request' propery when not set" do
+    config = Sunspot::Rails::Configuration.new
+    config.auto_commit_after_request?.should == true
+  end
+end
+
+describe Sunspot::Rails::Configuration, "user settings" do
+  before(:each) do
+    Rails.stub!(:env => 'config_test')
+  end
+
+  it "should handle the 'hostname' property when not set" do
+    config = Sunspot::Rails::Configuration.new
+    config.hostname.should == 'some.host'
+  end
+
+  it "should handle the 'port' property when not set" do
+    config = Sunspot::Rails::Configuration.new
+    config.port.should == 1234
+  end
+  
+  it "should handle the 'path' property when set" do
+    config = Sunspot::Rails::Configuration.new
+    config.path.should == '/solr/idx'
+  end
+
+  it "should handle the 'auto_commit_after_request' propery when set" do
+    config = Sunspot::Rails::Configuration.new
+    config.auto_commit_after_request?.should == false
+  end
+end

data/spec/mock_app/app/controllers/application.rb

@@ -0,0 +1,10 @@
+# Filters added to this controller apply to all controllers in the application.
+# Likewise, all the methods added will be available for all controllers.
+
+class ApplicationController < ActionController::Base
+  helper :all # include all helpers, all the time
+  protect_from_forgery # See ActionController::RequestForgeryProtection for details
+
+  # Scrub sensitive parameters from your log
+  # filter_parameter_logging :password
+end