solrizer 0.1.0.pre2

data/spec/rcov.opts

@@ -0,0 +1,2 @@
+--exclude "spec/*,gems/*"
+--rails

data/spec/spec.opts

@@ -0,0 +1 @@
+--color

data/spec/spec_helper.rb

@@ -0,0 +1,16 @@
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+require 'solrizer'
+require 'spec'
+require 'spec/autorun'
+
+Spec::Runner.configure do |config|
+  
+  config.mock_with :mocha
+  
+  
+  def fixture(file)
+    File.new(File.join(File.dirname(__FILE__), 'fixtures', file))
+  end
+  
+end

data/spec/units/extractor_spec.rb

@@ -0,0 +1,50 @@
+require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
+require 'solrizer'
+
+describe Solrizer::Extractor do
+  
+  before(:each) do
+    @extractor = Solrizer::Extractor.new
+  end
+  
+  describe ".xml_to_solr" do
+    it "should turn simple xml into a solr document" do
+      desc_meta = fixture("druid-bv448hq0314-descMetadata.xml")
+      result = @extractor.xml_to_solr(desc_meta)
+      result[:type_t].should == "text"
+      result[:medium_t].should == "Paper Document"
+      result[:rights_t].should == "Presumed under copyright. Do not publish."
+      result[:date_t].should == "1985-12-30"
+      result[:format_t].should == "application/tiff"
+      result[:title_t].should == "This is a Sample Title"
+      result[:publisher_t].should == "Sample Unversity"
+
+      # ... and a hacky way of making sure that it added a field for each of the dc:medium values
+      result.inspect.include?('@value="application/tiff"').should be_true
+      result.inspect.include?('@value="application/pdf"').should be_true
+    end
+  end
+  
+  describe "extract_rels_ext" do 
+    it "should extract the content model of the RELS-EXT datastream of a Fedora object and set hydra_type using hydra_types mapping" do
+      rels_ext = fixture("rels_ext_cmodel.xml")
+      result = @extractor.extract_rels_ext( rels_ext )
+      result[:cmodel_t].should == "info:fedora/fedora-system:ContentModel-3.0"
+      result[:hydra_type_t].should == "salt_document"
+      
+      # ... and a hacky way of making sure that it added a field for each of the dc:medium values
+      result.inspect.include?('@value="info:fedora/afmodel:SaltDocument"').should be_true
+      result.inspect.include?('@value="jp2_document"').should be_true
+    end
+  end
+  
+  describe "extract_hydra_types" do 
+    it "should extract the hydra_type of a Fedora object" do
+      rels_ext = fixture("rels_ext_cmodel.xml")
+      result = @extractor.extract_rels_ext( rels_ext )
+      result[:hydra_type_t].should == "salt_document"
+    end
+  end
+  
+  
+end

data/spec/units/indexer_spec.rb

@@ -0,0 +1,127 @@
+require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
+require 'solrizer'
+
+describe Solrizer::Indexer do
+    
+  before(:each) do
+     Solrizer::Indexer.any_instance.stubs(:connect).returns("foo")
+  
+     @extractor = mock("Extractor")
+     @extractor.stubs(:html_content_to_solr).returns(@solr_doc)
+#     @solr_doc = mock('solr_doc')
+#     @solr_doc.stubs(:<<)
+#     @solr_doc.stubs(:[])
+     
+     @solr_doc = Solr::Document.new
+     
+     Solrizer::Extractor.expects(:new).returns(@extractor)
+     @indexer = Solrizer::Indexer.new
+     
+   end
+  
+  describe "#generate_dates" do
+    it "should still give 9999-99-99 date if the solr document does not have a date_t field" do
+    
+    solr_result = @indexer.generate_dates(@solr_doc)
+    solr_result.should be_kind_of Solr::Document
+    solr_result[:date_t].should == "9999-99-99"
+    solr_result[:month_facet].should == "99"
+    solr_result[:day_facet].should == '99'
+    
+    end
+    
+    it "should still give 9999-99-99 date if the solr_doc[:date_t] is not valid date in YYYY-MM-DD format " do
+     
+      @solr_doc << Solr::Field.new(:date_t => "Unknown")
+      solr_result = @indexer.generate_dates(@solr_doc)
+      solr_result.should be_kind_of Solr::Document
+      solr_result[:date_t].should == "Unknown"
+      solr_result[:month_facet].should == "99"
+      solr_result[:day_facet].should == '99'
+  
+    end
+    
+    it "should give month and dates even if the :date_t is not a valid date but is in YYYY-MM-DD format  " do
+      
+       @solr_doc << Solr::Field.new(:date_t => "0000-13-11")
+       solr_result = @indexer.generate_dates(@solr_doc)
+       solr_result.should be_kind_of Solr::Document
+       solr_result[:date_t].should == "0000-13-11"
+       solr_result[:month_facet].should == "99"
+       solr_result[:day_facet].should == '11'
+     end
+     
+     it "should give month and day when in a valid date format" do
+           @solr_doc << Solr::Field.new(:date_t => "1978-04-11")
+            solr_result = @indexer.generate_dates(@solr_doc)
+            solr_result.should be_kind_of Solr::Document
+            solr_result[:date_t].should == "1978-04-11"
+            solr_result[:month_facet].should == "04"
+            solr_result[:day_facet].should == '11'
+     
+     end
+     
+     it "should still give two digit strings even if the month/day is single digit" do
+     
+         @solr_doc << Solr::Field.new(:date_t => "1978-4-1")
+         solr_result = @indexer.generate_dates(@solr_doc)
+         solr_result.should be_kind_of Solr::Document
+         solr_result[:date_t].should == "1978-4-1"
+         solr_result[:month_facet].should == "04"
+         solr_result[:day_facet].should == '01'  
+     
+     end
+     
+  end
+  
+  
+  
+  describe "#solrize" do
+    it "should convert a hash to a solr doc" do
+      example_hash = {"box"=>"Box 51A", "city"=>["Ann Arbor", "Hyderabad", "Palo Alto"], "person"=>["ELLIE ENGELMORE", "Reddy", "EDWARD FEIGENBAUM"], "title"=>"Letter from Ellie Engelmore to Professor K. C. Reddy", "series"=>"eaf7000", "folder"=>"Folder 15", "technology"=>["artificial intelligence"], "year"=>"1985", "organization"=>["Heuristic Programming Project", "Mathematics and Computer/Information Sciences University of Hyderabad Central University P. O. Hyder", "Professor K. C. Reddy School of Mathematics and Computer/Information Sciences"], "collection"=>"e-a-feigenbaum-collection", "state"=>["Michigan", "California"]}
+      
+      example_result = Solrizer::Indexer.solrize( example_hash )
+      example_result.should be_kind_of Solr::Document
+      example_hash.each_pair do |key,values|
+        if values.class == String
+          example_result["#{key}_facet"].should == values
+        else
+          values.each do |v|
+            example_result.inspect.include?("@name=\"#{key}_facet\"").should be_true
+            example_result.inspect.include?("@value=\"#{v}\"").should be_true
+          end
+        end        
+      end
+    end
+    
+    it "should handle hashes with facets listed in a sub-hash" do
+      simple_hash = Hash[:facets => {'technology'=>["t1", "t2"], 'company'=>"c1", "person"=>["p1", "p2"]}]
+      result = Solrizer::Indexer.solrize( simple_hash )
+      result.should be_kind_of Solr::Document
+      result["technology_facet"].should == "t1"
+      result.inspect.include?('@boost=nil').should be_true
+      result.inspect.include?('@name="technology_facet"').should be_true
+      result.inspect.include?('@value="t2"').should be_true
+      result["company_facet"].should == "c1"
+      result["person_facet"].should == "p1"
+      result.inspect.include?('@name="person_facet"').should be_true
+      result.inspect.include?('@value="p2"').should be_true
+      
+    end
+    
+    it "should create symbols from the :symbols subhash" do
+      simple_hash = Hash[:facets => {'technology'=>["t1", "t2"], 'company'=>"c1", "person"=>["p1", "p2"]}, :symbols=>{'technology'=>["t1", "t2"], 'company'=>"c1", "person"=>["p1", "p2"]}]
+      result = Solrizer::Indexer.solrize( simple_hash )
+      result.should be_kind_of Solr::Document
+      result["technology_s"].should == "t1"
+      result.inspect.include?('@name="technology_s"').should be_true
+      result.inspect.include?('@value="t2"').should be_true
+    
+      result["company_s"].should == "c1"
+      result["person_s"].should == "p1"
+      result.inspect.include?('@name="person_s"').should be_true
+      result.inspect.include?('@value="p2"').should be_true
+  
+    end
+  end
+end

data/spec/units/shelver_spec.rb

@@ -0,0 +1,42 @@
+require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
+require 'solrizer'
+
+describe Solrizer::Solrizer do
+  
+  before(:each) do
+    @solrizer = Solrizer::Solrizer.new
+  end
+  
+  describe "solrize" do
+    it "should trigger the indexer for the provided object" do
+      # sample_obj = ActiveFedora::Base.new
+      mock_object = mock("my object")
+      mock_object.expects(:kind_of?).with(ActiveFedora::Base).returns(true)
+      mock_object.stubs(:pid)
+      mock_object.stubs(:label)
+      mock_object.stubs(:datastreams).returns({'descMetadata'=>"foo","location"=>"bar"})
+      ActiveFedora::Base.expects(:load_instance).never
+      @solrizer.indexer.expects(:index).with( mock_object )
+      @solrizer.solrize( mock_object )
+    end
+    it "should still load the object if only a pid is provided" do
+      mock_object = mock("my object")
+      mock_object.stubs(:pid)
+      mock_object.stubs(:label)
+      mock_object.stubs(:datastreams).returns({'descMetadata'=>"foo","location"=>"bar"})
+
+      ActiveFedora::Base.expects(:load_instance).with( "_PID_" ).returns(mock_object)
+      @solrizer.indexer.expects(:index).with(mock_object)
+      @solrizer.solrize("_PID_")
+    end
+  end
+  
+  describe "solrize_objects" do
+    it "should call solrize for each pid returned by solr" do
+      pids = [["pid1"], ["pid2"], ["pid3"]]
+      Solrizer::Repository.expects(:get_pids).returns(pids)
+      pids.each {|pid| @solrizer.expects(:solrize).with( pid ) }
+      @solrizer.solrize_objects
+    end
+  end
+end

metadata

@@ -0,0 +1,126 @@
+--- !ruby/object:Gem::Specification 
+name: solrizer
+version: !ruby/object:Gem::Version 
+  prerelease: true
+  segments: 
+  - 0
+  - 1
+  - 0
+  - pre2
+  version: 0.1.0.pre2
+platform: ruby
+authors: 
+- Matt Zumwalt
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-05-15 00:00:00 -05:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: active-fedora
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">"
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 1
+        - 1
+        - 3
+        version: 1.1.3
+  type: :runtime
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  name: rspec
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 1
+        - 2
+        - 9
+        version: 1.2.9
+  type: :development
+  version_requirements: *id002
+description: Use solrizer to populate solr indexes from Fedora repository content or from other sources.  You can run solrizer from within your apps, using the provided rake tasks, or as a JMS listener
+email: matt.zumwalt@yourmediashelf.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README.rdoc
+files: 
+- .gitignore
+- LICENSE
+- README.rdoc
+- Rakefile
+- VERSION
+- config/fedora.yml
+- config/hydra_types.yml
+- config/solr.yml
+- lib/solrizer.rb
+- lib/solrizer/configuration.rb
+- lib/solrizer/extractor.rb
+- lib/solrizer/indexer.rb
+- lib/solrizer/main.rb
+- lib/solrizer/replicator.rb
+- lib/solrizer/repository.rb
+- lib/tasks/solrizer.rake
+- solrizer.gemspec
+- spec/fixtures/druid-bv448hq0314-descMetadata.xml
+- spec/fixtures/druid-bv448hq0314-extProperties.xml
+- spec/fixtures/druid-cm234kq4672-extProperties.xml
+- spec/fixtures/druid-cm234kq4672-stories.xml
+- spec/fixtures/druid-hc513kw4806-descMetadata.xml
+- spec/fixtures/rels_ext_cmodel.xml
+- spec/integration/indexer_spec.rb
+- spec/rcov.opts
+- spec/spec.opts
+- spec/spec_helper.rb
+- spec/units/extractor_spec.rb
+- spec/units/indexer_spec.rb
+- spec/units/shelver_spec.rb
+has_rdoc: true
+homepage: http://github.com/projecthydra/solrizer
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">"
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 1
+      - 3
+      - 1
+      version: 1.3.1
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.6
+signing_key: 
+specification_version: 3
+summary: A utility for building solr indexes, usually from Fedora repository content.
+test_files: 
+- spec/integration/indexer_spec.rb
+- spec/spec_helper.rb
+- spec/units/extractor_spec.rb
+- spec/units/indexer_spec.rb
+- spec/units/shelver_spec.rb