solrizer-fedora 0.1.0

data/.document

@@ -0,0 +1,5 @@
+README.rdoc
+lib/**/*.rb
+bin/*
+features/**/*.feature
+LICENSE

data/.gitignore

@@ -0,0 +1,22 @@
+## MAC OS
+.DS_Store
+
+## TEXTMATE
+*.tmproj
+tmtags
+
+## EMACS
+*~
+\#*
+.\#*
+
+## VIM
+*.swp
+
+## PROJECT::GENERAL
+coverage
+rdoc
+pkg
+/.bundle
+
+## PROJECT::SPECIFIC

data/Gemfile

@@ -0,0 +1,10 @@
+source "http://rubygems.org"
+gem 'active-fedora', '1.2.4'  
+gem 'solrizer', '>=0.3.0'
+
+group :development, :test do
+  gem 'ruby-debug'
+  gem 'ruby-debug-base'
+  gem 'rspec', '<2.0.0'
+  gem 'mocha'
+end

data/Gemfile.lock

@@ -0,0 +1,44 @@
+GEM
+  remote: http://rubygems.org/
+  specs:
+    active-fedora (1.2.4)
+      mime-types (>= 1.16)
+      multipart-post
+      nokogiri
+      om (>= 1.0)
+      solr-ruby (>= 0.0.6)
+      xml-simple (>= 1.0.12)
+    columnize (0.3.1)
+    facets (2.9.0)
+    linecache (0.43)
+    mime-types (1.16)
+    mocha (0.9.9)
+      rake
+    multipart-post (1.0.1)
+    nokogiri (1.4.3.1)
+    om (1.0.0)
+      facets
+      nokogiri (>= 1.4.2)
+    rake (0.8.7)
+    rspec (1.3.1)
+    ruby-debug (0.10.3)
+      columnize (>= 0.1)
+      ruby-debug-base (~> 0.10.3.0)
+    ruby-debug-base (0.10.3)
+      linecache (>= 0.3)
+    solr-ruby (0.0.8)
+    solrizer (0.3.0)
+      active-fedora (>= 1.1.5)
+      om (>= 1.0.0)
+    xml-simple (1.0.12)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  active-fedora (= 1.2.4)
+  mocha
+  rspec (< 2.0.0)
+  ruby-debug
+  ruby-debug-base
+  solrizer (>= 0.2.0)

data/History.textile

@@ -0,0 +1,3 @@
+h2. 0.1.0
+
+Initial Release -- pretty much a direct replica of all of the fedora-related stuff in solrizer versions older than 0.3.0

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2009 Matt Zumwalt
+
+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/README.textile

@@ -0,0 +1,34 @@
+h1. solrizer-fedora
+
+An extension to projecthydra/solrizer that provides utilities for loading objects from Fedora Repositories and creating solr documents from them.
+
+h2. Usage
+
+<pre>gem install solrizer-fedora</pre>
+
+You must tell the app where to find fedora and solr.  Put that information into config/fedora.yml and config/solr.yml
+
+Then...
+
+<pre>
+irb
+require "rubygems"
+require "solrizer-fedora"
+solrizer = Solrizer::Fedora::Solrizer.new
+solrizer.solrize("demo:5")
+</pre>
+
+
+h2.  Note on Patches/Pull Requests
+ 
+* Fork the project.
+* Make your feature addition or bug fix.
+* Add tests for it. This is important so I don't break it in a
+  future version unintentionally.
+* Commit, do not mess with rakefile, version, or history.
+  (if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
+* Send me a pull request. Bonus points for topic branches.
+
+h2. Copyright
+
+Copyright (c) 2010 Matt Zumwalt and MediaShelf. See LICENSE for details.

data/Rakefile

@@ -0,0 +1,57 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "solrizer-fedora"
+    gem.summary = %Q{An extension to solrizer that deals with Fedora objects & Repositories}
+    gem.description = %Q{An extension to projecthydra/solrizer that provides utilities for loading objects from Fedora Repositories and creating solr documents from them.}
+    gem.email = "matt.zumwalt@yourmediashelf.com"
+    gem.homepage = "http://github.com/projecthydra/solrizer-fedora"
+    gem.authors = ["Matt Zumwalt"]
+    # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
+  end
+  Jeweler::GemcutterTasks.new
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
+end
+
+require 'spec/rake/spectask'
+Spec::Rake::SpecTask.new(:spec) do |spec|
+  spec.libs << 'lib' << 'spec'
+  spec.spec_files = FileList['spec/**/*_spec.rb']
+end
+
+Spec::Rake::SpecTask.new(:rcov) do |spec|
+  spec.libs << 'lib' << 'spec'
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.rcov = true
+end
+
+task :spec => :check_dependencies
+
+task :default => :spec
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "solrizer #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end
+
+begin
+  require 'rcov/rcovtask'
+  Rcov::RcovTask.new do |test|
+    test.libs << 'test'
+    test.pattern = 'test/**/test_*.rb'
+    test.verbose = true
+  end
+rescue LoadError
+  task :rcov do
+    abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
+  end
+end

data/VERSION

@@ -0,0 +1 @@
+0.1.0

data/config/fedora.yml

@@ -0,0 +1,16 @@
+development:
+  fedora:
+    url: http://fedoraAdmin:fedoraAdmin@127.0.0.1:8983/fedora
+  solr:
+    url: http://127.0.0.1:8983/solr/development
+test:
+  fedora:
+    url: http://fedoraAdmin:fedoraAdmin@127.0.0.1:8983/fedora
+  solr:
+    url: http://127.0.0.1:8983/solr/test
+production:
+  fedora:
+    url: http://fedoraAdmin:fedoraAdmin@127.0.0.1:8080/fedora
+  solr:
+    url: http://127.0.0.1:8080/solr
+    

data/config/hydra_types.yml

@@ -0,0 +1,4 @@
+info:fedora/afmodel:SaltDocument : salt_document
+info:fedora/afmodel:JP2Document : jp2_document
+info:fedora/afmodel:ModsDocument : mods_document
+info:fedora/afmodel:DCDocument : dc_document

data/config/solr.yml

@@ -0,0 +1,7 @@
+development:
+  url: http://localhost:8983/solr/development
+test: &TEST
+  url: http://localhost:8983/solr/test
+production:
+  url: http://localhost:8080/solr/production 
+

data/lib/solrizer-fedora.rb

@@ -0,0 +1 @@
+require "solrizer/fedora"

data/lib/solrizer/fedora.rb

@@ -0,0 +1,7 @@
+require "rubygems"
+require "solrizer"
+module Solrizer::Fedora
+end
+Dir[File.join(File.dirname(__FILE__),"fedora","*.rb")].each {|file| require file }
+
+Solrizer::Extractor.send(:include, Solrizer::Fedora::Extractor)

data/lib/solrizer/fedora/extractor.rb

@@ -0,0 +1,34 @@
+require 'solr'
+require 'rexml/document'
+require "nokogiri"
+require 'yaml'
+
+module Solrizer::Fedora::Extractor
+
+  #
+  # Extracts content-model and hydra-type from RELS-EXT datastream
+  #
+  def extract_rels_ext( text, solr_doc=Solr::Document.new )
+    # TODO: only read in this file once
+    
+    if defined?(RAILS_ROOT)
+      config_path = File.join(RAILS_ROOT, "config")
+    else
+      config_path = File.join(File.dirname(__FILE__), "..", "..", "..", "config")
+    end    
+    map = YAML.load(File.open(File.join(config_path, "hydra_types.yml")))
+    
+    doc = Nokogiri::XML(text)
+    doc.xpath( '//foo:hasModel', 'foo' => 'info:fedora/fedora-system:def/model#' ).each do |element|
+      cmodel = element.attributes['resource'].to_s
+      solr_doc << Solr::Field.new( :cmodel_t => cmodel )
+      
+      if map.has_key?(cmodel)
+        solr_doc << Solr::Field.new( :hydra_type_t => map[cmodel] )
+      end
+    end
+
+    return solr_doc
+  end
+  
+end

data/lib/solrizer/fedora/indexer.rb

@@ -0,0 +1,213 @@
+require 'solr'
+require 'solrizer/extractor'
+require 'solrizer/fedora/repository'
+
+module Solrizer::Fedora
+class Indexer  
+  #
+  # Class variables
+  #
+  @@unique_id = 0
+
+  def self.unique_id
+    @@unique_id
+  end
+
+  #
+  # Member variables
+  #
+  attr_accessor :connection, :extractor, :index_full_text
+
+  #
+  # This method performs initialization tasks
+  #
+  def initialize( opts={} )
+    @@index_list = false unless defined?(@@index_list)
+    @extractor = ::Solrizer::Extractor.new
+    
+    if opts[:index_full_text] == true || opts[:index_full_text] == "true"
+      @index_full_text = true 
+    else
+      @index_full_text = false 
+    end
+    
+    connect
+  end
+
+  #
+  # This method connects to the Solr instance
+  #
+  def connect
+    
+    if ActiveFedora.fedora_config.empty?
+      ActiveFedora.init
+    end
+    
+    if defined?(Blacklight)
+      solr_config = Blacklight.solr_config
+    else
+      
+      if defined?(RAILS_ROOT)
+        config_path = File.join(RAILS_ROOT, "config")
+        yaml = YAML.load(File.open(File.join(config_path, "solr.yml")))
+        solr_config = yaml[RAILS_ENV]
+        puts solr_config.inspect
+      else
+        config_path = File.join(File.dirname(__FILE__), "..", "..", "..", "config")
+        yaml = YAML.load(File.open(File.join(config_path, "solr.yml")))
+        
+        
+        if ENV["environment"].nil?
+          environment = "development"
+        else
+          environment = ENV["environment"]
+        end
+        
+        solr_config = yaml[environment]
+        puts solr_config.inspect
+      end
+      
+    end
+        
+    if index_full_text == true
+      url = solr_config['fulltext']['url']
+    elsif solr_config.has_key?("default")
+      url = solr_config['default']['url']
+    else
+      url = solr_config['url']
+    end
+    @connection = Solr::Connection.new(url, :autocommit => :on )
+  end
+
+  #
+  # This method extracts the facet categories from the given Fedora object's external tag datastream
+  #
+  def extract_xml_to_solr( obj, ds_name, solr_doc=Solr::Document.new )
+    xml_ds = Repository.get_datastream( obj, ds_name )
+    extractor.xml_to_solr( xml_ds.content, solr_doc )
+  end
+  
+  #
+  #
+  #
+  def extract_rels_ext( obj, ds_name, solr_doc=Solr::Document.new )
+    rels_ext_ds = Repository.get_datastream( obj, ds_name )
+    extractor.extract_rels_ext( rels_ext_ds.content, solr_doc )
+  end
+  
+  #
+  # This method generates the month and day facets from the date_t in solr_doc
+  #
+  
+  def generate_dates(solr_doc)
+    
+    # This will check for valid dates, but it seems most of the dates are currently invalid....
+    #date_check =  /^(19|20)\d\d([- \/.])(0[1-9]|1[012])\2(0[1-9]|[12][0-9]|3[01])/
+
+   #if there is not date_t, add on with easy-to-find value
+   if solr_doc[:date_t].nil?
+        solr_doc << Solr::Field.new( :date_t => "9999-99-99")
+   end #if
+
+    # unless date_check !~  solr_doc[:date_t]     
+    date_obj = Date._parse(solr_doc[:date_t])
+    
+    if date_obj[:mon].nil? 
+       solr_doc << Solr::Field.new(:month_facet => 99)
+    elsif 0 < date_obj[:mon] && date_obj[:mon] < 13
+      solr_doc << Solr::Field.new( :month_facet => date_obj[:mon].to_s.rjust(2, '0'))
+    else
+      solr_doc << Solr::Field.new( :month_facet => 99)
+    end
+      
+    if  date_obj[:mday].nil?
+      solr_doc << Solr::Field.new( :day_facet => 99)
+    elsif 0 < date_obj[:mday] && date_obj[:mday] < 32   
+      solr_doc << Solr::Field.new( :day_facet => date_obj[:mday].to_s.rjust(2, '0'))
+    else
+       solr_doc << Solr::Field.new( :day_facet => 99)
+    end
+    
+    return solr_doc
+#      end
+        
+  end
+  
+  
+  #
+  # This method creates a Solr-formatted XML document
+  #
+  def create_document( obj )        
+    
+    solr_doc = Solr::Document.new
+    
+    model_klazz_array = ActiveFedora::ContentModel.known_models_for( obj )
+    model_klazz_array.delete(ActiveFedora::Base)
+    
+    # If the object was passed in as an ActiveFedora::Base, call to_solr in order to get the base field entries from ActiveFedora::Base
+    # Otherwise, the object was passed in as a model instance other than ActiveFedora::Base,so call its to_solr method & allow it to insert the fields from ActiveFedora::Base
+    if obj.class == ActiveFedora::Base
+      solr_doc = obj.to_solr(solr_doc)
+      puts "  added base fields from #{obj.class.to_s}"
+    else
+      solr_doc = obj.to_solr(solr_doc)
+      model_klazz_array.delete(obj.class)
+      puts "    added base fields from #{obj.class.to_s} and model fields from #{obj.class.to_s}"
+    end
+   
+    # Load the object as an instance of each of its other models and get the corresponding solr fields
+    # Include :model_only=>true in the options in order to avoid adding the metadata from ActiveFedora::Base every time.
+    model_klazz_array.each do |klazz|
+      instance = klazz.load_instance(obj.pid)
+      solr_doc = instance.to_solr(solr_doc, :model_only=>true)
+      puts "  added solr fields from #{klazz.to_s}"
+    end
+    
+    solr_doc << Solr::Field.new( :id_t => "#{obj.pid}" )
+    solr_doc << Solr::Field.new( :id => "#{obj.pid}" ) unless solr_doc[:id]
+    
+    # increment the unique id to ensure that all documents in the search index are unique
+    @@unique_id += 1
+
+    return solr_doc
+  end
+
+  #
+  # This method adds a document to the Solr search index
+  #
+  def index( obj )
+   # print "Indexing '#{obj.pid}'..."
+    begin
+      
+      solr_doc = create_document( obj )
+      connection.add( solr_doc )
+ 
+     # puts connection.url
+     #puts solr_doc
+     #  puts "done"
+   
+    # rescue Exception => e
+    #    p "unable to index #{obj.pid}.  Failed with #{e.inspect}"
+    end
+   
+  end
+
+  #
+  # This method queries the Solr search index and returns a response
+  #
+  def query( query_str )
+    response = conn.query( query_str )
+  end
+  
+
+  private :connect, :create_document
+
+  def class_exists?(class_name)
+    klass = Module.const_get(class_name)
+    return klass.is_a?(Class)
+  rescue NameError
+    return false
+  end
+  
+end
+end

data/lib/solrizer/fedora/repository.rb

@@ -0,0 +1,44 @@
+require 'active-fedora'
+
+module Solrizer::Fedora
+class Repository
+
+  #
+  # This method retrieves a comprehensive list of unique ids in the fedora repository
+  #
+  def self.get_pids( num_docs )
+    solr_results = ActiveFedora::SolrService.instance.conn.query( "active_fedora_model_field:Document", { :rows => num_docs } )
+    id_array = []
+    solr_results.hits.each do |hit|
+      id_array << hit[SOLR_DOCUMENT_ID]
+    end
+    return id_array
+  end
+  
+  #
+  # This method retrieves the object associated with the given unique id
+  #
+  def self.get_object( pid )
+    object = ActiveFedora::Base.load_instance( pid )
+  end
+  
+  #
+  # This method retrieves a comprehensive list of datastreams for the given object
+  #
+  def self.get_datastreams( obj )
+    ds_keys = obj.datastreams.keys
+  end
+  
+  #
+  # This method retrieves the datastream for the given object with the given datastream name
+  #
+  def self.get_datastream( obj, ds_name )
+    begin
+      obj.datastreams[ ds_name ]
+    rescue
+      return nil
+    end
+  end
+
+end
+end

data/lib/solrizer/fedora/solrizer.rb

@@ -0,0 +1,118 @@
+require 'solrizer/field_mapper.rb'
+require 'solrizer/field_name_mapper'
+
+require 'solrizer/fedora/indexer'
+require 'solrizer/xml'
+require 'solrizer/html'
+
+# Let people explicitly require xml support if they want it ...
+# require 'solrizer/xml.rb'
+
+# require 'fastercsv'
+require "ruby-debug"
+
+
+module Solrizer::Fedora
+class Solrizer
+
+  attr_accessor :indexer, :index_full_text
+
+  #
+  # This method initializes the indexer
+  # If passed an argument of :index_full_text=>true, it will perform full-text indexing instead of indexing fields only.
+  #
+  def initialize( opts={} )
+    @@index_list = false unless defined?(@@index_list)
+    if opts[:index_full_text] == true || opts[:index_full_text] == "true"
+      @index_full_text = true 
+    else
+      @index_full_text = false 
+    end
+    @indexer = Indexer.new( :index_full_text=>@index_full_text )
+  end
+
+  #
+  # This method solrizes the given Fedora object's full-text and facets into the search index
+  #
+  def solrize( obj )
+    # retrieve the Fedora object based on the given unique id
+      
+      begin
+      
+      start = Time.now
+      print "Retrieving object #{obj} ..."
+
+      case obj
+      when ActiveFedora::Base
+        # do nothing
+      when Fedora::FedoraObject
+        obj = Repository.get_object( obj.pid )
+      when String
+        obj = Repository.get_object( obj )
+      else
+        raise "you must pass either a ActiveFedora::Base, Fedora::RepositoryObject, or a String.  You submitted a #{obj.class}"
+      end
+      
+      # obj = obj.kind_of?(ActiveFedora::Base) ? obj : Repository.get_object( obj )
+        
+          obj_done = Time.now
+          obj_done_elapse = obj_done - start
+          puts  " completed. Duration: #{obj_done_elapse}"
+          
+         print "\t Indexing object #{obj.pid} ... "
+         # add the keywords and facets to the search index
+         index_start = Time.now
+         indexer.index( obj )
+         
+         index_done = Time.now
+         index_elapsed = index_done - index_start
+         
+          puts "completed. Duration:  #{index_elapsed} ."
+        
+      
+      rescue Exception => e
+           p "unable to index #{obj}.  Failed with #{e.inspect}"
+        
+      
+      end #begin
+  
+  end
+  
+  #
+  # This method retrieves a comprehensive list of all the unique identifiers in Fedora and 
+  # solrizes each object's full-text and facets into the search index
+  def solrize_objects
+    # retrieve a list of all the pids in the fedora repository
+    num_docs = 1000000   # modify this number to guarantee that all the objects are retrieved from the repository
+    puts "WARNING: You have turned off indexing of Full Text content.  Be sure to re-run indexer with @@index_full_text set to true in main.rb" if index_full_text == false
+
+    if @@index_list == false
+      
+      objects = ::Fedora::Repository.instance.find_objects(:limit=>num_docs)
+
+      puts "Shelving #{objects.length} Fedora objects"
+      objects.each do |object|
+        solrize( object )
+      end
+     
+    else
+    
+       if File.exists?(@@index_list)
+          arr_of_pids = FasterCSV.read(@@index_list, :headers=>false)
+          
+          puts "Indexing from list at #{@@index_list}"
+          puts "Shelving #{arr_of_pids.length} Fedora objects"
+          
+         arr_of_pids.each do |row|
+            pid = row[0]
+            solrize( pid )
+	 end #FASTERCSV
+        else
+          puts "#{@@index_list} does not exists!"
+        end #if File.exists
+     
+    end #if Index_LISTS
+  end #solrize_objects
+
+end #class
+end #module

data/lib/tasks/solrizer-fedora.rake

@@ -0,0 +1,35 @@
+namespace :solrizer do
+  
+  namespace :fedora  
+    desc 'Index a fedora object of the given pid.'
+    task :solrize => :environment do 
+      index_full_text = ENV['FULL_TEXT'] == 'true'
+      if ENV['PID']
+        puts "indexing #{ENV['PID'].inspect}"
+        solrizer = Solrizer::Fedora::Solrizer.new :index_full_text=> index_full_text
+        solrizer.solrize(ENV['PID'])
+        puts "Finished shelving #{ENV['PID']}"
+      else
+        puts "You must provide a pid using the format 'solrizer::solrize_object PID=sample:pid'."
+      end
+    end
+  
+    desc 'Index all objects in the repository.'
+    task :solrize_objects => :environment do
+      index_full_text = ENV['FULL_TEXT'] == 'true'
+      if ENV['INDEX_LIST']
+        @@index_list = ENV['INDEX_LIST']
+      end
+    
+      puts "Re-indexing Fedora Repository."
+      puts "Fedora URL: #{ActiveFedora.fedora_config[:url]}"
+      puts "Fedora Solr URL: #{ActiveFedora.solr_config[:url]}"
+      puts "Blacklight Solr Config: #{Blacklight.solr_config.inspect}"
+      puts "Doing full text index." if index_full_text
+      solrizer = Solrizer::Fedora::Solrizer.new :index_full_text=> index_full_text
+      solrizer.solrize_objects
+      puts "Solrizer task complete."
+    end  
+  end
+  
+end

data/solrizer-fedora.gemspec

@@ -0,0 +1,72 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{solrizer-fedora}
+  s.version = "0.1.0"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Matt Zumwalt"]
+  s.date = %q{2010-10-26}
+  s.description = %q{An extension to projecthydra/solrizer that provides utilities for loading objects from Fedora Repositories and creating solr documents from them.}
+  s.email = %q{matt.zumwalt@yourmediashelf.com}
+  s.extra_rdoc_files = [
+    "LICENSE",
+     "README.textile"
+  ]
+  s.files = [
+    ".document",
+     ".gitignore",
+     "Gemfile",
+     "Gemfile.lock",
+     "History.textile",
+     "LICENSE",
+     "README.textile",
+     "Rakefile",
+     "VERSION",
+     "config/fedora.yml",
+     "config/hydra_types.yml",
+     "config/solr.yml",
+     "lib/solrizer-fedora.rb",
+     "lib/solrizer/fedora.rb",
+     "lib/solrizer/fedora/extractor.rb",
+     "lib/solrizer/fedora/indexer.rb",
+     "lib/solrizer/fedora/repository.rb",
+     "lib/solrizer/fedora/solrizer.rb",
+     "lib/tasks/solrizer-fedora.rake",
+     "solrizer-fedora.gemspec",
+     "spec/fixtures/rels_ext_cmodel.xml",
+     "spec/integration/fedora_indexer_spec.rb",
+     "spec/rcov.opts",
+     "spec/spec.opts",
+     "spec/spec_helper.rb",
+     "spec/units/fedora_extractor_spec.rb",
+     "spec/units/fedora_indexer_spec.rb",
+     "spec/units/fedora_solrizer_spec.rb"
+  ]
+  s.homepage = %q{http://github.com/projecthydra/solrizer-fedora}
+  s.rdoc_options = ["--charset=UTF-8"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.3.7}
+  s.summary = %q{An extension to solrizer that deals with Fedora objects & Repositories}
+  s.test_files = [
+    "spec/integration/fedora_indexer_spec.rb",
+     "spec/spec_helper.rb",
+     "spec/units/fedora_extractor_spec.rb",
+     "spec/units/fedora_indexer_spec.rb",
+     "spec/units/fedora_solrizer_spec.rb"
+  ]
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+    else
+    end
+  else
+  end
+end
+

data/spec/fixtures/rels_ext_cmodel.xml

@@ -0,0 +1,8 @@
+<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+	<rdf:Description rdf:about="info:fedora/demo:multipurpose-objects-model_and_sdef">
+		<hasModel xmlns="info:fedora/fedora-system:def/model#" rdf:resource="info:fedora/fedora-system:ContentModel-3.0"/>
+		<hasModel xmlns="info:fedora/fedora-system:def/model#" rdf:resource="info:fedora/afmodel:SaltDocument"/>
+		<hasModel xmlns="info:fedora/fedora-system:def/model#" rdf:resource="info:fedora/afmodel:JP2Document"/>
+		<hasModel xmlns="info:fedora/fedora-system:def/model#" rdf:resource="info:fedora/afmodel:DCDocument"/>
+	</rdf:Description>
+</rdf:RDF>

data/spec/integration/fedora_indexer_spec.rb

@@ -0,0 +1,18 @@
+require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
+require 'solrizer'
+
+describe Solrizer::Fedora::Indexer do
+  
+  before(:each) do
+    @indexer = Solrizer::Fedora::Indexer.new
+  end
+  
+  describe "index" do
+    it "should update solr with the metadata from the given object" do
+      pending "Got to decide if/how to handle fixtures in this gem. Probably should just mock out Fedora & Solr entirely."
+      obj = Solrizer::Repository.get_object( "druid:sb733gr4073" )
+      @indexer.index( obj )
+    end
+  end
+  
+end

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 +1,18 @@
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+require 'solrizer/fedora'
+require 'spec'
+require 'spec/autorun'
+
+require 'solrizer'
+
+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/fedora_extractor_spec.rb

@@ -0,0 +1,31 @@
+require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
+require 'solrizer'
+
+describe Solrizer::Fedora::Extractor do
+  
+  before(:all) do
+    @extractor = Solrizer::Extractor.new
+  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/fedora_indexer_spec.rb

@@ -0,0 +1,78 @@
+require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
+require 'solrizer'
+require "solrizer/fedora"
+
+describe Solrizer::Fedora::Indexer do
+    
+  before(:each) do
+     Solrizer::Fedora::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::Fedora::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
+
+end

data/spec/units/fedora_solrizer_spec.rb

@@ -0,0 +1,42 @@
+require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
+
+describe Solrizer::Fedora::Solrizer do
+  
+  before(:each) do
+    @solrizer = Solrizer::Fedora::Solrizer.new
+  end
+  
+  describe "solrize" do
+    it "should trigger the indexer for the provided object" do
+      sample_obj = ActiveFedora::Base.new
+      @solrizer.indexer.expects(:index).with( sample_obj )
+      @solrizer.solrize( sample_obj )
+    end
+    it "should work with Fedora::FedoraObject objects" do
+      mock_object = Fedora::FedoraObject.new(:pid=>"my:pid", :label=>"my label")
+      ActiveFedora::Base.expects(:load_instance).with( mock_object.pid ).returns(mock_object)
+      @solrizer.indexer.expects(:index).with( mock_object )
+      @solrizer.solrize( mock_object )
+    end
+    it "should 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 object returned by Fedora::Repository.find_objects" do
+      objects = [["pid1"], ["pid2"], ["pid3"]]
+      Fedora::Repository.any_instance.expects(:find_objects).returns(objects)
+      objects.each {|object| @solrizer.expects(:solrize).with( object ) }
+      @solrizer.solrize_objects
+    end
+  end
+end

metadata

@@ -0,0 +1,99 @@
+--- !ruby/object:Gem::Specification 
+name: solrizer-fedora
+version: !ruby/object:Gem::Version 
+  hash: 27
+  prerelease: false
+  segments: 
+  - 0
+  - 1
+  - 0
+  version: 0.1.0
+platform: ruby
+authors: 
+- Matt Zumwalt
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-10-26 00:00:00 -05:00
+default_executable: 
+dependencies: []
+
+description: An extension to projecthydra/solrizer that provides utilities for loading objects from Fedora Repositories and creating solr documents from them.
+email: matt.zumwalt@yourmediashelf.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README.textile
+files: 
+- .document
+- .gitignore
+- Gemfile
+- Gemfile.lock
+- History.textile
+- LICENSE
+- README.textile
+- Rakefile
+- VERSION
+- config/fedora.yml
+- config/hydra_types.yml
+- config/solr.yml
+- lib/solrizer-fedora.rb
+- lib/solrizer/fedora.rb
+- lib/solrizer/fedora/extractor.rb
+- lib/solrizer/fedora/indexer.rb
+- lib/solrizer/fedora/repository.rb
+- lib/solrizer/fedora/solrizer.rb
+- lib/tasks/solrizer-fedora.rake
+- solrizer-fedora.gemspec
+- spec/fixtures/rels_ext_cmodel.xml
+- spec/integration/fedora_indexer_spec.rb
+- spec/rcov.opts
+- spec/spec.opts
+- spec/spec_helper.rb
+- spec/units/fedora_extractor_spec.rb
+- spec/units/fedora_indexer_spec.rb
+- spec/units/fedora_solrizer_spec.rb
+has_rdoc: true
+homepage: http://github.com/projecthydra/solrizer-fedora
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.7
+signing_key: 
+specification_version: 3
+summary: An extension to solrizer that deals with Fedora objects & Repositories
+test_files: 
+- spec/integration/fedora_indexer_spec.rb
+- spec/spec_helper.rb
+- spec/units/fedora_extractor_spec.rb
+- spec/units/fedora_indexer_spec.rb
+- spec/units/fedora_solrizer_spec.rb