solrizer 3.0.0.pre7 → 3.0.0.pre8

data/lib/solrizer/extractor.rb

@@ -1,6 +1,3 @@
-require "nokogiri"
-require 'yaml'
-
 module Solrizer
   
 # Provides utilities for extracting solr fields from a variety of objects and/or creating solr documents from a given object

data/lib/solrizer/field_mapper.rb

@@ -34,8 +34,6 @@ module Solrizer
   #   #   t.dish_name   :index_as => [:some_field_type]           -maps to->   dish_name_ssim
   #   #   t.ingredients :index_as => [:some_field_type, :edible]  -maps to->   ingredients_ssim, ingredients_food
   #
-  # (See Solrizer::XML::TerminologyBasedSolrizer for instructions on applying a custom mapping once you have defined it.)
-  #
   #
   # == Custom Value Converters
   #

data/lib/solrizer/version.rb

@@ -1,3 +1,3 @@
 module Solrizer
-  VERSION = "3.0.0.pre7"
+  VERSION = "3.0.0.pre8"
 end

data/lib/solrizer/xml/extractor.rb

@@ -4,7 +4,7 @@ module Solrizer::XML::Extractor
 
   #
   # This method extracts solr fields from simple xml
-  # If you want to do anything more nuanced with the xml, use TerminologyBasedSolrizer instead.
+  # If you want to do anything more nuanced with the xml, use OM instead.
   #
   # @param [xml] text xml content to index
   # @param [Hash] solr_doc

data/lib/solrizer/xml.rb

@@ -1,7 +1,5 @@
-require "solrizer"
-require "om"
 module Solrizer::XML
 end
 Dir[File.join(File.dirname(__FILE__),"xml","*.rb")].each {|file| require file }
 
-Solrizer::Extractor.send(:include, Solrizer::XML::Extractor)
+Solrizer::Extractor.send(:include, Solrizer::XML::Extractor)

data/solrizer.gemspec

@@ -13,7 +13,6 @@ Gem::Specification.new do |s|
   s.description = %q{Use solrizer to populate solr indexes.  You can run solrizer from within your app, using the provided rake tasks, or as a JMS listener}
 
   s.add_dependency "nokogiri"
-  s.add_dependency "om", ">=1.5.0"
   s.add_dependency "xml-simple"
   s.add_dependency "mediashelf-loggable", "~>0.4.7"
   s.add_dependency "stomp"

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: solrizer
 version: !ruby/object:Gem::Version
-  version: 3.0.0.pre7
+  version: 3.0.0.pre8
   prerelease: 6
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-02-02 00:00:00.000000000 Z
+date: 2013-02-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -27,22 +27,6 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: om
-  requirement: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 1.5.0
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 1.5.0
 - !ruby/object:Gem::Dependency
   name: xml-simple
   requirement: !ruby/object:Gem::Requirement
@@ -218,25 +202,16 @@ files:
 - lib/solrizer/version.rb
 - lib/solrizer/xml.rb
 - lib/solrizer/xml/extractor.rb
-- lib/solrizer/xml/terminology_based_solrizer.rb
 - lib/tasks/solrizer.rake
 - solrizer.gemspec
 - spec/.rspec
 - 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/mods_article.rb
-- spec/fixtures/mods_articles/hydrangea_article1.xml
-- spec/fixtures/test_solr_mappings.yml
 - spec/spec_helper.rb
 - spec/units/common_spec.rb
 - spec/units/extractor_spec.rb
 - spec/units/field_mapper_spec.rb
 - spec/units/solrizer_spec.rb
 - spec/units/xml_extractor_spec.rb
-- spec/units/xml_terminology_based_solrizer_spec.rb
 homepage: http://github.com/projecthydra/solrizer
 licenses: []
 post_install_message: 
@@ -249,6 +224,9 @@ required_ruby_version: !ruby/object:Gem::Requirement
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
+      segments:
+      - 0
+      hash: 1646376342601153569
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -264,18 +242,10 @@ summary: A utility for building solr indexes, usually from Fedora repository con
   with solrizer-fedora extension gem.
 test_files:
 - 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/mods_article.rb
-- spec/fixtures/mods_articles/hydrangea_article1.xml
-- spec/fixtures/test_solr_mappings.yml
 - spec/spec_helper.rb
 - spec/units/common_spec.rb
 - spec/units/extractor_spec.rb
 - spec/units/field_mapper_spec.rb
 - spec/units/solrizer_spec.rb
 - spec/units/xml_extractor_spec.rb
-- spec/units/xml_terminology_based_solrizer_spec.rb
 has_rdoc: 

data/lib/solrizer/xml/terminology_based_solrizer.rb

@@ -1,92 +0,0 @@
-# This module is only suitable to mix into Classes that use the OM::XML::Document Module
-module Solrizer::XML::TerminologyBasedSolrizer
-  def self.included(klass)
-    klass.send(:include, Solrizer::Common)
-    klass.send(:extend, ClassMethods)
-  end
-  
-  # Module Methods
-  module ClassMethods
-  
-    # Build a solr document from +doc+ based on its terminology
-    # @param [OM::XML::Document] doc  
-    # @param [Hash] (optional) solr_doc (values hash) to populate
-    def solrize(doc, solr_doc=Hash.new, field_mapper = nil)
-      unless doc.class.terminology.nil?
-        doc.class.terminology.terms.each_pair do |term_name,term|
-          doc.solrize_term(term, solr_doc, field_mapper)
-        end
-      end
-
-      return solr_doc
-    end
-    
-    # Populate a solr document with fields based on nodes in +xml+ 
-    # Values for a term are gathered by to +term_pointer+ using OM::XML::TermValueOperators.term_values 
-    # and are deserialized by OM according to :type, as determined in its terminology.
-    # The content of the actual field in solr is each +node+ of the +nodeset+ returned by OM,
-    # rendered to a string.
-    # @param [OM::XML::Document] doc xml document to extract values from
-    # @param [OM::XML::Term] term corresponding to desired xml values
-    # @param [Hash] (optional) solr_doc (values hash) to populate
-    def solrize_term(doc, term, solr_doc = Hash.new, field_mapper = nil, opts={})
-      parents = opts.fetch(:parents, [])
-      term_pointer = parents+[term.name]
-      nodeset = doc.term_values(*term_pointer)
-      
-      nodeset.each do |n|
-        doc.solrize_node(n, term_pointer, term, solr_doc, field_mapper)
-# FIXME:  there should be no dependencies on OM in Solrizer
-        unless term.kind_of? OM::XML::NamedTermProxy
-          term.children.each_pair do |child_term_name, child_term|
-            doc.solrize_term(child_term, solr_doc, field_mapper, opts={:parents=>parents+[{term.name=>nodeset.index(n)}]})
-          end
-        end
-      end
-      solr_doc
-    end
-
-    # Populate a solr document with solr fields corresponding to the given xml node
-    # Field names are generated using settings from the term in the +doc+'s terminology corresponding to +term_pointer+
-    # If the supplied term does not have an index_as attribute, no indexing will be performed.
-    # @param [Nokogiri::XML::Node] node to solrize
-    # @param [OM::XML::Document] doc document the node came from
-    # @param [Array] term_pointer Array pointing to the term that should be used for solrization settings
-    # @param [Term] term the term to be solrized
-    # @param [Hash] (optional) solr_doc (values hash) to populate
-    # @return [Hash] the solr doc
-    def solrize_node(node_value, doc, term_pointer, term, solr_doc = Hash.new, field_mapper = nil, opts = {})
-      return solr_doc unless term.index_as && !term.index_as.empty?
-      
-# FIXME:  there should be no dependencies on OM in Solrizer
-      generic_field_name_base = OM::XML::Terminology.term_generic_name(*term_pointer)
-      create_and_insert_terms(generic_field_name_base, node_value, term.index_as, solr_doc)
-      
-      if term_pointer.length > 1
-# FIXME:  there should be no dependencies on OM in Solrizer
-        hierarchical_field_name_base = OM::XML::Terminology.term_hierarchical_name(*term_pointer)
-        create_and_insert_terms(hierarchical_field_name_base, node_value, term.index_as, solr_doc)
-      end
-      solr_doc
-    end
-
-  end
-
-  
-  # Instance Methods
-  
-  attr_accessor :field_mapper
-  
-  def to_solr(solr_doc = Hash.new, field_mapper = self.field_mapper) # :nodoc:
-    self.class.solrize(self, solr_doc, field_mapper)
-  end
-  
-  def solrize_term(term, solr_doc = Hash.new, field_mapper = self.field_mapper, opts={})
-    self.class.solrize_term(self, term, solr_doc, field_mapper, opts)    
-  end
-  
-  def solrize_node(node, term_pointer, term, solr_doc = Hash.new, field_mapper = self.field_mapper, opts={})
-    self.class.solrize_node(node, self, term_pointer, term, solr_doc, field_mapper, opts)
-  end
-  
-end

data/spec/fixtures/druid-bv448hq0314-extProperties.xml

@@ -1,52 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<document>
-  <attributes>
-    <attribute type="item">5958</attribute>
-    <attribute type="objectid">FEI0010-00013142</attribute>
-    <attribute type="title">Letter from Ellie Engelmore to Professor K. C. Reddy</attribute>
-    <attribute type="copyright">Presumed under copyright. Do not publish.</attribute>
-    <attribute type="description"/>
-    <attribute type="date">1985-12-30</attribute>
-    <attribute type="datestr">30/12/1985</attribute>
-    <attribute type="docurl">https://www.stanford.edu/group/salt_project/SLA/Feigenbaum/eaf7000/pdf/00013142.pdf</attribute>
-    <attribute type="doctn">http://www.stanford.edu/group/salt_project/cgi-bin/SLA/Feigenbaum/eaf7000/png/small_00013142.png</attribute>
-    <attribute type="url"/>
-    <attribute type="industryterm"/>
-    <attribute type="technology">artificial intelligence</attribute>
-    <attribute type="company"/>
-    <attribute type="person">ELLIE ENGELMORE</attribute>
-    <attribute type="year">1985</attribute>
-    <attribute type="organization">Mathematics and Computer/Information Sciences University of Hyderabad Central University P. O. Hyder</attribute>
-    <attribute type="sourcelocation">Folder 15</attribute>
-  </attributes>
-  <facets>
-    <facet type="year" id="49">1980s</facet>
-    <facet type="year" id="49">1985</facet>
-    <facet type="year" id="42">1980s</facet>
-    <facet type="sourcelocation" id="592">Feigenbaum</facet>
-    <facet type="sourcelocation" id="592">eaf7000</facet>
-    <facet type="sourcelocation" id="592">Box 51A</facet>
-    <facet type="sourcelocation" id="594">Feigenbaum</facet>
-    <facet type="sourcelocation" id="594">eaf7000</facet>
-    <facet type="sourcelocation" id="594">Box 51A</facet>
-    <facet type="sourcelocation" id="594">Folder 15</facet>
-    <facet type="sourcelocation" id="691">Feigenbaum</facet>
-    <facet type="sourcelocation" id="692">Feigenbaum</facet>
-    <facet type="sourcelocation" id="692">eaf7000</facet>
-    <facet type="doctype" id="32">Correspondence</facet>
-    <facet type="city" id="82">Ann Arbor</facet>
-    <facet type="city" id="910">Hyderabad</facet>
-    <facet type="city" id="1519">Palo Alto</facet>
-    <facet type="country" id="68">India</facet>
-    <facet type="emailaddress" id="288">EENGELMORE@SUMEX-AIM.ARPA</facet>
-    <facet type="organization" id="5065">Heuristic Programming Project</facet>
-    <facet type="organization" id="7012">Mathematics and Computer/Information Sciences University of Hyderabad Central University P. O. Hyder</facet>
-    <facet type="organization" id="8878">Professor K. C. Reddy School of Mathematics and Computer/Information Sciences</facet>
-    <facet type="person" id="5810">ELLIE ENGELMORE</facet>
-    <facet type="person" id="17934">Reddy</facet>
-    <facet type="person" id="5787">EDWARD FEIGENBAUM</facet>
-    <facet type="provinceorstate" id="96">Michigan</facet>
-    <facet type="provinceorstate" id="27">California</facet>
-    <facet type="technology" id="1713">artificial intelligence</facet>
-  </facets>
-</document>

data/spec/fixtures/druid-cm234kq4672-extProperties.xml

@@ -1,5 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<document>
- <attributes><attribute type="item">4290</attribute><attribute type="objectid">FEI0010-00011325</attribute><attribute type="title">Letter from Ellie Engelmore to Wemara Lichty</attribute><attribute type="copyright">Presumed under copyright. Do not publish.</attribute><attribute type="description"/><attribute type="date">1984-6-4</attribute><attribute type="datestr">4/6/1984</attribute><attribute type="docurl">https://www.stanford.edu/group/salt_project/SLA/Feigenbaum/eaf7000/pdf/00011325.pdf</attribute><attribute type="doctn">http://www.stanford.edu/group/salt_project/cgi-bin/SLA/Feigenbaum/eaf7000/png/small_00011325.png</attribute><attribute type="url"/><attribute type="industryterm"/><attribute type="technology">artificial intelligence</attribute><attribute type="company"/><attribute type="person">A. FEIGENBAUM</attribute><attribute type="year">1984</attribute><attribute type="organization">McAlcster Hall University</attribute><attribute type="sourcelocation">Folder 5</attribute></attributes>
- <facets><facet type="year" id="48">1980s</facet><facet type="year" id="48">1984</facet><facet type="year" id="42">1980s</facet><facet type="sourcelocation" id="578">Feigenbaum</facet><facet type="sourcelocation" id="578">eaf7000</facet><facet type="sourcelocation" id="578">Box 51</facet><facet type="sourcelocation" id="587">Feigenbaum</facet><facet type="sourcelocation" id="587">eaf7000</facet><facet type="sourcelocation" id="587">Box 51</facet><facet type="sourcelocation" id="587">Folder 5</facet><facet type="sourcelocation" id="692">Feigenbaum</facet><facet type="sourcelocation" id="692">eaf7000</facet><facet type="sourcelocation" id="691">Feigenbaum</facet><facet type="doctype" id="32">Correspondence</facet><facet type="city" id="1948">Stanford</facet><facet type="country" id="33">Columbia</facet><facet type="facility" id="2551">U. Missouri library</facet><facet type="organization" id="5065">Heuristic Programming Project</facet><facet type="organization" id="7026">McAlcster Hall University</facet><facet type="organization" id="9645">STANFORD UNIVERSITY</facet><facet type="organization" id="11964">University of Missouri</facet><facet type="organization" id="12407">Wemara Lichty Psychology Department</facet><facet type="person" id="15650">Morton Hunt</facet><facet type="person" id="37">A. FEIGENBAUM</facet><facet type="person" id="5810">ELLIE ENGELMORE</facet><facet type="provinceorstate" id="27">California</facet><facet type="provinceorstate" id="100">Missouri</facet><facet type="publishedmedium" id="44">Artificial Intelligence</facet><facet type="technology" id="1713">artificial intelligence</facet></facets>
-</document>

data/spec/fixtures/druid-cm234kq4672-stories.xml

@@ -1,17 +0,0 @@
-
-<html>
-  <body>
-    <pre>
-This is
-preformatted text.
-It preserves      both spaces
-and line breaks.
-</pre>
-    <p>The pre tag is good for displaying computer code:</p>
-    <pre>
-for i = 1 to 10
-     print i
-next i
-</pre>
-  </body>
-</html>

data/spec/fixtures/druid-hc513kw4806-descMetadata.xml

@@ -1,11 +0,0 @@
-<dc xmlns:dcterms="http://purl.org/dc/terms/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
-  <dcterms:type xsi:type="DCMITYPE">text</dcterms:type>
-  <dcterms:medium>Paper Document</dcterms:medium>
-  <dcterms:rights>Copyright © 2006 All rights reserved. Distribution for commercial purposes is prohibited.</dcterms:rights>
-  <dcterms:date/>
-  <dcterms:format>application/tiff</dcterms:format>
-  <dcterms:format>application/jp2000</dcterms:format>
-  <dcterms:format>application/pdf</dcterms:format>
-  <dcterms:title>The Rise and Fall of the YouTube Empire</dcterms:title>
-  <dcterms:publisher>Sample Unversity</dcterms:publisher>
-</dc>

data/spec/fixtures/mods_article.rb

@@ -1,90 +0,0 @@
-module Samples
-  class ModsArticle
-    
-    include OM::XML::Document
-    
-    set_terminology do |t|
-      t.root(:path=>"mods", :xmlns=>"http://www.loc.gov/mods/v3", :schema=>"http://www.loc.gov/standards/mods/v3/mods-3-2.xsd", "xmlns:foo"=>"http://my.custom.namespace")
-
-
-      t.title_info(:path=>"titleInfo") {
-        t.main_title(:index_as=>[:facetable],:path=>"title", :label=>"title") {
-          t.main_title_lang(:path=>{:attribute=> "xml:lang"})
-        }
-        t.french_title(:ref=>[:title_info,:main_title], :attributes=>{"xml:lang"=>"fre"})
-        
-        t.language(:index_as=>[:facetable, :stored_searchable],:path=>{:attribute=>"lang"})
-      } 
-      t.language{
-        t.lang_code(:index_as=>[:facetable], :path=>"languageTerm", :attributes=>{:type=>"code"})
-      }
-      t.abstract(:index_as=>[:stored_searchable])
-      t.subject {
-        t.topic(:index_as=>[:facetable])
-      }      
-      t.topic_tag(:proxy=>[:subject, :topic], :index_as=>[:stored_searchable])    
-      # t.topic_tag(:index_as=>[:facetable],:path=>"subject", :default_content_path=>"topic")
-      # This is a mods:name.  The underscore is purely to avoid namespace conflicts.
-      t.name_ {
-        # this is a namepart
-        t.namePart(:type=>:string, :label=>"generic name")
-        # affiliations are great
-        t.affiliation
-        t.institution(:path=>"affiliation", :index_as=>[:facetable], :label=>"organization")
-        t.displayForm
-        t.role(:ref=>[:role])
-        t.description(:index_as=>[:facetable])
-        t.date(:path=>"namePart", :attributes=>{:type=>"date"})
-        t.last_name(:path=>"namePart", :attributes=>{:type=>"family"}, :index_as=>[:stored_searchable])
-        t.first_name(:path=>"namePart", :attributes=>{:type=>"given"}, :label=>"first name")
-        t.terms_of_address(:path=>"namePart", :attributes=>{:type=>"termsOfAddress"})
-        t.computing_id
-        t.name_content(:path=>"text()")
-      }
-      # lookup :person, :first_name        
-      t.person(:ref=>:name, :attributes=>{:type=>"personal"}, :index_as=>[:facetable])
-      t.department(:proxy=>[:person,:description],:index_as=>[:facetable])
-      t.organization(:ref=>:name, :attributes=>{:type=>"corporate"}, :index_as=>[:facetable])
-      t.conference(:ref=>:name, :attributes=>{:type=>"conference"}, :index_as=>[:facetable])
-      t.role {
-        t.text(:path=>"roleTerm",:attributes=>{:type=>"text"}, :index_as=>[:stored_searchable])
-        t.code(:path=>"roleTerm",:attributes=>{:type=>"code"})
-      }
-      t.journal(:path=>'relatedItem', :attributes=>{:type=>"host"}) {
-        t.title_info(:index_as=>[:facetable],:ref=>[:title_info])
-        t.origin_info(:path=>"originInfo") {
-          t.publisher
-          t.date_issued(:path=>"dateIssued", :type => :date, :index_as => [:stored_searchable])
-          t.issuance(:index_as=>[:facetable])
-        }
-        t.issn(:path=>"identifier", :attributes=>{:type=>"issn"})
-        t.issue(:path=>"part") {
-          t.volume(:path=>"detail", :attributes=>{:type=>"volume"}, :default_content_path=>"number")
-          t.level(:path=>"detail", :attributes=>{:type=>"number"}, :default_content_path=>"number")
-          t.extent
-          t.pages(:path=>"extent", :attributes=>{:unit=>"pages"}) {
-            t.start
-            t.end
-          }
-          t.start_page(:proxy=>[:pages, :start])
-          t.end_page(:proxy=>[:pages, :end])
-          t.publication_date(:path=>"date", :type => :date, :index_as => [:stored_searchable])
-        }
-      }
-      t.note
-      t.location(:path=>"location") {
-        t.url(:path=>"url")
-      }
-      t.publication_url(:proxy=>[:location,:url])
-      t.title(:proxy=>[:title_info, :main_title])
-      t.journal_title(:proxy=>[:journal, :title_info, :main_title])
-      t.pub_date(:proxy=>[:journal, :issue, :publication_date])
-      t.issue_date(:ref=>[:journal, :origin_info, :date_issued], :type=> :date)
-    end
-    
-    # Changes from OM::Properties implementation
-    # renamed family_name => last_name
-    # start_page & end_page now accessible as [:journal, :issue, :pages, :start] (etc.)
-
-  end
-end

data/spec/fixtures/mods_articles/hydrangea_article1.xml

@@ -1,90 +0,0 @@
-<mods version="3.0" xsi:schemaLocation="http://www.loc.gov/mods/v3
- http://www.loc.gov/standards/mods/v3/mods-3-0.xsd" xmlns="http://www.loc.gov/mods/v3" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
-
-    <titleInfo>
-        <nonSort>THE</nonSort>
-        <title xml:lang="eng">ARTICLE TITLE HYDRANGEA ARTICLE 1</title>
-        <subTitle>SUBTITLE</subTitle>
-    </titleInfo>
-    <titleInfo lang="finnish">
-        <title>Artikkelin otsikko Hydrangea artiklan 1</title>
-    </titleInfo>
-
-    <name type="personal">
-        <namePart type="family">FAMILY NAME</namePart>
-        <namePart type="given">GIVEN NAMES</namePart>
-        <namePart type="termsOfAddress">DR.</namePart>
-        <displayForm>NAME AS IT APPEARS</displayForm>
-        <affiliation>FACULTY, UNIVERSITY</affiliation>    
-        <role> 
-            <roleTerm authority="marcrelator" type="text">creator</roleTerm>
-        </role>
-        <role>
-            <roleTerm type="text">submitter</roleTerm>
-        </role>
-    </name>
-    
-    <name type="personal">
-        <namePart type="family">Gautama</namePart>
-        <namePart type="given">Siddartha</namePart>
-        <namePart type="termsOfAddress">Prince</namePart>
-        <affiliation>Nirvana</affiliation>    
-        <role> 
-            <roleTerm authority="marcrelator" type="text">teacher</roleTerm>
-        </role>
-    </name>
-
-    <typeOfResource>text</typeOfResource>
-    <genre authority="local">journal article</genre>
-
-    <abstract>ABSTRACT</abstract>
-    <subject>
-        <topic>TOPIC 1</topic>
-        <topic>TOPIC 2</topic>
-    </subject>
-    <subject authority="AUTHORITY SOURCE (RFCD, LCSH)">
-        <topic>CONTROLLED TERM</topic>
-    </subject>
-
-    <language>
-        <languageTerm authority="iso639-2b" type="code">en-aus </languageTerm>
-    </language>
-
-    <physicalDescription>
-        <internetMediaType>application/pdf</internetMediaType>
-        <extent>36 p.</extent>
-    </physicalDescription>
-
-    <relatedItem type="host">
-        <titleInfo>
-            <title>TITLE OF HOST JOURNAL</title>
-        </titleInfo>
-        <originInfo>
-            <publisher>PUBLISHER</publisher>
-            <dateIssued>2007-02-15</dateIssued>
-        </originInfo>
-        <identifier type="issn">0013-8908</identifier>    
-        <part>
-            <detail type="volume">
-                <number>2</number>
-            </detail>
-            <detail type="level">
-                <number>2</number>
-            </detail>
-            <extent unit="pages">
-                <start>195</start>
-                <end>230</end>
-            </extent>
-            <date>2007-02-01</date>
-        </part>            
-    </relatedItem>
-
-    <identifier type="uri">http://URL.edu.au/</identifier>
-    <identifier type="doi">doi:10.1006/jmbi.1995.0238</identifier>
-    <location>
-        <url>http://URL.edu.au/</url>
-    </location>        
-    <accessCondition type="restrictionOnAccess">EMBARGO NOTE</accessCondition>
-    <accessCondition type="use and reproduction">OPEN ACCESS</accessCondition>
-
-</mods>

data/spec/fixtures/test_solr_mappings.yml

@@ -1,16 +0,0 @@
-id: pid
-default: edible
-edible:
-  date: _edible_date
-  string: _edible_string
-  text: _edible_text
-  symbol: _edible_sym
-  integer: _edible_int
-  long: _edible_long
-  boolean: _edible_bool
-  float: _edible_float
-  double: _edible_double
-displayable: _display
-facetable: _facet
-sortable: _sort
-unstemmed_searchable: _unstem_search

data/spec/units/xml_terminology_based_solrizer_spec.rb

@@ -1,109 +0,0 @@
-require 'spec_helper'
-require 'fixtures/mods_article'
-
-# TODO:  there should be no dependencies on OM in Solrizer
-describe Solrizer::XML::TerminologyBasedSolrizer do
-  
-  before(:all) do
-    Samples::ModsArticle.send(:include, Solrizer::XML::TerminologyBasedSolrizer)
-  end
-  
-  before(:each) do
-    article_xml = fixture( File.join("mods_articles", "hydrangea_article1.xml") )
-    @mods_article = Samples::ModsArticle.from_xml(article_xml)
-  end
-  
-  describe ".to_solr" do
-  
-    it "should provide .to_solr and return a SolrDocument" do
-      @mods_article.should respond_to(:to_solr)
-      @mods_article.to_solr.should be_kind_of(Hash)
-    end
-  
-    it "should optionally allow you to provide the Hash to add fields to and return that document when done" do
-      doc = Hash.new
-      @mods_article.to_solr(doc).should equal(doc)
-    end
-  
-    it "should iterate through the terminology terms, calling .solrize_term on each and passing in the solr doc" do
-      solr_doc = Hash.new
-      @mods_article.field_mapper = Solrizer::FieldMapper.new
-      Samples::ModsArticle.terminology.terms.each_pair do |k,v|
-        @mods_article.should_receive(:solrize_term).with(v, solr_doc, @mods_article.field_mapper)
-      end
-      @mods_article.to_solr(solr_doc)
-    end
-  
-    it "should use Solr mappings to generate field names" do
-      solr_doc =  @mods_article.to_solr
-      solr_doc["abstract"].should be_nil
-      # NOTE:  OM's old default expected stored and indexed;  this is a change.
-      solr_doc["abstract_tesim"].should == ["ABSTRACT"]
-      solr_doc["title_info_1_language_tesim"].should == ["finnish"]
-      solr_doc["person_1_role_0_text_tesim"].should == ["teacher"]
-      # No index_as on the code field.
-      solr_doc["person_1_role_0_code_tesim"].should be_nil 
-      solr_doc["person_last_name_tesim"].sort.should == ["FAMILY NAME", "Gautama"]
-      solr_doc["topic_tag_tesim"].sort.should == ["CONTROLLED TERM", "TOPIC 1", "TOPIC 2"]
-      # These are a holdover from an old verison of OM
-      solr_doc['journal_0_issue_0_publication_date_dtsim'].should == ["2007-02-01T00:00:00Z"]
-    end
-
-  end
-
-  describe ".solrize_term" do
-  
-    it "should add fields to a solr document for all nodes corresponding to the given term and its children" do
-      solr_doc = Hash.new
-      result = @mods_article.solrize_term(Samples::ModsArticle.terminology.retrieve_term(:title_info), solr_doc)
-      result.should == solr_doc
-    end
-
-    it "should add multiple fields based on index_as" do
-      fake_solr_doc = {}
-      term = Samples::ModsArticle.terminology.retrieve_term(:name)
-      term.children[:namePart].index_as = [:searchable, :displayable, :facetable]
-
-      @mods_article.solrize_term(term, fake_solr_doc)
-      
-      expected_names = ["DR.", "FAMILY NAME", "GIVEN NAMES"]
-      %w(_teim _sim).each do |suffix|
-        actual_names = fake_solr_doc["name_0_namePart#{suffix}"].sort
-        actual_names.should == expected_names
-      end
-    end
-
-    it "should add fields based on type using proxy" do
-      unless RUBY_VERSION.match("1.8.7")
-        solr_doc = Hash.new
-        result = @mods_article.solrize_term(Samples::ModsArticle.terminology.retrieve_term(:pub_date), solr_doc)
-        solr_doc["pub_date_dtsim"].should == ["2007-02-01T00:00:00Z"]
-      end
-    end
-
-    it "should add fields based on type using ref" do
-      solr_doc = Hash.new
-      result = @mods_article.solrize_term(Samples::ModsArticle.terminology.retrieve_term(:issue_date), solr_doc)
-      solr_doc["issue_date_dtsim"].should == ["2007-02-15T00:00:00Z"]
-    end
-
-    it "shouldn't index terms where index_as is an empty array" do
-      fake_solr_doc = {}
-      term = Samples::ModsArticle.terminology.retrieve_term(:name)
-      term.children[:namePart].index_as = []
-
-      @mods_article.solrize_term(term, fake_solr_doc)
-      fake_solr_doc["name_0_namePart_teim"].should be_nil
-    end
-
-    it "should index terms where index_as is searchable" do
-      fake_solr_doc = {}
-      term = Samples::ModsArticle.terminology.retrieve_term(:name)
-      term.children[:namePart].index_as = [:searchable]
-
-      @mods_article.solrize_term(term, fake_solr_doc)
-      
-      fake_solr_doc["name_0_namePart_teim"].sort.should == ["DR.", "FAMILY NAME", "GIVEN NAMES"]
-    end
-  end
-end