mods 0.0.2 → 0.0.4

data/lib/mods/reader.rb

@@ -0,0 +1,41 @@
+module Mods
+  class Reader
+    
+    DEFAULT_NS_AWARE = false
+
+    # true if the XML parsing should be strict about using namespaces. 
+    attr_accessor :namespace_aware
+    attr_reader :mods_ng_xml
+    
+    # @param ns_aware true if the XML parsing should be strict about using namespaces.  Default is false
+    def initialize(ns_aware = DEFAULT_NS_AWARE)
+      @namespace_aware = ns_aware
+    end
+    
+    # @param str - a string containing mods xml
+    # @return a Nokogiri::XML::Document object
+    def from_str(str)
+      @mods_ng_xml = Nokogiri::XML(str)
+      normalize_mods
+      @mods_ng_xml
+    end
+  
+    # @param url (String) - url that has mods xml as its content
+    # @return a Nokogiri::XML::Document object
+    def from_url(url, encoding = nil, options = Nokogiri::XML::ParseOptions::DEFAULT_XML)
+      require 'open-uri'
+      @mods_ng_xml = Nokogiri::XML(open(url).read)
+      normalize_mods
+      @mods_ng_xml
+    end
+    
+    # Whatever we get, normalize it into a Nokogiri::XML::Document,
+    # strip any elements enclosing the mods record
+    def normalize_mods
+      if !@namespace_aware
+        @mods_ng_xml.remove_namespaces!
+      end
+    end
+    
+  end # class 
+end # module

data/lib/mods/record.rb

@@ -0,0 +1,145 @@
+require 'iso-639'
+
+module Mods
+
+  class Record
+
+    attr_reader :mods_ng_xml
+    # string to use when combining a title and subtitle, e.g. 
+    #  for title "MODS" and subtitle "Metadata Odious Delimited Stuff" and delimiter " : "
+    #  we get "MODS : Metadata Odious Delimited Stuff"
+    attr_accessor :title_delimiter
+
+    NS_HASH = {'m' => MODS_NS_V3}
+    
+    ATTRIBUTES = ['id', 'version']
+
+    # @param (String) what to use when combining a title and subtitle, e.g. 
+    #  for title "MODS" and subtitle "Metadata Odious Delimited Stuff" and delimiter " : "
+    #  we get "MODS : Metadata Odious Delimited Stuff"
+    def initialize(title_delimiter = Mods::TitleInfo::DEFAULT_TITLE_DELIM)
+      @title_delimiter = title_delimiter
+    end
+
+    # convenience method to call Mods::Reader.new.from_str and to nom
+    # @param ns_aware true if the XML parsing should be strict about using namespaces.  Default is false
+    # @param str - a string containing mods xml
+    def from_str(str, ns_aware = false)
+      @mods_ng_xml = Mods::Reader.new(ns_aware).from_str(str)
+      if ns_aware
+        set_terminology_ns(@mods_ng_xml)
+      else
+        set_terminology_no_ns(@mods_ng_xml)
+      end
+    end
+
+    # convenience method to call Mods::Reader.new.from_url and to nom
+    # @param ns_aware true if the XML parsing should be strict about using namespaces.  Default is false
+    # @param url (String) - url that has mods xml as its content
+    def from_url(url, namespace_aware = false)
+      @mods_ng_xml = Mods::Reader.new(ns_aware).from_url(url)
+      if ns_aware
+        set_terminology_ns(@mods_ng_xml)
+      else
+        set_terminology_no_ns(@mods_ng_xml)
+      end
+    end
+
+    # @return Array of Strings, each containing the text contents of <mods><titleInfo>   <nonSort> + ' ' + <title> elements
+    #  but not including any titleInfo elements with type="alternative"
+    def short_titles
+      @mods_ng_xml.title_info.short_title.map { |n| n }
+    end
+
+    # @return Array of Strings, each containing the text contents of <mods><titleInfo>   <nonSort> + ' ' + <title> + (delim) + <subTitle> elements
+    def full_titles
+      @mods_ng_xml.title_info.full_title.map { |n| n }
+    end
+        
+    # @return Array of Strings, each containing the text contents of <mods><titleInfo @type="alternative"><title>  elements
+    def alternative_titles
+      @mods_ng_xml.title_info.alternative_title.map { |n| n }
+    end
+    
+    # @return String containing sortable title for this mods record
+    def sort_title
+      @mods_ng_xml.title_info.sort_title.find { |n| !n.nil? }
+    end
+    
+    
+    # use the displayForm of a personal name if present
+    #   if no displayForm, try to make a string from family name and given name "family_name, given_name"
+    #   otherwise, return all nameParts concatenated together
+    # @return Array of Strings, each containing the above described string
+    def personal_names
+      @mods_ng_xml.personal_name.map { |n|
+        if n.displayForm.size > 0
+          n.displayForm.text
+        elsif n.family_name.size > 0
+          n.given_name.size > 0 ? n.family_name.text + ', ' + n.given_name.text : n.family_name.text
+        else
+          n.namePart.text
+        end
+      }
+    end
+
+    # use the displayForm of a corporate name if present
+    #   otherwise, return all nameParts concatenated together
+    # @return Array of Strings, each containing the above described string
+    def corporate_names
+      @mods_ng_xml.corporate_name.map { |n|
+        if n.displayForm.size > 0
+          n.displayForm.text
+        else
+          n.namePart.text 
+        end
+      }
+    end
+    
+    # Translates iso-639 language codes, and leaves everything else alone.
+    # @return Array of Strings, each a (hopefully English) name of a language
+    def languages
+      result = []
+      @mods_ng_xml.language.each { |n| 
+        # get languageTerm codes and add their translations to the result
+        n.code_term.each { |ct| 
+          if ct.authority.match(/^iso639/)
+            begin
+              vals = ct.text.split(/[,|\ ]/).reject {|x| x.strip.length == 0 } 
+              vals.each do |v|
+                result << ISO_639.find(v.strip).english_name
+              end
+            rescue => e
+              p "Couldn't find english name for #{code.text}"
+              result << ct.text
+            end
+          else
+            result << ct.text
+          end
+        }
+        # add languageTerm text values
+        n.text_term.each { |tt| 
+          val = tt.text.strip
+          result << val if val.length > 0
+        }
+          
+        # add language values that aren't in languageTerm subelement
+        if n.languageTerm.size == 0
+          result << n.text
+        end
+      }
+      result.uniq
+    end
+
+
+    def method_missing method_name, *args
+      if mods_ng_xml.respond_to?(method_name)
+        mods_ng_xml.send(method_name, *args)
+      else
+        super.method_missing(method_name, *args)
+      end
+    end
+    
+  end # class Record
+
+end # module Mods

data/lib/mods/title_info.rb

@@ -0,0 +1,24 @@
+module Mods
+  # NAOMI_MUST_COMMENT_THIS_CLASS
+  class TitleInfo
+#    attr_reader :ng_node
+    
+    NS_HASH = {'m' => MODS_NS_V3}
+    SUBELEMENTS = ['title', 'subTitle', 'partNumber', 'partName', 'nonSort']
+        
+    # attributes on titleInfo node
+    ATTRIBUTES = ['type', 'authority', 'authorityURI', 'valueURI', 'displayLabel', 'supplied', 'usage', 'altRepGroup', 'nameTitleGroup']
+
+    # valid values for type attribute on titleInfo node <titleInfo type="val">
+    TYPES = ['abbreviated', 'translated', 'alternative', 'uniform']
+    
+    DEFAULT_TITLE_DELIM = ' '
+    
+    # @param (Nokogiri::XML::Node) mods:titleInfo node
+#    def initialize(title_info_node)
+#      @ng_node = title_info_node
+#    end
+    
+  end
+  
+end

data/lib/mods/version.rb

@@ -1,3 +1,4 @@
 module Mods
-  VERSION = "0.0.2"
+  # this is the Ruby Gem version
+  VERSION = "0.0.4"
 end

data/mods.gemspec

@@ -3,21 +3,27 @@ require File.expand_path('../lib/mods/version', __FILE__)
 
 Gem::Specification.new do |gem|
   gem.name          = "mods"
-  gem.authors       = ["Naomi Dushay", "Bess Sadler"]
   gem.version       = Mods::VERSION
+  gem.authors       = ["Naomi Dushay", "Bess Sadler"]
   gem.email         = ["ndushay AT stanford.edu", "bess AT stanford.edu"]
-  gem.description   = %q{A Ruby gem to parse MODS (Metadata Object Description Schema) records}
-  gem.summary       = %q{A Ruby gem to parse MODS (Metadata Object Description Schema) records.  More information about MODS can be found at http://www.loc.gov/standards/mods/registry.php.}
-  gem.homepage      = ""
+  gem.description   = "Parse MODS (Metadata Object Description Schema) records.  More information about MODS can be found at http://www.loc.gov/standards/mods/"
+  gem.summary       = "Parse MODS (Metadata Object Description Schema) records."
+  gem.homepage      = "https://github.com/sul-dlss/mods"
 
+  gem.extra_rdoc_files = ["LICENSE", "README.rdoc"]
   gem.files         = `git ls-files`.split($\)
   gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
-  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.test_files    = gem.files.grep(%r{^spec/})
   gem.require_paths = ["lib"]
   
-  # Runtime dependencies
   gem.add_dependency 'nokogiri'
+  gem.add_dependency 'nom-xml'
+  gem.add_dependency 'iso-639'
+
+  # Runtime dependencies
+  # gem.add_runtime_dependency 'nokogiri'
 
+  # Development dependencies
   # Bundler will install these gems too if you've checked out solrmarc-wrapper source from git and run 'bundle install'
   # It will not add these as dependencies if you require solrmarc-wrapper for other projects
   gem.add_development_dependency "rake"

data/spec/language_spec.rb

@@ -0,0 +1,69 @@
+require 'spec_helper'
+
+describe "Mods <language> Element" do
+  before(:all) do
+    @mods_rec = Mods::Record.new
+    @simple = '<mods><language>Greek</language></mods>'
+    @iso639_2b_code = '<mods><language><languageTerm authority="iso639-2b" type="code">fre</languageTerm></language></mods>'
+    @iso639_2b_text = '<mods><language><languageTerm authority="iso639-2b" type="text">English</languageTerm></language></mods>'
+    @mult_codes = '<mods><language><languageTerm authority="iso639-2b" type="code">per ara, dut</languageTerm></language></mods>'
+    @mult_code_terms = '<mods><language><languageTerm authority="iso639-2b" type="code">spa</languageTerm><languageTerm authority="iso639-2b" type="code">dut</languageTerm></language></mods>'
+    @mult_text_terms = '<mods><language><languageTerm authority="iso639-2b" type="text">Chinese</languageTerm><languageTerm authority="iso639-2b" type="text">Spanish</languageTerm></language></mods>'
+  end
+
+  context "basic language terminology pieces" do
+    before(:all) do
+      @mods_rec.from_str(@iso639_2b_code)
+    end
+    it "should understand languageTerm.type_at attribute" do
+      @mods_rec.language.languageTerm.type_at.should == ["code"]
+    end
+    it "should understand languageTerm.authority attribute" do
+      @mods_rec.language.languageTerm.authority.should == ["iso639-2b"]
+    end
+    it "should understand languageTerm value" do
+      @mods_rec.language.languageTerm.text.should == "fre"
+      @mods_rec.language.languageTerm.size.should == 1
+    end
+    it "should get one language.code_term for each languageTerm element with a type attribute of 'code'" do
+      @mods_rec.language.code_term.size.should == 1
+      @mods_rec.language.code_term.text.should == "fre"
+      @mods_rec.from_str(@mult_code_terms)
+      @mods_rec.language.code_term.size.should == 2
+      @mods_rec.language.code_term.first.text.should include("spa")
+      @mods_rec.language.code_term[1].text.should == "dut"
+    end
+    it "should get one language.text_term for each languageTerm element with a type attribute of 'text'" do
+      @mods_rec.from_str(@mult_text_terms)
+      @mods_rec.language.text_term.size.should == 2
+      @mods_rec.language.text_term.first.text.should include("Chinese")
+      @mods_rec.language.text_term[1].text.should == "Spanish"
+    end
+  end
+  
+  context "Mods::Record.languages convenience method" do
+    
+    it "should translate iso639-2b codes to English" do
+      @mods_rec.from_str(@iso639_2b_code)
+      @mods_rec.languages.should == ["French"]
+    end
+    
+    it "should pass thru language values that are already text (not code)" do
+      @mods_rec.from_str(@iso639_2b_text)
+      @mods_rec.languages.should == ["English"]
+    end
+    
+    it "should keep values that are not inside <languageTerm> elements" do
+      @mods_rec.from_str(@simple)
+      @mods_rec.languages.should == ["Greek"]
+    end
+    
+    it "should create a separate value for each language in a comma, space, or | separated list " do
+      @mods_rec.from_str(@mult_codes)
+      @mods_rec.languages.should include("Arabic")
+      @mods_rec.languages.should include("Persian")
+      @mods_rec.languages.should include("Dutch; Flemish")
+    end
+  end
+  
+end

data/spec/location_spec.rb

@@ -0,0 +1,148 @@
+require 'spec_helper'
+
+describe "Mods <location> Element" do
+  before(:all) do
+    @mods_rec = Mods::Record.new
+    @url_and_phys = '<mods><location>
+                <url displayLabel="Digital collection of 46 images available online" usage="primary display">http://searchworks.stanford.edu/?f%5Bcollection%5D%5B%5D=The+Reid+W.+Dennis+Collection+of+California+Lithographs&amp;view=gallery</url>
+              </location><location>
+                <physicalLocation>Department of Special Collections, Stanford University Libraries, Stanford, CA 94305.</physicalLocation>
+              </location></mods>'
+    # from http://www.loc.gov/standards/mods/v3/mods-userguide-elements.html !!
+    #  sublocation is not allowed directly under location
+    @incorrect = '<mods><location>
+                    	<physicalLocation>Library of Congress </physicalLocation>
+                    	<sublocation>Prints and Photographs Division Washington, D.C. 20540 USA</sublocation>
+                    	<shelfLocator>DAG no. 1410</shelfLocator>
+                  </location></mods>'
+  end
+
+  context "basic location terminology pieces" do
+    before(:all) do
+      @mods_rec.from_str(@form_and_extent)
+    end
+    
+    context "physicalLocation child element" do
+      before(:all) do
+        @phys_loc_only = '<mods><location><physicalLocation>here</physicalLocation></location></mods>'
+        @phys_loc_authority = '<mods><location><physicalLocation authority="marcorg">MnRM</physicalLocation></location></mods>'
+      end
+      it "should have access to text value of element" do
+        @mods_rec.from_str(@phys_loc_only)
+        @mods_rec.location.physicalLocation.text.should == "here"
+        @mods_rec.from_str(@phys_loc_authority)
+        @mods_rec.location.physicalLocation.map { |n| n.text }.should == ["MnRM"]
+      end
+      it "should recognize authority attribute" do
+        @mods_rec.from_str(@phys_loc_authority)
+        @mods_rec.location.physicalLocation.authority.should == ["marcorg"]
+      end
+      it "should recognize displayLabel attribute" do
+        @mods_rec.from_str('<mods><location><physicalLocation displayLabel="Correspondence">some address</physicalLocation></location></mods>')
+        @mods_rec.location.physicalLocation.displayLabel.should == ["Correspondence"]
+      end      
+    end
+    
+    it "shelfLocator child element" do
+      shelf_loc = '<mods><location>
+                      	<physicalLocation>Library of Congress </physicalLocation>
+                      	<shelfLocator>DAG no. 1410</shelfLocator>
+                    </location></mods>'
+      @mods_rec.from_str(shelf_loc)
+      @mods_rec.location.shelfLocator.map { |n| n.text }.should == ["DAG no. 1410"]
+    end
+
+    context "url child element" do
+      before(:all) do
+        @empty_loc_url = '<mods><location><url/></location></mods>'
+        @mult_flavor_loc_urls = '<mods><location>
+                  	<url access="preview">http://preview.org</url>
+                  	<url access="object in context">http://context.org</url>
+                  	<url access="raw object">http://object.org</url>
+                </location></mods>'
+      end
+      it "should have access to text value of element" do
+        urls = @mods_rec.from_str(@mult_flavor_loc_urls).location.url.map { |e| e.text }
+        urls.size.should == 3
+        urls.should include("http://preview.org")
+        urls.should include("http://context.org")
+        urls.should include("http://object.org")
+      end
+      context "attributes" do
+        before(:all) do
+          @url_attribs = '<mods><location>
+                      <url displayLabel="Digital collection of 46 images available online" usage="primary display">http://searchworks.stanford.edu/?f%5Bcollection%5D%5B%5D=The+Reid+W.+Dennis+Collection+of+California+Lithographs&amp;view=gallery</url>
+                    </location></mods>'
+        end
+        it "should recognize displayLabel attribute" do
+          @mods_rec.from_str(@url_attribs).location.url.displayLabel.should == ["Digital collection of 46 images available online"]
+        end
+        it "should recognize access attribute" do
+          vals = @mods_rec.from_str(@mult_flavor_loc_urls).location.url.access
+          vals.size.should == 3
+          vals.should include("preview")
+          vals.should include("object in context")
+          vals.should include("raw object")
+        end
+        it "should recognize usage attribute" do
+          @mods_rec.from_str(@url_attribs).location.url.usage.should == ["primary display"]
+        end
+        it "should recognize note attribute" do
+          @mods_rec.from_str('<mods><location><url note="something">http://somewhere.org</url></location></mods>')
+          @mods_rec.location.url.note.should == ["something"]
+        end
+        it "should recognize dateLastAccessed attribute" do
+          @mods_rec.from_str('<mods><location><url dateLastAccessed="something">http://somewhere.org</url></location></mods>')
+          @mods_rec.location.url.dateLastAccessed.should == ["something"]
+        end
+      end # attributes
+      it "should have array with empty string for single empty url element" do
+        @mods_rec.from_str(@empty_loc_url).location.url.map { |n| n.text }.should == [""]
+      end
+    end # url child element
+    
+    it "holdingSimple child element" do
+      xml = '<mods><location>
+        	<physicalLocation authority="marcorg">MnRM</physicalLocation>
+        	<holdingSimple>
+        	  	<copyInformation>
+        	  	  	<sublocation>Patient reading room</sublocation>
+        	  	  	<shelfLocator>QH511.A1J68</shelfLocator>
+        	  	  	<enumerationAndChronology unitType="1"> v.1-v.8 1970-1976</enumerationAndChronology>
+        	  	</copyInformation>
+        	</holdingSimple></location></mods>'
+      @mods_rec.from_str(xml).location.holdingSimple.should be_an_instance_of(Nokogiri::XML::NodeSet)
+      @mods_rec.from_str(xml).location.holdingSimple.first.should be_an_instance_of(Nokogiri::XML::Element)
+    end
+    it "holdingComplex child element" do
+      xml = '<mods>
+      <location>
+      <physicalLocation>Menlo Park Public Library</physicalLocation> 	 
+        	<holdingExternal> 	 
+        	<holding xmlns:iso20775="info:ofi/fmt:xml:xsd:iso20775" xsi:schemaLocation="info:ofi/fmt:xml:xsd:iso20775 http://www.loc.gov/standards/iso20775/N130_ISOholdings_v6_1.xsd"> 	 
+        	  	<institutionIdentifier> 	  	 
+        	  	<value>JRF</value> 	  	 
+        	  	<typeOrSource> 	  	 
+        	  	  	<pointer>http://worldcat.org/registry/institutions/</pointer> 	 
+        	  	</typeOrSource> 	  	 
+        	  	</institutionIdentifier> 	  	 
+        	  	  	<physicalLocation>Menlo Park Public Library</physicalLocation> 	  	 
+        	  	  	<physicalAddress> 	  	  	 
+        	  	  	<text>Menlo Park, CA 94025 United States </text> 	  	 
+        	  	  	  	</physicalAddress> 	  	 
+        	  	  	  	  	<electronicAddress> 	  	 
+        	  	  	  	  	<text>http://www.worldcat.org/wcpa/oclc/15550774? page=frame&amp;url=%3D%3FUTF-8%3FB%FaHR0cDovL2NhdGFsb2cucGxzaW5mby5vcmcvc2VhcmNoL2kwMTk1MDM4NjMw%3F%3D&amp;title=Menlo+Park+Public+Library&amp;linktype=opac&amp;detail=JRF%3AMenlo+Park+Public+Library%3APublic&amp;app=wcapi&amp;id=OCL-OCLC+Staff+use</text>
+        	  	  	  	  	</electronicAddress> 	  	  	 
+        	  	  	  	  	<holdingSimple> 	  	  	 
+        	  	  	  	  	  	<copiesSummary> 	  	  	 
+        	  	  	  	  	  	  	<copiesCount>1</copiesCount> 	  	  	 
+        	  	  	  	  	  	</copiesSummary> 	  	  	 
+        	  	  	  	</holdingSimple> 	  	  	 
+        	  	</holding> 	  	  	 
+        	  	  	  	</holdingExternal>
+          </mods>'
+      @mods_rec.from_str(xml).location.holdingExternal.should be_an_instance_of(Nokogiri::XML::NodeSet)
+      @mods_rec.from_str(xml).location.holdingExternal.first.should be_an_instance_of(Nokogiri::XML::Element)
+    end
+  end
+end