gutenberg_rdf 0.0.2

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: bbef70a3ac7d39b2bb3c3e0945ba6d722ffa1d2b
+  data.tar.gz: 98cd1b9df8ad4ff1507cea7a2ade4686aee9302b
+SHA512:
+  metadata.gz: 0a2174ab980a295ec48ee2f8791b8bb8d12de541f8159d257f9e2e2ff57d0ad373e60ce40188e9a4007d5be0a54a98e3631532dee07820b609222112382b77e5
+  data.tar.gz: 2ee305ee3749ba4cfa6239af9acc49e6eea65f4d8ab461eccab474bc4bbdf47df433791b7b398b0a60eaac132255aa3f85123bca3a5e3f3814fa2881d0288deb

data/.gitignore

@@ -0,0 +1,20 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+
+.ruby-*
+.DS_Store

data/.rspec

@@ -0,0 +1,2 @@
+--color
+--format progress

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in gutenberg_rdf.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2013 Mike Cook
+
+MIT License
+
+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.md

@@ -0,0 +1,76 @@
+# Gutenberg RDF
+
+Gutenberg RDF is a Ruby wrapper for the Project Gutenberg RDF catalog book files,
+providing a nice API to all the metadata contained within.
+
+## Requirements
+
+*  Ruby 2.0 - this is so we get UTF-8 by default
+*  Nokogiri - for parsing the RDF
+
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'gutenberg_rdf'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install gutenberg_rdf
+
+## Usage
+
+    require 'gutenberg_rdf'
+
+    xml = Nokogiri::XML(File.new('/path/to/pg2746.rdf'))
+    book = GutenbergRdf::Rdf.new(xml)
+
+    puts book.id
+    #=> "2746"
+
+    puts book.type
+    #=> "Text"
+
+    puts book.title
+    #=> "Urbain Grandier"
+
+    puts book.subtitle
+    #=> "Celebrated Crimes"
+
+    puts book.authors.first.fullname
+    #=> "Alexandre Dumas"
+
+    puts book.subjects.first
+    #=> "Crime"
+
+    puts book.published
+    #=> "2004-09-22"
+
+    puts book.publisher
+    #=> "Project Gutenberg"
+
+    puts book.rights
+    #=> "Public domain in the USA."
+
+    puts book.language
+    #=> "en"
+
+    puts book.covers.first
+    #=> "http://www.gutenberg.org/ebooks/2746.cover.medium"
+
+    puts book.ebooks[3][:uri]
+    #=> "http://www.gutenberg.org/ebooks/2746.epub.images"
+
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/gutenberg_rdf.gemspec

@@ -0,0 +1,28 @@
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'gutenberg_rdf/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "gutenberg_rdf"
+  spec.version       = GutenbergRdf::VERSION
+  spec.authors       = ["Mike Cook"]
+  spec.email         = ["m@mikecook.co.uk"]
+  spec.summary       = %q{A Ruby wrapper for the Project Gutenberg RDF catalog files.}
+  spec.description   = %q{A Ruby wrapper providing a nice API for the Project Gutenberg RDF catalog files. See the README for more information.}
+  spec.homepage      = ""
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.required_ruby_version = ">= 2.0.0" # so we have UTF-8 by default
+
+  spec.add_dependency "nokogiri", "~> 1.6.0"
+
+  spec.add_development_dependency "bundler", "~> 1.3"
+  spec.add_development_dependency "rake"
+
+  spec.add_development_dependency "rspec", "~> 2.14.1"
+end

data/lib/gutenberg_rdf/rdf/agent.rb

@@ -0,0 +1,58 @@
+module GutenbergRdf
+  class Rdf
+    class Agent
+      attr_reader :xml
+
+      def initialize(xml)
+        @xml = xml
+      end
+
+      def id
+        xml.at_xpath('pgterms:agent').attribute('about').content.match(/\A\d\d\d\d\/agents\/(\d+)\z/)[1]
+      end
+
+      def fullname
+        [firstname, lastname].join(' ')
+      end
+
+      def lastname
+        @lastname ||= name_parts[:last]
+      end
+
+      def firstname
+        @firstname ||= name_parts[:first]
+      end
+
+      def birthdate
+        xml.at_xpath('pgterms:agent/pgterms:birthdate').text
+      end
+
+      def deathdate
+        xml.at_xpath('pgterms:agent/pgterms:deathdate').text
+      end
+
+      def webpage
+        xml.at_xpath('pgterms:agent/pgterms:webpage').attribute('resource').content
+      end
+
+      def aliases
+        entries = Array.new
+        xml.xpath('//pgterms:alias').each do |name|
+          entries << name.text
+        end
+        entries
+      end
+
+    private
+
+      def name_parts
+        parts = xml.xpath('//pgterms:name').text.split(/, */)
+        last  = parts.shift
+        first = parts.reverse.join(' ')
+
+        {first: first, last: last}
+      end
+
+    end
+  end
+end

data/lib/gutenberg_rdf/rdf.rb

@@ -0,0 +1,125 @@
+require 'date'
+
+module GutenbergRdf
+  class Rdf
+    attr_reader :xml
+
+    def initialize(xml)
+      @xml = xml.at_xpath('rdf:RDF')
+    end
+
+    def id
+      xml.at_xpath('pgterms:ebook').attribute('about').content.match(/\Aebooks\/(.+)\z/)[1]
+    end
+
+    def type
+      xml.at_xpath('pgterms:ebook/dcterms:type/rdf:Description/rdf:value').text
+    end
+
+    def title
+      titles.first
+    end
+
+    def subtitle
+      titles[1..-1].join(' - ')
+    end
+
+    def authors
+      @authors ||= extract_authors
+    end
+
+    def subjects
+      entries = Array.new
+      xml.xpath('pgterms:ebook//dcterms:subject').each do |entry|
+        next unless entry.at_xpath('rdf:Description/dcam:memberOf').attribute('resource').text.match(/LCSH\z/)
+        entry.xpath('rdf:Description//rdf:value').each do |value|
+          entries << value.text
+        end
+      end
+      entries
+    end
+
+    def published
+      xml.at_xpath('pgterms:ebook/dcterms:issued').text
+    end
+
+    def publisher
+      xml.at_xpath('pgterms:ebook/dcterms:publisher').text
+    end
+
+    def language
+      xml.at_xpath('pgterms:ebook/dcterms:language').text
+    end
+
+    def rights
+      xml.at_xpath('pgterms:ebook/dcterms:rights').text
+    end
+
+    def covers
+      official_cover_images.concat(other_cover_images).sort.uniq
+    end
+
+    def ebooks
+      files = Array.new
+      xml.xpath('//pgterms:file').each do |file|
+        uri = file.attribute('about').content
+        datatypes = separate_mimetype_and_encoding(file.at_xpath('dcterms:format/rdf:Description/rdf:value').text)
+        modified = DateTime.parse(file.at_xpath('dcterms:modified').text + '-07:00')
+        files << {uri: uri, mime_type: datatypes[:mimetype], encoding: datatypes[:encoding], modified: modified}
+      end
+      files
+    end
+
+  private
+
+    def titles
+      @titles ||= split_title_and_subtitle
+    end
+
+    def split_title_and_subtitle
+      # Note this gsub is replacing UTF-8 hyphens with normal ASCII ones
+      t = xml.at_xpath('pgterms:ebook/dcterms:title').text.gsub(/—/, '-')
+
+      title_array = t.split(/\n/)
+      title_array = title_array.first.split(/:/) if title_array.count == 1
+      title_array = title_array.first.split(/;/) if title_array.count == 1
+
+      title_array.each(&:strip!)
+    end
+
+    def extract_authors
+      entries = Array.new
+      xml.xpath('//pgterms:agent').each do |agent|
+        entries << Agent.new(agent)
+      end
+      entries
+    end
+
+    def official_cover_images
+      entries = Array.new
+      xml.xpath('//pgterms:file').each do |file|
+        url = file.attribute('about').content
+        entries << url if file.xpath('dcterms:format/rdf:Description//rdf:value').detect { |v| v.text.match(/image/) }
+      end
+      entries
+    end
+
+    def other_cover_images
+      entries = Array.new
+      xml.xpath('pgterms:ebook//pgterms:marc901').each do |node|
+        cover = node.text
+        cover.sub!(/\Afile:\/\/\/public\/vhost\/g\/gutenberg\/html/, 'http://www.gutenberg.org')
+        entries << cover
+      end
+      entries
+    end
+
+    def separate_mimetype_and_encoding(string)
+      parts = string.split(/; */)
+      m = parts.shift
+      e = parts.join(';').sub('charset=', '')
+      {mimetype: m, encoding: e}
+    end
+
+  end
+end

data/lib/gutenberg_rdf/version.rb

@@ -0,0 +1,3 @@
+module GutenbergRdf
+  VERSION = "0.0.2"
+end

data/lib/gutenberg_rdf.rb

@@ -0,0 +1,13 @@
+require 'nokogiri'
+
+require "gutenberg_rdf/rdf"
+require "gutenberg_rdf/rdf/agent"
+require "gutenberg_rdf/version"
+
+module GutenbergRdf
+
+  def self.parse(path)
+    Rdf.new(Nokogiri::XML(File.new(path)))
+  end
+
+end

data/spec/gutenberg_rdf/rdf/agent_spec.rb

@@ -0,0 +1,112 @@
+require 'spec_helper'
+
+module GutenbergRdf
+  class Rdf
+    describe Agent do
+      let(:agent) do
+        xml = '<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:pgterms="http://www.gutenberg.org/2009/pgterms/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+                <pgterms:agent rdf:about="2009/agents/402">
+                  <pgterms:birthdate rdf:datatype="http://www.w3.org/2001/XMLSchema#integer">1830</pgterms:birthdate>
+                  <pgterms:deathdate rdf:datatype="http://www.w3.org/2001/XMLSchema#integer">1905</pgterms:deathdate>
+                  <pgterms:name>Doe, Jon James</pgterms:name>
+                  <pgterms:alias>Doe, Jon</pgterms:alias>
+                  <pgterms:alias>Doe, J. J.</pgterms:alias>
+                  <pgterms:webpage rdf:resource="http://en.wikipedia.org/wiki/Jon_James_Doe"/>
+                </pgterms:agent>
+              </rdf:RDF>'
+        rdf = Nokogiri::XML(xml)
+        Agent.new(rdf.at_xpath('rdf:RDF'))
+      end
+
+      it "expects an agent ID" do
+        expect(agent.id).to eql '402'
+      end
+
+      it "expects the last name" do
+        expect(agent.lastname).to eql 'Doe'
+      end
+
+      it "expects the first name(s)" do
+        expect(agent.firstname).to eql 'Jon James'
+      end
+
+      it "expects the full name" do
+        expect(agent.fullname).to eql 'Jon James Doe'
+      end
+
+      it "expects a birth date" do
+        expect(agent.birthdate).to eql '1830'
+      end
+
+      it "expects a death date" do
+        expect(agent.deathdate).to eql '1905'
+      end
+
+      it "expects a webpage" do
+        expect(agent.webpage).to eql 'http://en.wikipedia.org/wiki/Jon_James_Doe'
+      end
+
+      it "expects any alias names" do
+        expect(agent.aliases[0]).to eql 'Doe, Jon'
+        expect(agent.aliases[1]).to eql 'Doe, J. J.'
+      end
+
+      context "when only a single name is given" do
+        let(:agent) do
+          xml = '<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:pgterms="http://www.gutenberg.org/2009/pgterms/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+                   <pgterms:agent rdf:about="2009/agents/402">
+                     <pgterms:name>Dato</pgterms:name>
+                   </pgterms:agent>
+                 </rdf:RDF>'
+          rdf = Nokogiri::XML(xml)
+          Agent.new(rdf.at_xpath('rdf:RDF'))
+        end
+
+        it "expects it to be assigned to the last name" do
+          expect(agent.lastname).to eql 'Dato'
+        end
+        it "expects firstname to be an empty string" do
+          expect(agent.firstname).to eql ''
+        end
+      end
+
+      context "when the name has a suffix" do
+        let(:agent) do
+          xml = '<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:pgterms="http://www.gutenberg.org/2009/pgterms/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+                   <pgterms:agent rdf:about="2009/agents/402">
+                     <pgterms:name>Doe, Jon, Sir</pgterms:name>
+                   </pgterms:agent>
+                 </rdf:RDF>'
+          rdf = Nokogiri::XML(xml)
+          Agent.new(rdf.at_xpath('rdf:RDF'))
+        end
+
+        it "expects the correct name order" do
+          expect(agent.firstname).to eql 'Sir Jon'
+          expect(agent.lastname).to eql 'Doe'
+        end
+      end
+
+      context "when full name is given in (brackets)" do
+        let(:agent) do
+          xml = '<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:pgterms="http://www.gutenberg.org/2009/pgterms/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+                   <pgterms:agent agent:about="2009/agents/402">
+                     <pgterms:name>Doe, J. J. (Jon James)</pgterms:name>
+                   </pgterms:agent>
+                 </rdf:RDF>'
+          rdf = Nokogiri::XML(xml)
+          Agent.new(rdf.at_xpath('rdf:RDF'))
+        end
+
+        it "expects initials to replaced by name in brackets" do
+          pending "Not yet implemented"
+          expect(agent.firstname).to eql 'Jon James'
+          expect(agent.lastname).to eql 'Doe'
+        end
+        it "expects the name (excluding name in brackets) to be added to the aliases"
+        it "should not have duplicate aliases"
+      end
+    end
+
+  end
+end

data/spec/gutenberg_rdf/rdf_spec.rb

@@ -0,0 +1,374 @@
+require 'spec_helper'
+
+module GutenbergRdf
+  describe Rdf do
+    let(:xml) do
+      '<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:pgterms="http://www.gutenberg.org/2009/pgterms/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+           <pgterms:ebook rdf:about="ebooks/98765">
+             <dcterms:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2006-09-28</dcterms:issued>
+             <dcterms:language rdf:datatype="http://purl.org/dc/terms/RFC4646">en</dcterms:language>
+             <dcterms:publisher>Project Gutenberg</dcterms:publisher>
+             <dcterms:rights>Public domain in the USA.</dcterms:rights>
+           </pgterms:ebook>
+       </rdf:RDF>'
+    end
+    let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+
+    it "expects an id" do
+      expect(rdf.id).to eql "98765"
+    end
+    it "expects a published date" do
+      expect(rdf.published).to eql "2006-09-28"
+    end
+    it "expects a publisher" do
+      expect(rdf.publisher).to eql "Project Gutenberg"
+    end
+    it "expects a language" do
+      expect(rdf.language).to eql "en"
+    end
+    it "expects the rights" do
+      expect(rdf.rights).to eql "Public domain in the USA."
+    end
+
+    describe "#type" do
+      let(:xml) do
+        '<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:pgterms="http://www.gutenberg.org/2009/pgterms/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+           <pgterms:ebook rdf:about="ebooks/98765">
+             <dcterms:type>
+               <rdf:Description>
+                 <dcam:memberOf rdf:resource="http://purl.org/dc/terms/DCMIType"/>
+                 <rdf:value>Text</rdf:value>
+               </rdf:Description>
+             </dcterms:type>
+           </pgterms:ebook>
+         </rdf:RDF>'
+      end
+      let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+
+      it "expect the type of entity" do
+        expect(rdf.type).to eql 'Text'
+      end
+    end
+
+    describe "Titles" do
+      let(:xml) do
+        '<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:pgterms="http://www.gutenberg.org/2009/pgterms/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+           <pgterms:ebook rdf:about="ebooks/98765">
+             <dcterms:title>A Great Title</dcterms:title>
+           </pgterms:ebook>
+         </rdf:RDF>'
+      end
+      let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+
+      it "expects a title" do
+        expect(rdf.title).to eql 'A Great Title'
+      end
+      it "expects subtitle to be empty" do
+        expect(rdf.subtitle).to eql ''
+      end
+
+      context "with a title and subtitle, on separate lines" do
+        let(:xml) do
+          '<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:pgterms="http://www.gutenberg.org/2009/pgterms/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+            <pgterms:ebook rdf:about="ebooks/98765">
+              <dcterms:title>A Great Multi-Title
+                Or, a Subtitle</dcterms:title>
+            </pgterms:ebook>
+          </rdf:RDF>'
+        end
+        let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+
+        it "expects the title to be the first line" do
+          expect(rdf.title).to eql 'A Great Multi-Title'
+        end
+        it "expects the subtitle to be the second line" do
+          expect(rdf.subtitle).to eql 'Or, a Subtitle'
+        end
+      end
+
+      context "when title:subtitle are separated by a colon" do
+        let(:xml) do
+          '<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:pgterms="http://www.gutenberg.org/2009/pgterms/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+            <pgterms:ebook rdf:about="ebooks/98765">
+              <dcterms:title>A Great Multi-Title: And a Subtitle</dcterms:title>
+            </pgterms:ebook>
+          </rdf:RDF>'
+        end
+        let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+
+        it "expects a title" do
+          expect(rdf.title).to eql 'A Great Multi-Title'
+        end
+        it "expects a subtitle" do
+          expect(rdf.subtitle).to eql 'And a Subtitle'
+        end
+      end
+
+      context "when title; and subtitle are separated by a semi-colon" do
+        let(:xml) do
+          '<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:pgterms="http://www.gutenberg.org/2009/pgterms/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+            <pgterms:ebook rdf:about="ebooks/98765">
+              <dcterms:title>A Great Multi-Title; Or, a Subtitle</dcterms:title>
+            </pgterms:ebook>
+          </rdf:RDF>'
+        end
+        let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+        it "expects a title" do
+          expect(rdf.title).to eql 'A Great Multi-Title'
+        end
+        it "expects a subtitle" do
+          expect(rdf.subtitle).to eql 'Or, a Subtitle'
+        end
+
+        context "...except when subtitles already exists" do
+          let(:xml) do
+            '<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:pgterms="http://www.gutenberg.org/2009/pgterms/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+            <pgterms:ebook rdf:about="ebooks/98765">
+              <dcterms:title>A Great Multi-Title; and some other text
+                Then a Subtitle on a newline</dcterms:title>
+            </pgterms:ebook>
+          </rdf:RDF>'
+          end
+          let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+          it "expects a title" do
+            expect(rdf.title).to eql 'A Great Multi-Title; and some other text'
+          end
+          it "expects a subtitle" do
+            expect(rdf.subtitle).to eql 'Then a Subtitle on a newline'
+          end
+        end
+      end
+    end
+
+    describe "#authors" do
+      let(:xml) do
+        '<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:pgterms="http://www.gutenberg.org/2009/pgterms/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+          <pgterms:agent rdf:about="2009/agents/402">
+            <pgterms:birthdate rdf:datatype="http://www.w3.org/2001/XMLSchema#integer">1830</pgterms:birthdate>
+            <pgterms:deathdate rdf:datatype="http://www.w3.org/2001/XMLSchema#integer">1905</pgterms:deathdate>
+            <pgterms:name>Dodge, Mary Mapes</pgterms:name>
+            <pgterms:alias>Dodge, Mary</pgterms:alias>
+            <pgterms:webpage rdf:resource="http://en.wikipedia.org/wiki/Mary_Mapes_Dodge"/>
+          </pgterms:agent>
+          <pgterms:agent rdf:about="2009/agents/116">
+            <pgterms:alias>Verschillende</pgterms:alias>
+            <pgterms:name>Various</pgterms:name>
+          </pgterms:agent>
+        </rdf:RDF>'
+      end
+      let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+      it "expects a Array" do
+        expect(rdf.authors.class).to be Array
+      end
+      it "expects correct number to be returned" do
+        expect(rdf.authors.count).to be 2
+      end
+      it "expects an author object" do
+        expect(rdf.authors.first.class).to be Rdf::Agent
+      end
+    end
+
+    describe "#subjects" do
+      let(:xml) do
+        %q{<rdf:RDF xmlns:dcam="http://purl.org/dc/dcam/" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:pgterms="http://www.gutenberg.org/2009/pgterms/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+           <pgterms:ebook rdf:about="ebooks/98765">
+             <dcterms:subject>
+               <rdf:Description>
+                 <dcam:memberOf rdf:resource="http://purl.org/dc/terms/LCSH"/>
+                 <rdf:value>Children's literature -- Periodicals</rdf:value>
+                 <rdf:value>Children's periodicals, American</rdf:value>
+               </rdf:Description>
+             </dcterms:subject>
+             <dcterms:subject>
+               <rdf:Description>
+                 <dcam:memberOf rdf:resource="http://purl.org/dc/terms/LCC"/>
+                 <rdf:value>PZ</rdf:value>
+               </rdf:Description>
+             </dcterms:subject>
+           </pgterms:ebook>
+        </rdf:RDF>}
+      end
+      let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+      it "expects correct number to be returned" do
+        expect(rdf.subjects.count).to be 2
+      end
+      it "expects the correct data" do
+        expect(rdf.subjects.first).to eql "Children's literature -- Periodicals"
+        expect(rdf.subjects.last).to eql "Children's periodicals, American"
+      end
+    end
+
+    describe "#covers" do
+      describe "official PG covers" do
+        let(:xml) do
+          '<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:pgterms="http://www.gutenberg.org/2009/pgterms/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+             <pgterms:ebook rdf:about="ebooks/12345">
+               <dcterms:hasFormat rdf:resource="http://www.gutenberg.org/ebooks/12345.epub.noimages"/>
+               <dcterms:hasFormat rdf:resource="http://www.gutenberg.org/ebooks/12345.cover.medium"/>
+               <dcterms:hasFormat rdf:resource="http://www.gutenberg.org/ebooks/12345.cover.small"/>
+               <pgterms:marc901>http://www.gutenberg.org/files/12345/12345-h/images/cover.jpg</pgterms:marc901>
+             </pgterms:ebook>
+             <pgterms:file rdf:about="http://www.gutenberg.org/ebooks/12345.epub.noimages">
+               <dcterms:extent rdf:datatype="http://www.w3.org/2001/XMLSchema#integer">92652</dcterms:extent>
+               <dcterms:format>
+                 <rdf:Description>
+                   <dcam:memberOf rdf:resource="http://purl.org/dc/terms/IMT"/>
+                   <rdf:value rdf:datatype="http://purl.org/dc/terms/IMT">application/epub+zip</rdf:value>
+                 </rdf:Description>
+               </dcterms:format>
+               <dcterms:isFormatOf rdf:resource="ebooks/12345"/>
+               <dcterms:modified rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2013-09-21T19:22:32.115259</dcterms:modified>
+             </pgterms:file>
+             <pgterms:file rdf:about="http://www.gutenberg.org/ebooks/12345.cover.medium">
+               <dcterms:extent rdf:datatype="http://www.w3.org/2001/XMLSchema#integer">10856</dcterms:extent>
+               <dcterms:format>
+                 <rdf:Description>
+                   <dcam:memberOf rdf:resource="http://purl.org/dc/terms/IMT"/>
+                   <rdf:value rdf:datatype="http://purl.org/dc/terms/IMT">image/jpeg</rdf:value>
+                 </rdf:Description>
+               </dcterms:format>
+               <dcterms:isFormatOf rdf:resource="ebooks/12345"/>
+               <dcterms:modified rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2013-09-21T19:22:34.484114</dcterms:modified>
+             </pgterms:file>
+             <pgterms:file rdf:about="http://www.gutenberg.org/ebooks/12345.cover.small">
+               <dcterms:extent rdf:datatype="http://www.w3.org/2001/XMLSchema#integer">1904</dcterms:extent>
+               <dcterms:format>
+                 <rdf:Description>
+                   <dcam:memberOf rdf:resource="http://purl.org/dc/terms/IMT"/>
+                   <rdf:value rdf:datatype="http://purl.org/dc/terms/IMT">image/jpeg</rdf:value>
+                 </rdf:Description>
+               </dcterms:format>
+               <dcterms:isFormatOf rdf:resource="ebooks/12345"/>
+               <dcterms:modified rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2013-09-21T19:22:34.379124</dcterms:modified>
+             </pgterms:file>
+           </rdf:RDF>'
+        end
+        let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+
+        it "expects the correct number of entries returned" do
+          expect(rdf.covers.count).to be 3
+        end
+        it "expects those to be used" do
+          expect(rdf.covers[0]).to eql 'http://www.gutenberg.org/ebooks/12345.cover.medium'
+          expect(rdf.covers[1]).to eql 'http://www.gutenberg.org/ebooks/12345.cover.small'
+        end
+        it "expects any other images to be listed after the official ones" do
+          expect(rdf.covers[2]).to eql 'http://www.gutenberg.org/files/12345/12345-h/images/cover.jpg'
+        end
+      end
+
+      describe "HTML ebook cover image" do
+        let(:xml) do
+          '<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:pgterms="http://www.gutenberg.org/2009/pgterms/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+             <pgterms:ebook rdf:about="ebooks/12345">
+               <pgterms:marc901>file:///public/vhost/g/gutenberg/html/files/12345/12345-rst/images/cover.jpg</pgterms:marc901>
+               <pgterms:marc901>file:///public/vhost/g/gutenberg/html/files/12345/12345-h/images/cover.jpg</pgterms:marc901>
+               <pgterms:marc901>http://www.gutenberg.org/files/12345/12345-h/images/cover.jpg</pgterms:marc901>
+             </pgterms:ebook>
+           </rdf:RDF>'
+        end
+        let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+
+        it "expects only unique entries" do
+          expect(rdf.covers.count).to be 2
+        end
+        it "should convert File URIs to the Gutenberg URL" do
+          expect(rdf.covers.first).to match 'http://www.gutenberg.org'
+        end
+        it "expects the covers to be listed in the correct order" do
+          expect(rdf.covers[0]).to eql 'http://www.gutenberg.org/files/12345/12345-h/images/cover.jpg'
+          expect(rdf.covers[1]).to eql 'http://www.gutenberg.org/files/12345/12345-rst/images/cover.jpg'
+        end
+      end
+    end
+
+    describe "#ebook" do
+      let(:xml) do
+        '<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:pgterms="http://www.gutenberg.org/2009/pgterms/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+          <pgterms:ebook rdf:about="ebooks/98765">
+            <dcterms:hasFormat rdf:resource="http://www.gutenberg.org/ebooks/98765.txt.utf-8"/>
+            <dcterms:hasFormat rdf:resource="http://www.gutenberg.org/ebooks/98765.zip"/>
+          </pgterms:ebook>
+          <pgterms:file rdf:about="http://www.gutenberg.org/ebooks/98765.txt.utf-8">
+            <dcterms:extent rdf:datatype="http://www.w3.org/2001/XMLSchema#integer">293684</dcterms:extent>
+            <dcterms:format>
+              <rdf:Description>
+                <dcam:memberOf rdf:resource="http://purl.org/dc/terms/IMT"/>
+                <rdf:value rdf:datatype="http://purl.org/dc/terms/IMT">text/plain; charset=utf-8</rdf:value>
+              </rdf:Description>
+            </dcterms:format>
+            <dcterms:isFormatOf rdf:resource="ebooks/98765"/>
+            <dcterms:modified rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2010-02-16T08:29:52.373092</dcterms:modified>
+          </pgterms:file>
+          <pgterms:file rdf:about="http://www.gutenberg.org/files/98765/98765.zip">
+            <dcterms:extent rdf:datatype="http://www.w3.org/2001/XMLSchema#integer">116685</dcterms:extent>
+            <dcterms:format>
+              <rdf:Description>
+                <dcam:memberOf rdf:resource="http://purl.org/dc/terms/IMT"/>
+                <rdf:value rdf:datatype="http://purl.org/dc/terms/IMT">application/zip</rdf:value>
+                <rdf:value rdf:datatype="http://purl.org/dc/terms/IMT">text/plain; charset=us-ascii</rdf:value>
+              </rdf:Description>
+            </dcterms:format>
+            <dcterms:isFormatOf rdf:resource="ebooks/98765"/>
+            <dcterms:modified rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2006-09-28T12:37:26</dcterms:modified>
+          </pgterms:file>
+        </rdf:RDF>'
+      end
+      let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+
+      it "expects the correct number of entries" do
+        expect(rdf.ebooks.count).to be 2
+      end
+      it "expects an entry Hash to have the correct keys" do
+        expect(rdf.ebooks.first).to have_key :uri
+        expect(rdf.ebooks.first).to have_key :mime_type
+        expect(rdf.ebooks.first).to have_key :encoding
+        expect(rdf.ebooks.first).to have_key :modified
+      end
+      it "expcts the modified value to be a DateTime" do
+        expect(rdf.ebooks.first[:modified].class).to be DateTime
+      end
+
+      it "should return the URL" do
+        expect(rdf.ebooks.first[:uri]).to eql 'http://www.gutenberg.org/ebooks/98765.txt.utf-8'
+      end
+      it "should return the mime_type" do
+        expect(rdf.ebooks.first[:mime_type]).to eql 'text/plain'
+      end
+      it "should return the encoding" do
+        expect(rdf.ebooks.first[:encoding]).to eql 'utf-8'
+      end
+      it "should return the modified datetime" do
+        expect(rdf.ebooks.first[:modified].to_s).to eql '2010-02-16T08:29:52-07:00'
+      end
+
+      context "when there are two mime-types" do
+        let(:xml) do
+          '<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:pgterms="http://www.gutenberg.org/2009/pgterms/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+             <pgterms:file rdf:about="http://www.gutenberg.org/files/98765/98765.zip">
+               <dcterms:extent rdf:datatype="http://www.w3.org/2001/XMLSchema#integer">116685</dcterms:extent>
+               <dcterms:format>
+                 <rdf:Description>
+                   <dcam:memberOf rdf:resource="http://purl.org/dc/terms/IMT"/>
+                   <rdf:value rdf:datatype="http://purl.org/dc/terms/IMT">application/zip</rdf:value>
+                   <rdf:value rdf:datatype="http://purl.org/dc/terms/IMT">text/plain; charset=us-ascii</rdf:value>
+                 </rdf:Description>
+               </dcterms:format>
+               <dcterms:isFormatOf rdf:resource="ebooks/98765"/>
+               <dcterms:modified rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2006-09-28T12:37:26</dcterms:modified>
+             </pgterms:file>
+          </rdf:RDF>'
+        end
+        let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+
+        it "should use just the first one" do
+          expect(rdf.ebooks.first[:mime_type]).to eql 'application/zip'
+        end
+        it "expects the encoding to be an empty string" do
+          expect(rdf.ebooks.first[:encoding]).to eql ''
+        end
+      end
+    end
+
+  end
+end

data/spec/gutenberg_rdf_spec.rb

@@ -0,0 +1,16 @@
+require 'spec_helper'
+
+module GutenbergRdf
+  describe ".parse" do
+    let(:file) { StringIO.new('<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:pgterms="http://www.gutenberg.org/2009/pgterms/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"><pgterms:ebook rdf:about="ebooks/98765"/></rdf:RDF>') }
+
+    it "expects an Rdf object" do
+      File.stub(:new).and_return(file)
+      book = GutenbergRdf.parse(file)
+
+      expect(book.class).to be Rdf
+      expect(book.id).to eql '98765'
+    end
+
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,9 @@
+require 'gutenberg_rdf'
+
+RSpec.configure do |config|
+  config.mock_with :rspec
+  config.treat_symbols_as_metadata_keys_with_true_values = true
+  config.run_all_when_everything_filtered = true
+  config.filter_run :focus
+  config.order = 'random'
+end

metadata

@@ -0,0 +1,120 @@
+--- !ruby/object:Gem::Specification
+name: gutenberg_rdf
+version: !ruby/object:Gem::Version
+  version: 0.0.2
+platform: ruby
+authors:
+- Mike Cook
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-10-18 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.6.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.6.0
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 2.14.1
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 2.14.1
+description: A Ruby wrapper providing a nice API for the Project Gutenberg RDF catalog
+  files. See the README for more information.
+email:
+- m@mikecook.co.uk
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- .rspec
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- gutenberg_rdf.gemspec
+- lib/gutenberg_rdf.rb
+- lib/gutenberg_rdf/rdf.rb
+- lib/gutenberg_rdf/rdf/agent.rb
+- lib/gutenberg_rdf/version.rb
+- spec/gutenberg_rdf/rdf/agent_spec.rb
+- spec/gutenberg_rdf/rdf_spec.rb
+- spec/gutenberg_rdf_spec.rb
+- spec/spec_helper.rb
+homepage: ''
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: 2.0.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.0.6
+signing_key: 
+specification_version: 4
+summary: A Ruby wrapper for the Project Gutenberg RDF catalog files.
+test_files:
+- spec/gutenberg_rdf/rdf/agent_spec.rb
+- spec/gutenberg_rdf/rdf_spec.rb
+- spec/gutenberg_rdf_spec.rb
+- spec/spec_helper.rb