gutenberg_rdf 0.0.2 → 0.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: bbef70a3ac7d39b2bb3c3e0945ba6d722ffa1d2b
-  data.tar.gz: 98cd1b9df8ad4ff1507cea7a2ade4686aee9302b
+  metadata.gz: cde8f277e56fe12183ccc5386414bb2161d8fed3
+  data.tar.gz: c5ece359a2fa5e80addb608e5441440e9a46f2cb
 SHA512:
-  metadata.gz: 0a2174ab980a295ec48ee2f8791b8bb8d12de541f8159d257f9e2e2ff57d0ad373e60ce40188e9a4007d5be0a54a98e3631532dee07820b609222112382b77e5
-  data.tar.gz: 2ee305ee3749ba4cfa6239af9acc49e6eea65f4d8ab461eccab474bc4bbdf47df433791b7b398b0a60eaac132255aa3f85123bca3a5e3f3814fa2881d0288deb
+  metadata.gz: 92fe622ad63fac10e422b6f4597d14d0fd7e933d8efbe82c68f8f103fe4112a529746eceaadcbe3457432fd9bb298c95018284292b9727d9a0ea0cd06c5ca314
+  data.tar.gz: 45324adf7e17df7e5faeaf1b2b599d8d73bd056d8e3ee82205950e6e1409db114d838c8fb6ef11eba9df1330d0d08a5364e2467ab07095cca50765a2bbd505f0

data/README.md

@@ -6,7 +6,6 @@ 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
@@ -27,8 +26,7 @@ Or install it yourself as:
 
     require 'gutenberg_rdf'
 
-    xml = Nokogiri::XML(File.new('/path/to/pg2746.rdf'))
-    book = GutenbergRdf::Rdf.new(xml)
+    book = GutenbergRdf.parse('/path/to/pg2746.rdf')
 
     puts book.id
     #=> "2746"

data/gutenberg_rdf.gemspec

@@ -8,7 +8,7 @@ Gem::Specification.new do |spec|
   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.description   = %q{A Ruby wrapper for the Project Gutenberg RDF catalog files (requires Ruby 2).}
   spec.homepage      = ""
   spec.license       = "MIT"
 
@@ -19,10 +19,5 @@ Gem::Specification.new do |spec|
 
   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

@@ -8,7 +8,7 @@ module GutenbergRdf
       end
 
       def id
-        xml.at_xpath('pgterms:agent').attribute('about').content.match(/\A\d\d\d\d\/agents\/(\d+)\z/)[1]
+        xml.elements['pgterms:agent'].attributes['about'].match(/\A\d\d\d\d\/agents\/(\d+)\z/)[1]
       end
 
       def fullname
@@ -24,20 +24,20 @@ module GutenbergRdf
       end
 
       def birthdate
-        xml.at_xpath('pgterms:agent/pgterms:birthdate').text
+        xml.elements['pgterms:agent/pgterms:birthdate'].text
       end
 
       def deathdate
-        xml.at_xpath('pgterms:agent/pgterms:deathdate').text
+        xml.elements['pgterms:agent/pgterms:deathdate'].text
       end
 
       def webpage
-        xml.at_xpath('pgterms:agent/pgterms:webpage').attribute('resource').content
+        xml.elements['pgterms:agent/pgterms:webpage'].attributes['resource']
       end
 
       def aliases
         entries = Array.new
-        xml.xpath('//pgterms:alias').each do |name|
+        xml.elements.each('pgterms:agent/pgterms:alias') do |name|
           entries << name.text
         end
         entries
@@ -46,7 +46,7 @@ module GutenbergRdf
     private
 
       def name_parts
-        parts = xml.xpath('//pgterms:name').text.split(/, */)
+        parts = xml.elements['pgterms:agent/pgterms:name'].text.split(/, */)
         last  = parts.shift
         first = parts.reverse.join(' ')
 

data/lib/gutenberg_rdf/rdf.rb

@@ -5,15 +5,15 @@ module GutenbergRdf
     attr_reader :xml
 
     def initialize(xml)
-      @xml = xml.at_xpath('rdf:RDF')
+      @xml = xml.root
     end
 
     def id
-      xml.at_xpath('pgterms:ebook').attribute('about').content.match(/\Aebooks\/(.+)\z/)[1]
+      xml.elements['pgterms:ebook'].attributes['about'].match(/\Aebooks\/(.+)\z/)[1]
     end
 
     def type
-      xml.at_xpath('pgterms:ebook/dcterms:type/rdf:Description/rdf:value').text
+      xml.elements['pgterms:ebook/dcterms:type/rdf:Description/rdf:value'].text
     end
 
     def title
@@ -30,9 +30,9 @@ module GutenbergRdf
 
     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|
+      xml.elements.each('pgterms:ebook/dcterms:subject') do |entry|
+        next unless entry.elements['rdf:Description/dcam:memberOf'].attributes['resource'].match(/LCSH\z/)
+        entry.elements.each('rdf:Description//rdf:value') do |value|
           entries << value.text
         end
       end
@@ -40,19 +40,19 @@ module GutenbergRdf
     end
 
     def published
-      xml.at_xpath('pgterms:ebook/dcterms:issued').text
+      xml.elements['pgterms:ebook/dcterms:issued'].text
     end
 
     def publisher
-      xml.at_xpath('pgterms:ebook/dcterms:publisher').text
+      xml.elements['pgterms:ebook/dcterms:publisher'].text
     end
 
     def language
-      xml.at_xpath('pgterms:ebook/dcterms:language').text
+      xml.elements['pgterms:ebook/dcterms:language'].text
     end
 
     def rights
-      xml.at_xpath('pgterms:ebook/dcterms:rights').text
+      xml.elements['pgterms:ebook/dcterms:rights'].text
     end
 
     def covers
@@ -61,10 +61,10 @@ module GutenbergRdf
 
     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')
+      xml.elements.each('pgterms:file') do |file|
+        uri = file.attributes['about']
+        datatypes = separate_mimetype_and_encoding(file.elements['dcterms:format/rdf:Description/rdf:value'].text)
+        modified = DateTime.parse(file.elements['dcterms:modified'].text + '-07:00')
         files << {uri: uri, mime_type: datatypes[:mimetype], encoding: datatypes[:encoding], modified: modified}
       end
       files
@@ -77,8 +77,8 @@ module GutenbergRdf
     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(/—/, '-')
+      # NOTE: this gsub is replacing UTF-8 hyphens with normal ASCII ones
+      t = xml.elements['pgterms:ebook/dcterms:title'].text.gsub(/—/, '-')
 
       title_array = t.split(/\n/)
       title_array = title_array.first.split(/:/) if title_array.count == 1
@@ -89,24 +89,30 @@ module GutenbergRdf
 
     def extract_authors
       entries = Array.new
-      xml.xpath('//pgterms:agent').each do |agent|
-        entries << Agent.new(agent)
+      xml.elements.each('pgterms:agent') do |agent|
+        entries << Agent.new(agent.root)
       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/) }
+      xml.elements.each('pgterms:file') do |file|
+        entries << file.attributes['about'] if file_is_image?(file)
       end
       entries
     end
 
+    def file_is_image?(node)
+      node.elements.each('dcterms:format/rdf:Description/rdf:value') do |value|
+        return true if value.text.match(/image/)
+      end
+      false
+    end
+
     def other_cover_images
       entries = Array.new
-      xml.xpath('pgterms:ebook//pgterms:marc901').each do |node|
+      xml.elements.each('pgterms:ebook/pgterms:marc901') do |node|
         cover = node.text
         cover.sub!(/\Afile:\/\/\/public\/vhost\/g\/gutenberg\/html/, 'http://www.gutenberg.org')
         entries << cover

data/lib/gutenberg_rdf/version.rb

@@ -1,3 +1,3 @@
 module GutenbergRdf
-  VERSION = "0.0.2"
+  VERSION = "0.1.0"
 end

data/lib/gutenberg_rdf.rb

@@ -1,4 +1,4 @@
-require 'nokogiri'
+require 'rexml/document'
 
 require "gutenberg_rdf/rdf"
 require "gutenberg_rdf/rdf/agent"
@@ -7,7 +7,7 @@ require "gutenberg_rdf/version"
 module GutenbergRdf
 
   def self.parse(path)
-    Rdf.new(Nokogiri::XML(File.new(path)))
+    Rdf.new(REXML::Document.new(File.new(path)))
   end
 
 end

data/spec/gutenberg_rdf/rdf/agent_spec.rb

@@ -14,8 +14,8 @@ module GutenbergRdf
                   <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'))
+        rdf = REXML::Document.new(xml)
+        Agent.new(rdf.root)
       end
 
       it "expects an agent ID" do
@@ -58,8 +58,8 @@ module GutenbergRdf
                      <pgterms:name>Dato</pgterms:name>
                    </pgterms:agent>
                  </rdf:RDF>'
-          rdf = Nokogiri::XML(xml)
-          Agent.new(rdf.at_xpath('rdf:RDF'))
+          rdf = REXML::Document.new(xml)
+          Agent.new(rdf.root)
         end
 
         it "expects it to be assigned to the last name" do
@@ -77,8 +77,8 @@ module GutenbergRdf
                      <pgterms:name>Doe, Jon, Sir</pgterms:name>
                    </pgterms:agent>
                  </rdf:RDF>'
-          rdf = Nokogiri::XML(xml)
-          Agent.new(rdf.at_xpath('rdf:RDF'))
+          rdf = REXML::Document.new(xml)
+          Agent.new(rdf.root)
         end
 
         it "expects the correct name order" do
@@ -94,8 +94,8 @@ module GutenbergRdf
                      <pgterms:name>Doe, J. J. (Jon James)</pgterms:name>
                    </pgterms:agent>
                  </rdf:RDF>'
-          rdf = Nokogiri::XML(xml)
-          Agent.new(rdf.at_xpath('rdf:RDF'))
+          rdf = REXML::Document.new(xml)
+          Agent.new(rdf.root)
         end
 
         it "expects initials to replaced by name in brackets" do

data/spec/gutenberg_rdf/rdf_spec.rb

@@ -12,7 +12,7 @@ module GutenbergRdf
            </pgterms:ebook>
        </rdf:RDF>'
     end
-    let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+    let(:rdf) { Rdf.new(REXML::Document.new(xml)) }
 
     it "expects an id" do
       expect(rdf.id).to eql "98765"
@@ -32,7 +32,7 @@ module GutenbergRdf
 
     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#">
+        '<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:type>
                <rdf:Description>
@@ -43,7 +43,7 @@ module GutenbergRdf
            </pgterms:ebook>
          </rdf:RDF>'
       end
-      let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+      let(:rdf) { Rdf.new(REXML::Document.new(xml)) }
 
       it "expect the type of entity" do
         expect(rdf.type).to eql 'Text'
@@ -58,7 +58,7 @@ module GutenbergRdf
            </pgterms:ebook>
          </rdf:RDF>'
       end
-      let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+      let(:rdf) { Rdf.new(REXML::Document.new(xml)) }
 
       it "expects a title" do
         expect(rdf.title).to eql 'A Great Title'
@@ -76,7 +76,7 @@ module GutenbergRdf
             </pgterms:ebook>
           </rdf:RDF>'
         end
-        let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+        let(:rdf) { Rdf.new(REXML::Document.new(xml)) }
 
         it "expects the title to be the first line" do
           expect(rdf.title).to eql 'A Great Multi-Title'
@@ -94,7 +94,7 @@ module GutenbergRdf
             </pgterms:ebook>
           </rdf:RDF>'
         end
-        let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+        let(:rdf) { Rdf.new(REXML::Document.new(xml)) }
 
         it "expects a title" do
           expect(rdf.title).to eql 'A Great Multi-Title'
@@ -112,7 +112,7 @@ module GutenbergRdf
             </pgterms:ebook>
           </rdf:RDF>'
         end
-        let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+        let(:rdf) { Rdf.new(REXML::Document.new(xml)) }
         it "expects a title" do
           expect(rdf.title).to eql 'A Great Multi-Title'
         end
@@ -129,7 +129,7 @@ module GutenbergRdf
             </pgterms:ebook>
           </rdf:RDF>'
           end
-          let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+          let(:rdf) { Rdf.new(REXML::Document.new(xml)) }
           it "expects a title" do
             expect(rdf.title).to eql 'A Great Multi-Title; and some other text'
           end
@@ -156,7 +156,8 @@ module GutenbergRdf
           </pgterms:agent>
         </rdf:RDF>'
       end
-      let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+      let(:rdf) { Rdf.new(REXML::Document.new(xml)) }
+
       it "expects a Array" do
         expect(rdf.authors.class).to be Array
       end
@@ -188,7 +189,7 @@ module GutenbergRdf
            </pgterms:ebook>
         </rdf:RDF>}
       end
-      let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+      let(:rdf) { Rdf.new(REXML::Document.new(xml)) }
       it "expects correct number to be returned" do
         expect(rdf.subjects.count).to be 2
       end
@@ -201,7 +202,7 @@ module GutenbergRdf
     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#">
+          '<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/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"/>
@@ -243,7 +244,7 @@ module GutenbergRdf
              </pgterms:file>
            </rdf:RDF>'
         end
-        let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+        let(:rdf) { Rdf.new(REXML::Document.new(xml)) }
 
         it "expects the correct number of entries returned" do
           expect(rdf.covers.count).to be 3
@@ -267,7 +268,7 @@ module GutenbergRdf
              </pgterms:ebook>
            </rdf:RDF>'
         end
-        let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+        let(:rdf) { Rdf.new(REXML::Document.new(xml)) }
 
         it "expects only unique entries" do
           expect(rdf.covers.count).to be 2
@@ -284,7 +285,7 @@ module GutenbergRdf
 
     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#">
+        '<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:hasFormat rdf:resource="http://www.gutenberg.org/ebooks/98765.txt.utf-8"/>
             <dcterms:hasFormat rdf:resource="http://www.gutenberg.org/ebooks/98765.zip"/>
@@ -314,7 +315,7 @@ module GutenbergRdf
           </pgterms:file>
         </rdf:RDF>'
       end
-      let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+      let(:rdf) { Rdf.new(REXML::Document.new(xml)) }
 
       it "expects the correct number of entries" do
         expect(rdf.ebooks.count).to be 2
@@ -344,7 +345,7 @@ module GutenbergRdf
 
       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#">
+          '<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: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>
@@ -359,7 +360,7 @@ module GutenbergRdf
              </pgterms:file>
           </rdf:RDF>'
         end
-        let(:rdf) { Rdf.new(Nokogiri::XML(xml)) }
+        let(:rdf) { Rdf.new(REXML::Document.new(xml)) }
 
         it "should use just the first one" do
           expect(rdf.ebooks.first[:mime_type]).to eql 'application/zip'

metadata

@@ -1,57 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: gutenberg_rdf
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.1.0
 platform: ruby
 authors:
 - Mike Cook
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-10-18 00:00:00.000000000 Z
+date: 2013-10-19 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
@@ -66,8 +24,8 @@ dependencies:
     - - ~>
       - !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.
+description: A Ruby wrapper for the Project Gutenberg RDF catalog files (requires
+  Ruby 2).
 email:
 - m@mikecook.co.uk
 executables: []