repub 0.3.3 → 0.3.4

data/lib/repub/epub/opf.rb

@@ -0,0 +1,136 @@
+require 'rubygems'
+require 'builder'
+
+module Repub
+  module Epub
+  
+  # Open Packaging Format (OPF) 2.0 wrapper
+  # (see http://www.idpf.org/2007/opf/OPF_2.0_final_spec.html)
+  #
+  class OPF
+    include ContainerItem
+    
+    def initialize(uid, file_path = 'package.opf')
+      @file_path = file_path
+      @media_type = 'application/oebps-package+xml'
+      @metadata = Metadata.new('Untitled', 'en', uid, Date.today.to_s)
+      @items = []
+    end
+    
+    class Metadata < Struct.new(
+        :title,
+        :language,
+        :identifier,
+        :date,
+        :subject,
+        :description,
+        :relation,
+        :creator,
+        :publisher,
+        :rights
+      )
+      
+      def to_xml(builder)
+        builder.metadata 'xmlns:dc' => "http://purl.org/dc/elements/1.1/",
+          'xmlns:dcterms' => "http://purl.org/dc/terms/",
+          'xmlns:xsi' => "http://www.w3.org/2001/XMLSchema-instance",
+          'xmlns:opf' => "http://www.idpf.org/2007/opf" do
+            # Required elements
+            builder.dc :title do
+              builder << self.title
+            end
+            builder.dc :language, 'xsi:type' => "dcterms:RFC3066" do
+              builder << self.language
+            end
+            builder.dc :identifier, :id => 'dcidid', 'opf:scheme' => 'URI' do
+              builder << self.identifier
+            end
+            # Optional elements
+            builder.dc :subject do
+              builder << self.subject
+            end if self.subject
+            builder.dc :description do
+              builder << self.description
+            end if self.description
+            builder.dc :relation do
+              builder << self.relation
+            end if self.relation
+            builder.dc :creator do                  # TODO: roles
+              builder << self.creator
+            end if self.creator
+            builder.dc :publisher do
+              builder << self.publisher
+            end if self.publisher
+            builder.dc :date do
+              builder << self.date.to_s
+            end if self.date
+            builder.dc :rights do
+              builder << self.rights
+            end if self.rights
+        end
+      end
+    end
+    
+    attr_reader :metadata
+    attr_reader :items
+    
+    def <<(item)
+      if item.kind_of? NCX
+        @ncx = item
+      elsif item.kind_of? ContainerItem
+        @items << item
+      elsif item.is_a? String
+        @items << Item.new(item)
+      else
+        raise "Unsupported item class: #{item.class}"
+      end
+    end
+
+    def to_xml
+      out = ''
+      builder = Builder::XmlMarkup.new(:target => out)
+      builder.instruct!
+      builder.package :xmlns => "http://www.idpf.org/2007/opf",
+          'unique-identifier' => "dcidid",
+          'version' => "2.0" do
+        @metadata.to_xml(builder)
+        manifest_to_xml(builder)
+        spine_to_xml(builder)
+      end
+      out
+    end
+    
+    def save
+      File.open(@file_path, 'w') do |f|
+        f << to_xml
+      end
+    end
+    
+    private
+
+    def item_id(index)
+      "item-#{index + 1}"
+    end
+    
+    def manifest_to_xml(builder)
+      builder.manifest do
+        # NCX has fixed id
+        builder.item :id => 'ncx', :href => @ncx.file_path, 'media-type' => @ncx.media_type if @ncx
+        @items.each_with_index do |item, index|
+          builder.item :id => item_id(index), :href => item.file_path, 'media-type' => item.media_type
+        end
+      end
+    end
+    
+    def spine_to_xml(builder)
+      # toc attribute points to the NCX item in manifest
+      builder.spine :toc => 'ncx' do
+        @items.each_with_index do |item, index|
+          builder.itemref :idref => item_id(index) if item.document?
+        end
+      end
+    end
+  end
+  
+  end
+end

data/repub.gemspec

@@ -2,11 +2,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{repub}
-  s.version = "0.3.3"
+  s.version = "0.3.4"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Dmitri Goutnik"]
-  s.date = %q{2009-07-05}
+  s.date = %q{2009-07-17}
   s.default_executable = %q{repub}
   s.description = %q{Repub is a simple HTML to ePub converter.
 
@@ -16,14 +16,14 @@ ePub documents.}
   s.email = %q{dg@invisiblellama.net}
   s.executables = ["repub"]
   s.extra_rdoc_files = ["History.txt", "README.rdoc", "bin/repub"]
-  s.files = ["History.txt", "README.rdoc", "Rakefile", "TODO", "bin/repub", "lib/repub.rb", "lib/repub/app.rb", "lib/repub/app/builder.rb", "lib/repub/app/fetcher.rb", "lib/repub/app/logger.rb", "lib/repub/app/options.rb", "lib/repub/app/parser.rb", "lib/repub/app/profile.rb", "lib/repub/app/utility.rb", "lib/repub/epub.rb", "lib/repub/epub/container.rb", "lib/repub/epub/content.rb", "lib/repub/epub/toc.rb", "repub.gemspec", "test/data/custom.css", "test/data/invisiblellama.png", "test/data/test.css", "test/data/test.html", "test/epub/test_container.rb", "test/epub/test_content.rb", "test/epub/test_toc.rb", "test/test_builder.rb", "test/test_fetcher.rb", "test/test_logger.rb", "test/test_parser.rb"]
+  s.files = ["History.txt", "README.rdoc", "Rakefile", "TODO", "bin/repub", "lib/repub.rb", "lib/repub/app.rb", "lib/repub/app/builder.rb", "lib/repub/app/fetcher.rb", "lib/repub/app/filter.rb", "lib/repub/app/logger.rb", "lib/repub/app/options.rb", "lib/repub/app/parser.rb", "lib/repub/app/post_filters.rb", "lib/repub/app/pre_filters.rb", "lib/repub/app/profile.rb", "lib/repub/app/utility.rb", "lib/repub/epub.rb", "lib/repub/epub/container_item.rb", "lib/repub/epub/ncx.rb", "lib/repub/epub/ocf.rb", "lib/repub/epub/opf.rb", "repub.gemspec", "test/data/custom.css", "test/data/invisiblellama.png", "test/data/test.css", "test/data/test.html", "test/epub/test_ncx.rb", "test/epub/test_ocf.rb", "test/epub/test_opf.rb", "test/test_builder.rb", "test/test_fetcher.rb", "test/test_filter.rb", "test/test_logger.rb", "test/test_parser.rb"]
   s.homepage = %q{http://rubyforge.org/projects/repub/}
   s.rdoc_options = ["--main", "README.rdoc"]
   s.require_paths = ["lib"]
   s.rubyforge_project = %q{repub}
   s.rubygems_version = %q{1.3.4}
   s.summary = %q{Repub is a simple HTML to ePub converter}
-  s.test_files = ["test/epub/test_container.rb", "test/epub/test_content.rb", "test/epub/test_toc.rb", "test/test_builder.rb", "test/test_fetcher.rb", "test/test_logger.rb", "test/test_parser.rb"]
+  s.test_files = ["test/epub/test_ncx.rb", "test/epub/test_ocf.rb", "test/epub/test_opf.rb", "test/test_builder.rb", "test/test_fetcher.rb", "test/test_filter.rb", "test/test_logger.rb", "test/test_parser.rb"]
 
   if s.respond_to? :specification_version then
     current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION

data/test/epub/{test_toc.rb → test_ncx.rb}

@@ -5,10 +5,11 @@ require 'repub/epub'
 
 class TestToc < Test::Unit::TestCase
   def test_toc_create
-    x = Repub::Epub::Toc.new('some-name')
-    s = x.to_xml
+    ncx = Repub::Epub::NCX.new('some-ncx')
+    s = ncx.to_xml
+    #p s
     doc = Nokogiri::XML.parse(s)
-    assert_equal('some-name', doc.at("//xmlns:meta[@name='dtb:uid']")['content'])
+    assert_equal('some-ncx', doc.at("//xmlns:meta[@name='dtb:uid']")['content'])
     assert_equal('1', doc.at("//xmlns:meta[@name='dtb:depth']")['content'])
     assert_equal('0', doc.at("//xmlns:meta[@name='dtb:totalPageCount']")['content'])
     assert_equal('0', doc.at("//xmlns:meta[@name='dtb:maxPageNumber']")['content'])
@@ -17,15 +18,16 @@ class TestToc < Test::Unit::TestCase
   end
   
   def test_nav_map
-    x = Repub::Epub::Toc.new('some-name')
-    p0 = x.nav_map.add_nav_point('Intro', 'intro.html')
-    p1 = x.nav_map.add_nav_point('Chapter 1', 'chapter-1.html')
-    p2 = x.nav_map.add_nav_point('Chapter 2', 'chapter-2.html')
-    p21 = p2.add_nav_point('Chapter 2-1', 'chapter-2-1.html')
-    pg = x.nav_map.add_nav_point('Glossary', 'glossary.html')
-    p11 = p1.add_nav_point('Chapter 1-1', 'chapter-1-1.html')
-    p12 = p1.add_nav_point('Chapter 1-2', 'chapter-1-2.html')
-    s = x.to_xml
+    ncx = Repub::Epub::NCX.new('some-ncx')
+    ncx.nav_map.points << Repub::Epub::NCX::NavPoint.new('Intro', 'intro.html')
+    ncx.nav_map.points << Repub::Epub::NCX::NavPoint.new('Chapter 1', 'chapter-1.html')
+    ncx.nav_map.points << Repub::Epub::NCX::NavPoint.new('Chapter 2', 'chapter-2.html')
+    ncx.nav_map.points[2].points << Repub::Epub::NCX::NavPoint.new('Chapter 2-1', 'chapter-2-1.html')
+    ncx.nav_map.points << Repub::Epub::NCX::NavPoint.new('Glossary', 'glossary.html')
+    ncx.nav_map.points[1].points << Repub::Epub::NCX::NavPoint.new('Chapter 1-1', 'chapter-1-1.html')
+    ncx.nav_map.points[1].points << Repub::Epub::NCX::NavPoint.new('Chapter 1-2', 'chapter-1-2.html')
+    s = ncx.to_xml
+    #p s
     doc = Nokogiri::XML.parse(s)
     assert_equal(4, doc.xpath('//xmlns:navMap/xmlns:navPoint').size)
     assert_equal('2', doc.at("//xmlns:meta[@name='dtb:depth']")['content'])

data/test/epub/test_ocf.rb

@@ -0,0 +1,28 @@
+require 'test/unit'
+require 'rubygems'
+require 'nokogiri'
+require 'repub/epub'
+
+class TestContainer < Test::Unit::TestCase
+  def test_container_create
+    container = Repub::Epub::OCF.new
+    container << 'test.html'
+    container << Repub::Epub::OPF.new('12345')
+    s = container.to_xml
+    #p s
+    doc = Nokogiri::XML.parse(s)
+    assert_not_nil(doc.at('rootfile'))
+    assert_equal('test.html', doc.at('rootfile[1]')['full-path'])
+    assert_equal('application/xhtml+xml', doc.at('rootfile[1]')['media-type'])
+    assert_equal('package.opf', doc.at('rootfile[2]')['full-path'])
+    assert_equal('application/oebps-package+xml', doc.at('rootfile[2]')['media-type'])
+  end
+  
+  def test_container_create_fail
+    assert_raise(RuntimeError) do
+      # unknown mime type
+      container = Repub::Epub::OCF.new
+      container << 'blah.blah'
+    end
+  end
+end

data/test/epub/{test_content.rb → test_opf.rb}

@@ -5,44 +5,46 @@ require 'repub/epub'
 
 class TestContent < Test::Unit::TestCase
   def test_create
-    x = Repub::Epub::Content.new('some-name')
-    s = x.to_xml
+    opf = Repub::Epub::OPF.new('some-opf')
+    s = opf.to_xml
     doc = Nokogiri::XML.parse(s)
     #p doc
 
     metadata = doc.at('metadata')
     assert_not_nil(metadata)
-    assert_equal('some-name', metadata.xpath('dc:identifier', 'xmlns:dc' => "http://purl.org/dc/elements/1.1/").inner_text)
+    assert_equal('some-opf', metadata.xpath('dc:identifier', 'xmlns:dc' => "http://purl.org/dc/elements/1.1/").inner_text)
     assert_equal('Untitled', metadata.xpath('dc:title', 'xmlns:dc' => "http://purl.org/dc/elements/1.1/").inner_text)
     assert_equal('en', metadata.xpath('dc:language', 'xmlns:dc' => "http://purl.org/dc/elements/1.1/").inner_text)
     assert_equal(Date.today.to_s, metadata.xpath('dc:date', 'xmlns:dc' => "http://purl.org/dc/elements/1.1/").inner_text)
   end
 
   def test_manifest_create
-    x = Repub::Epub::Content.new('some-name')
-    s = x.to_xml
+    opf = Repub::Epub::OPF.new('some-opf')
+    opf << Repub::Epub::NCX.new('some-ncx')
+    s = opf.to_xml
     doc = Nokogiri::XML.parse(s)
     #p doc
   
     manifest = doc.at('manifest')
     assert_not_nil(manifest)
     assert_equal(1, manifest.children.size)
-    assert_equal('ncx', manifest.at('item')['id'])
+    assert_equal('ncx', manifest.at('item[@href="toc.ncx"]')['id'])
     assert_not_nil(doc.at('spine'))
     assert_equal(0, doc.xpath('spine/item').size)
   end
 
-  def test_manifest_items
-    x = Repub::Epub::Content.new('some-name')
-    x.add_item 'style.css'
-    x.add_item 'more-style.css'
-    x.add_item ' logo.jpg '
-    x.add_item ' image.png'
-    x.add_item 'picture.jpeg     '
-    x.add_item 'intro.html', 'intro'
-    x.add_item 'chapter-1.html'
-    x.add_item 'glossary.html', 'glossary'
-    s = x.to_xml
+  def test_manifest_and_spine_items
+    opf = Repub::Epub::OPF.new('some-opf')
+    opf << 'style.css'
+    opf << 'more-style.css'
+    opf << ' logo.jpg '
+    opf << 'intro.html'
+    opf << ' image.png'
+    opf << 'picture.jpeg     '
+    opf << Repub::Epub::NCX.new('some-ncx')
+    opf << 'chapter-1.html'
+    opf << 'glossary.html'
+    s = opf.to_xml
     doc = Nokogiri::HTML(s)
     #p doc
   
@@ -51,10 +53,14 @@ class TestContent < Test::Unit::TestCase
     assert_equal(2, manifest.xpath('item[@media-type="text/css"]').size)
     assert_equal(2, manifest.search('item[@media-type="image/jpeg"]').size)
     assert_equal(1, manifest.search('item[@media-type="image/png"]').size)
+    # NCX is first and always has id = 'ncx'
+    assert_equal('ncx', manifest.at('./item[position()=1]')['id'])
     
     spine = doc.at('spine')
+    # attribute toc has and id of NCX manifest item
+    assert_equal('ncx', spine['toc'])
     assert_equal(3, spine.search('itemref').size)
-    assert_equal('intro', spine.at('./itemref[position()=1]')['idref'])
-    assert_equal('glossary', spine.at('./itemref[position()=3]')['idref'])
+    assert_equal('item-4', spine.at('./itemref[position()=1]')['idref'])
+    assert_equal('item-8', spine.at('./itemref[position()=3]')['idref'])
   end
 end

data/test/test_filter.rb

@@ -0,0 +1,28 @@
+require "test/unit"
+
+require 'repub'
+require 'repub/app'
+
+class TestFilter < Test::Unit::TestCase
+  include Repub::App::Filter
+  
+  filter :filter_1 do |s|
+    log.info 'in filter_1'
+    s.upcase
+  end
+  
+  filter :filter_2 do |s|
+    log.info 'in filter_2'
+    "++ #{s} --"
+  end
+  
+  filter :filter_3 do |s|
+    log.info 'in filter_3'
+    s.gsub(/\s/, '|')
+  end
+  
+  def test_case_name
+    res = TestFilter.apply_filters('klaatu barada nikto')
+    assert_equal('++|KLAATU|BARADA|NIKTO|--', res)
+  end
+end

data/test/test_parser.rb

@@ -36,10 +36,9 @@ class TestParser < Test::Unit::TestCase
     assert_equal(3, parser.toc.size)
     assert_equal('Chapter 1', parser.toc[0].title)
     assert_equal('Chapter 3', parser.toc[2].title)
-    assert_equal(2, parser.toc[0].subitems.size)
-    assert_equal('Chapter 1.2', parser.toc[0].subitems[1].title)
-    assert_equal(cache.assets[:documents][0], parser.toc[0].subitems[1].uri)
-    assert_equal('c12', parser.toc[0].subitems[1].fragment_id)
+    assert_equal(2, parser.toc[0].points.size)
+    assert_equal('Chapter 1.2', parser.toc[0].points[1].title)
+    assert_equal("#{cache.assets[:documents][0]}#c12", parser.toc[0].points[1].src)
   end
 
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: repub
 version: !ruby/object:Gem::Version 
-  version: 0.3.3
+  version: 0.3.4
 platform: ruby
 authors: 
 - Dmitri Goutnik
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-07-05 00:00:00 +04:00
+date: 2009-07-17 00:00:00 +04:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -87,15 +87,19 @@ files:
 - lib/repub/app.rb
 - lib/repub/app/builder.rb
 - lib/repub/app/fetcher.rb
+- lib/repub/app/filter.rb
 - lib/repub/app/logger.rb
 - lib/repub/app/options.rb
 - lib/repub/app/parser.rb
+- lib/repub/app/post_filters.rb
+- lib/repub/app/pre_filters.rb
 - lib/repub/app/profile.rb
 - lib/repub/app/utility.rb
 - lib/repub/epub.rb
-- lib/repub/epub/container.rb
-- lib/repub/epub/content.rb
-- lib/repub/epub/toc.rb
+- lib/repub/epub/container_item.rb
+- lib/repub/epub/ncx.rb
+- lib/repub/epub/ocf.rb
+- lib/repub/epub/opf.rb
 - repub.gemspec
 - tasks/ann.rake
 - tasks/bones.rake
@@ -114,11 +118,12 @@ files:
 - test/data/invisiblellama.png
 - test/data/test.css
 - test/data/test.html
-- test/epub/test_container.rb
-- test/epub/test_content.rb
-- test/epub/test_toc.rb
+- test/epub/test_ncx.rb
+- test/epub/test_ocf.rb
+- test/epub/test_opf.rb
 - test/test_builder.rb
 - test/test_fetcher.rb
+- test/test_filter.rb
 - test/test_logger.rb
 - test/test_parser.rb
 has_rdoc: true
@@ -151,10 +156,11 @@ signing_key:
 specification_version: 3
 summary: Repub is a simple HTML to ePub converter
 test_files: 
-- test/epub/test_container.rb
-- test/epub/test_content.rb
-- test/epub/test_toc.rb
+- test/epub/test_ncx.rb
+- test/epub/test_ocf.rb
+- test/epub/test_opf.rb
 - test/test_builder.rb
 - test/test_fetcher.rb
+- test/test_filter.rb
 - test/test_logger.rb
 - test/test_parser.rb

data/lib/repub/epub/container.rb

@@ -1,28 +0,0 @@
-require 'rubygems'
-require 'builder'
-
-module Repub
-  module Epub
-  
-  class Container
-    def to_xml
-      out = ''
-      builder = Builder::XmlMarkup.new(:target => out)
-      builder.instruct!
-      builder.container :xmlns => "urn:oasis:names:tc:opendocument:xmlns:container", :version => "1.0" do
-        builder.rootfiles do
-          builder.rootfile 'full-path' => "content.opf", 'media-type' => "application/oebps-package+xml"
-        end
-      end
-      out
-    end
-  
-    def save(path = 'container.xml')
-      File.open(path, 'w') do |f|
-        f << to_xml
-      end
-    end
-  end
-
-  end
-end