epub-parser 0.2.5 → 0.2.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: ccf4841189745cdaa96e82b64a3493e4a3dc2421
-  data.tar.gz: e2c83bc88d36a63957b313136372568506377ae3
+  metadata.gz: 7b9ee0e48ab95b16264f66048d2f0d040f63ab2d
+  data.tar.gz: b16bd608fc1c7c54de24a30c13ad880cd9f096de
 SHA512:
-  metadata.gz: e635c138b09d454c17fd8f93b59b04403e828c73a4a0be14dc7d133501bc219a6d41a7d1108091b4bc845276ab33e7905d5ba7caed9403904cb6a71058c59dcf
-  data.tar.gz: 12fe31458bfcfd89e8dd6fee555473f02370c613893ee681b2a7d9b6d2db70640bdb1403140300057016c4595976d678509ab812de070e25b63b8e6dac17ee70
+  metadata.gz: 6df7c1519d379afe93635e085ae7c3d9548ac9005a7e6cb79066db2310deca63ac8d0089100516a3657e6a16f092c3472897e5b10c227dd60b0c5db5e028f570
+  data.tar.gz: 80f34c61d4043beba1ca680db124744a1c619c126e19b097d2b1ba4ac0cb0439efdb99ebd9c183119f8d5a210bfde7408f234b4bf25678a36b4401cf842f37a6

data/.travis.yml

@@ -1,4 +1,4 @@
 rvm:
-  - "2.1.8"
-  - "2.2.4"
-  - "2.3.0"
+  - "2.1.10"
+  - "2.2.5"
+  - "2.3.1"

data/.yardopts

@@ -12,3 +12,5 @@ docs/Searcher.markdown
 docs/UnpackedArchive.markdown
 docs/AggregateContentsFromWeb.markdown
 examples/aggregate-contents-from-web.rb
+examples/exctract-content-using-cfi.rb
+examples/find-elements-and-cfis.rb

data/CHANGELOG.markdown

@@ -1,12 +1,25 @@
 CHANGELOG
 =========
 
+0.2.6
+-----
+
+* Add `EPUB::Publication::Package::Metadata#package_identifier` as alias of `#release_identifier`, which is defined in EPUB Publication 3.0 spec
+* [BUG FIX]Metadata#modified returns modified with no refiners
+* Make second argument for `EPUB::Parser::Publication.new` deprecated
+* Add META-INF/metadata.xml support defined in [EPUB Multiple-Rendition Publications 1.0][multi-rendition]
+* Add `EPUB::Book::Features#packages` and `#default_rendition`
+* [BUG FIX]Don't raise error when using `Zipruby` container adapter
+
+[multi-rendition]: http://www.idpf.org/epub/renditions/multiple/
+
 0.2.5
 -----
 
-* [BUG FIX]RaiseDon't load Zip/Ruby if unneccessary
+* [BUG FIX]Don't load Zip/Ruby if unneccessary
 * Raise error when PhysicalContainer::ArchiveZip fails find entry
 * Remove unused files in schemas directory
+* Add `EPUB::CFI::PhysicalContainer.find_adapter`
 
 0.2.4
 -----

data/README.markdown

@@ -135,7 +135,7 @@ REQUIREMENTS
 ------------
 * Ruby 2.1.0 or later
 * `patch` command to install Nokogiri
-* C compiler to compile Zip/Ruby and Nokogiri
+* C compiler to compile Nokogiri
 
 Related Gems
 ------------
@@ -151,9 +151,21 @@ If you find other gems, please tell me or request a pull request.
 RECENT CHANGES
 --------------
 
+### 0.2.6
+
+* Add `EPUB::Publication::Package::Metadata#package_identifier` as alias of `#release_identifier`
+* [BUG FIX]Metadata#modified returns modified with no refiners
+* Make second argument for `EPUB::Parser::Publication.new` deprecated
+* Add META-INF/metadata.xml support defined in [EPUB Multiple-Rendition Publications 1.0][multi-rendition]
+* Add `EPUB::Book::Features#packages` and `#default_rendition`
+* [BUG FIX]Don't raise error when using `Zipruby` container adapter
+
+[multi-rendition]: http://www.idpf.org/epub/renditions/multiple/
+
 ### 0.2.5
 
-* [BUG FIX]RaiseDon't load Zip/Ruby if unneccessary
+* [BUG FIX]Don't load Zip/Ruby if unneccessary
+* Add `EPUB::CFI::PhysicalContainer.find_adapter`
 
 ### 0.2.4
 
@@ -163,38 +175,11 @@ RECENT CHANGES
 * Change attribute name: `EPUB::CFI::Step#step` -> `EPUB::CFI::Step#value`, `EPUB::CFI::CharacterOffset#offset` -> `EPUB::CFI::CharacterOffset#value`
 * Show modified on `epubinfo` command
 
-### 0.2.3
-
-* Change the name of physical container adapter for file system: :File -> :UnpackedDirectory
-* Add `EPUB::Publication::Package::Manifest::Item#full_path`
-* Make #href= acceptable String
-* Implement `EPUB::CFI` and `EPUB::Parser::CFI`
-* Remove [nokogumbo][] from dependencies. It ommits `head` and `body` elements
-* Remove Cucumber and Cucumber features
-* Add `EPUB::Publication::Package::Metadata#modified` and `EPUB::Book::Features#modified`
-* Add `EPUB::Book::Features#release_identifier`
-
-[nokogumbo]: https://github.com/rubys/nokogumbo/
-
-### 0.2.2
-
-* [BUGFIX]Item#entry_name returns normalized IRI
-
-### 0.2.1
-
-* Remove deprecated `EPUB::Constants::MediaType::UnsupportedError`. Use `UnsupportedMediatType` instead.
-* Make it possible to use [archive-zip][] gem to extract contents from EPUB package
-* Add warning about default physical container adapter change
-* Make it possible to extract contents from the web via `EPUB::OCF::PhysicalContainer::UnpackedURI` See {file:ExtractContentsFromWeb.markdown} for details.
-
-[archive-zip]: https://github.com/javanthropus/archive-zip
-
 See {file:CHANGELOG.markdown} for older changelogs and details.
 
 TODOS
 -----
 * EPUB 3.0.1
-* Multiple rootfiles
 * Help features for `epub-open` tool
 * Vocabulary Association Mechanisms
 * Implementing navigation document and so on
@@ -215,6 +200,7 @@ DONE
 * Vocabulary Association Mechanisms(only for itemref)
 * Archive library abstraction
 * Extracting and organizing common behavior from some classes to modules
+* Multiple rootfiles
 
 LICENSE
 -------

data/Rakefile

@@ -1,6 +1,6 @@
-require 'bundler/gem_helper'
 require 'rake/clean'
 require 'rake/testtask'
+require 'rubygems/tasks'
 require 'yard'
 require 'rdoc/task'
 require 'epub/parser/version'
@@ -54,7 +54,42 @@ namespace :doc do
   end
 end
 
-namespace :gem do
-  Bundler::GemHelper.install_tasks
-  task :build => [:clean, CFI_TAB]
+Gem::Tasks.new do |tasks|
+  tasks.console.command = 'pry'
+end
+task :build => [:clean, CFI_TAB]
+
+class ForwardableDefDelegatorsHandler < YARD::Handlers::Ruby::Base
+  handles method_call(:def_delegators)
+  namespace_only
+
+  def process
+    params = validated_attribute_names(statement.parameters(false))
+    accessor = params.shift
+    params.each do |param|
+      object = YARD::CodeObjects::MethodObject.new(namespace, param)
+      object.docstring = "Forwarded to +#{accessor}+"
+    end
+  end
+
+  protected
+
+  # Strips out any non-essential arguments from the attr statement.
+  #
+  # @param [Array<Parser::Ruby::AstNode>] params a list of the parameters
+  #   in the attr call.
+  # @return [Array<String>] the validated attribute names
+  # @raise [Parser::UndocumentableError] if the arguments are not valid.
+  def validated_attribute_names(params)
+    params.map do |obj|
+      case obj.type
+      when :symbol_literal
+        obj.jump(:ident, :op, :kw, :const).source
+      when :string_literal
+        obj.jump(:string_content).source
+      else
+        raise YARD::Parser::UndocumentableError, obj.source
+      end
+    end
+  end
 end

data/docs/FixedLayout.markdown

@@ -15,7 +15,7 @@ Methods for {EPUB::Publication::Package}
 
 It is `true` when `package@prefix` attribute has `rendition` property.
 
-    parser = EPUB::Parser::Publication.new(<<OPF, 'dummy/rootfile.opf')
+    parser = EPUB::Parser::Publication.new(<<OPF)
     <package version="3.0"
              unique-identifier="pub-id"
              xmlns="http://www.idpf.org/2007/opf"

data/docs/Item.markdown

@@ -4,7 +4,7 @@ Overview
 ========
 
 When manipulating resources (XHTML, images, audio...) in EPUB, {EPUB::Publication::Package::Manifest::Item} object will be used.
-And objects which {EPUB#each_page_on_spine} yields are also instances of this class.
+And objects which {EPUB::Book::Features#each_page_on_spine} yields are also instances of this class.
 
 Here's the tutorial of this class.
 

data/epub-parser.gemspec

@@ -27,6 +27,7 @@ Gem::Specification.new do |s|
   s.has_rdoc = 'yard'
 
   s.add_development_dependency 'rake'
+  s.add_development_dependency 'rubygems-tasks'
   s.add_development_dependency 'zipruby'
   s.add_development_dependency 'pry'
   s.add_development_dependency 'pry-doc'
@@ -40,6 +41,7 @@ Gem::Specification.new do |s|
   s.add_development_dependency 'epzip'
   s.add_development_dependency 'racc'
   s.add_development_dependency 'nokogiri-diff'
+  s.add_development_dependency 'pretty_backtrace'
 
   s.add_runtime_dependency 'archive-zip'
   s.add_runtime_dependency 'nokogiri', '~> 1.6'

data/examples/exctract-content-using-cfi.rb

@@ -0,0 +1,111 @@
+# coding: utf-8
+# Preparation
+#
+#   % cd examples
+#   % wget -O accessible-epub3.epub 'https://drive.google.com/uc?export=download&id=0B9g8D2Y-6aPLRmFKRTNIam93RTQ'
+#
+# Execution
+#
+#   % ruby exctract-content-using-cfi.rb accessible-epub3.epub '/6/10!/4/2/4'
+#   <p>Accessibility is a difficult concept to define. There’s no single magic bullet
+#   				solution that will make all content accessible to all people. Perhaps that’s a
+#   				strange way to preface a book on accessible practices, but it’s also a reality you
+#   				need to be aware of. Accessible practices change, technologies evolve to solve
+#   				stubborn problems, and the world becomes a more accessible place all the time.</p>
+#
+#   % ruby exctract-content-using-cfi.rb accessible-epub3.epub '/6/10!/4/2,/4,/8'
+#   <p>Accessibility is a difficult concept to define. There’s no single magic bullet
+#   				solution that will make all content accessible to all people. Perhaps that’s a
+#   				strange way to preface a book on accessible practices, but it’s also a reality you
+#   				need to be aware of. Accessible practices change, technologies evolve to solve
+#   				stubborn problems, and the world becomes a more accessible place all the time.</p>
+#   				                                                                         <p xmlns="http://www.w3.org/1999/xhtml">But although there are best practices that everyone should be following, and that
+#   				will be detailed as we go along, this guide should neither be read as an instrument
+#   				for accessibility compliance nor as a replacement for existing guidelines.</p>
+#   				<p></p>
+#
+# Yes, output above shows a bug!
+#
+#   % ruby exctract-content-using-cfi.rb accessible-epub3.epub '/6/10!/4/2/4,:0,:47'
+#   Accessibility is a difficult concept to define.
+
+require 'epub/parser'
+require 'epub/parser/cfi'
+require 'nokogiri' # Do gem install nokogiri
+require 'nokogiri/xml/range' # Do gem install nokogiri-xml-range
+
+def main(argv)
+  epub_path = argv.shift
+  cfi_string = argv.shift
+  if epub_path.nil? or cfi_string.nil?
+    $stderr.puts "USAGE: ruby #{$0} EPUB CFI"
+    abort
+  end
+
+  epub = EPUB::Parser.parse(epub_path)
+  cfi = EPUB::CFI(cfi_string)
+
+  content = extract_content(epub, cfi)
+  case content
+  when Nokogiri::XML::Element
+    puts content
+  when Nokogiri::XML::Range
+    puts content.clone_contents
+  end
+end
+
+def extract_content(epub, cfi)
+  if cfi.kind_of? EPUB::CFI::Location
+    node = get_element(cfi, epub)
+    offset = cfi.paths.last.offset
+    offset = offset.value if offset
+    # Maybe offset may not be used
+    return node
+  end
+
+  start_node = get_element(cfi.first, epub)
+  # Need more consideration
+  start_node = start_node.children.first if start_node.element?
+
+  end_node = get_element(cfi.last, epub)
+  # Need more consideration
+  end_node = end_node.children.last if end_node.element?
+
+  start_offset = cfi.first.paths.last.offset
+  start_offset = start_offset ? start_offset.value : 0
+  end_offset = cfi.last.paths.last.offset
+  end_offset = end_offset ? end_offset.value : 0
+
+  range = Nokogiri::XML::Range.new(start_node, start_offset, end_node, end_offset)
+
+  return range
+end
+
+def get_element(cfi, epub)
+  path_in_package = cfi.paths.first
+  step_to_itemref = path_in_package.steps[1]
+  itemref = epub.spine.itemrefs[step_to_itemref.step / 2 - 1]
+
+  doc = itemref.item.content_document.nokogiri
+  path_in_doc = cfi.paths[1]
+  current_node = doc.root
+  path_in_doc.steps.each do |step|
+    if step.element?
+      current_node = current_node.element_children[step.value / 2 - 1]
+    else
+      element_index = (step.value - 1) / 2 - 1
+      if element_index == -1
+        current_node = current_node.children.first
+      else
+        prev = current_node.element_children[element_index]
+        break unless prev
+        current_node = prev.next_sibling
+        break unless current_node
+      end
+    end
+  end
+
+  current_node
+end
+
+main(ARGV)

data/examples/find-elements-and-cfis.rb

@@ -0,0 +1,54 @@
+require 'English'
+require 'epub/parser'
+require 'epub/parser/cfi'
+require 'nokogiri'
+
+def usage
+  <<EOS
+
+USAGE:
+ ruby #{$PROGRAM_NAME} ELEMENT EPUB
+
+EOS
+end
+
+def main(argv)
+  elem_name = argv.shift
+  epub_path = argv.shift
+  if elem_name.nil? or epub_path.nil?
+    abort usage
+  end
+
+  spine_step = EPUB::CFI::Step.new(6)
+
+  epub = EPUB::Parser.parse(epub_path)
+  epub.package.spine.each_itemref.with_index do |itemref, i|
+    itemref_step = {
+      :step => (i + 1) * 2,
+      :id => itemref.id
+    }
+    assertion = itemref.id ? EPUB::CFI::IDAssertion.new(itemref.id) : nil
+    itemref_step = EPUB::CFI::Step.new((i + 1) * 2, assertion)
+    path_to_itemref = EPUB::CFI::Path.new([spine_step, itemref_step])
+    itemref.item.content_document.nokogiri.search(elem_name).each do |elem|
+      path = find_path(elem)
+      location = EPUB::CFI::Location.new([path_to_itemref, path])
+      puts
+      puts location
+      puts elem
+    end
+  end
+end
+
+def find_path(elem)
+  steps = []
+  until elem.parent.document?
+    index = elem.parent.element_children.index(elem)
+    assertion = elem["id"] ? EPUB::CFI::IDAssertion.new(elem["id"]) : nil
+    steps.unshift EPUB::CFI::Step.new((index + 1) * 2, assertion)
+    elem = elem.parent
+  end
+  EPUB::CFI::Path.new(steps)
+end
+
+main ARGV

data/lib/epub/book/features.rb

@@ -1,45 +1,57 @@
+require 'forwardable'
+
 module EPUB
   class Book
     module Features
-      modules = [:ocf, :package]
-      attr_reader *modules
+      extend Forwardable
+      attr_reader :ocf
+      attr_writer :package
       attr_accessor :epub_file
-      modules.each do |mod|
-        define_method "#{mod}=" do |obj|
-          instance_variable_set "@#{mod}", obj
-          obj.book = self
-        end
+
+      # When writing, sets +ocf.book+ to self.
+      # @param [OCF]
+      def ocf=(mod)
+        @ocf = mod
+        mod.book = self
+        mod
       end
 
-      Publication::Package::CONTENT_MODELS.each do |model|
-        define_method model do
-          package.__send__(model)
-        end
+      # @return [Array<OCF::Container::Rootfile>]
+      def rootfiles
+        ocf.container.rootfiles
       end
 
-      %w[title main_title subtitle short_title collection_title edition_title extended_title description date unique_identifier modified].each do |met|
-        define_method met do
-          metadata.__send__(met)
-        end
+      # @return [Array<Publication::Package>]
+      def packages
+        rootfiles.map(&:package)
       end
+      alias renditions packages
 
-      %w[nav].each do |met|
-        define_method met do
-          manifest.__send__(met)
-        end
+      # Syntax sugar.
+      # Returns package set by +package=+.
+      # Returns default rendition if any package has not been set ever.
+      # @return [Publication::Package]
+      def package
+        @package || default_rendition
       end
 
-      def release_identifier
-        "#{unique_identifier}@#{modified}"
+      # First +package+ in +packages+
+      # @return [Package|nil]
+      def default_rendition
+        packages.first
       end
 
+      # @!parse def_delegators :package, :metadata, :manifest, :spine, :guide, :bindings
+      def_delegators :package, *Publication::Package::CONTENT_MODELS
+      def_delegators :metadata, :title, :main_title, :subtitle, :short_title, :collection_title, :edition_title, :extended_title, :description, :date, :unique_identifier, :modified, :release_identifier, :package_identifier
+      def_delegators :manifest, :nav, :cover_image
+
       def container_adapter
         @adapter || OCF::PhysicalContainer.adapter
       end
 
       def container_adapter=(adapter)
-        @adapter = adapter.instance_of?(Class) ? adapter : OCF::PhysicalContainer.const_get(adapter)
-        adapter
+        @adapter = OCF::PhysicalContainer.find_adapter(adapter)
       end
 
       # @overload each_page_on_spine(&blk)
@@ -84,15 +96,10 @@ module EPUB
       end
 
       # Syntax sugar
+      # @return String
       def rootfile_path
         ocf.container.rootfile.full_path.to_s
       end
-
-      # Syntax sugar
-      def cover_image
-        manifest.cover_image
-      end
-
     end
   end
 end