epub-parser 0.3.6 → 0.3.7

data/epub-parser.gemspec

@@ -7,7 +7,7 @@ Gem::Specification.new do |s|
   s.version     = EPUB::Parser::VERSION
   s.authors     = ["KITAITI Makoto"]
   s.email       = ["KitaitiMakoto@gmail.com"]
-  s.homepage    = "http://www.rubydoc.info/gems/epub-parser/file/docs/Home.markdown"
+  s.homepage    = "https://kitaitimakoto.gitlab.io/epub-parser/file.Home.html"
   s.summary     = %q{EPUB 3 Parser}
   s.description = %q{Parse EPUB 3 book loosely}
   s.license     = 'MIT'
@@ -38,6 +38,7 @@ Gem::Specification.new do |s|
   s.add_development_dependency 'ronn'
   s.add_development_dependency 'pretty_backtrace'
   s.add_development_dependency 'epub-maker'
+  s.add_development_dependency 'asciidoctor'
 
   s.add_runtime_dependency 'archive-zip'
   s.add_runtime_dependency 'nokogiri', '>= 1.6.0', '< 1.9'

data/lib/epub/book/features.rb

@@ -36,7 +36,7 @@ module EPUB
       # @!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_delegators :manifest, :nav
 
       def container_adapter
         @adapter || OCF::PhysicalContainer.adapter
@@ -46,6 +46,12 @@ module EPUB
         @adapter = OCF::PhysicalContainer.find_adapter(adapter)
       end
 
+      # Cover image defined in EPUB 3 or used in EPUB 2
+      # @return [EPUB::Publication::Package::Manifest::Item]
+      def cover_image
+        manifest.cover_image || metadata.cover_image
+      end
+
       # @overload each_page_on_spine(&blk)
       #   iterate over items in order of spine when block given
       #   @yieldparam item [Publication::Package::Manifest::Item]

data/lib/epub/metadata.rb

@@ -65,6 +65,14 @@ module EPUB
       }
     end
 
+    # Cover image used in EPUB 2
+    # @return [EPUB::Publication::Package::Manifest::Item]
+    def cover_image
+      cover_image_meta = metas.find {|meta| meta.name == "cover"}
+      return unless cover_image_meta
+      package.manifest[cover_image_meta.meta_content]
+    end
+
     def to_h
       DC_ELEMS.inject({}) do |hsh, elem|
         hsh[elem] = __send__(elem)
@@ -137,7 +145,7 @@ module EPUB
     class Meta
       include Refinee
 
-      attr_accessor :property, :id, :scheme, :content
+      attr_accessor :property, :id, :scheme, :content, :name, :meta_content
       attr_reader :refines
 
       def refines=(refinee)

data/lib/epub/parser/metadata.rb

@@ -38,7 +38,7 @@ module EPUB
             when default_namespace_uri
               case elem_name
               when 'meta'
-                meta = build_model(child, :Meta, %w[property id scheme])
+                meta = build_model(child, :Meta, %w[property id scheme content name])
                 metadata.metas << meta
                 meta
               when 'link'
@@ -86,9 +86,11 @@ module EPUB
       def build_model(elem, klass=:DCMES, attributes=%w[id lang dir])
         model = EPUB::Metadata.const_get(klass).new
         attributes.each do |attr|
-          model.__send__ "#{attr.gsub('-', '_')}=", extract_attribute(elem, attr)
+          writer_name = (attr == "content") ? "meta_content=" : "#{attr.gsub('-', '_')}="
+          model.__send__ writer_name, extract_attribute(elem, attr)
         end
         model.content = elem.content unless klass == :Link
+        model.content.strip! if klass == :Identifier
         model
       end
 

data/lib/epub/parser/version.rb

@@ -1,5 +1,5 @@
 module EPUB
   class Parser
-    VERSION = "0.3.6"
+    VERSION = "0.3.7"
   end
 end

data/lib/epub/publication/package/manifest.rb

@@ -220,6 +220,7 @@ module EPUB
             raise ArgumentError, "Not relative: #{iri.inspect}" unless iri.relative?
             raise ArgumentError, "Start with slash: #{iri.inspect}" if iri.path.start_with? Addressable::URI::SLASH
             target_href = href + iri
+            target_href.fragment = nil
             segments = target_href.to_s.split(Addressable::URI::SLASH)
             clean_segments = []
             segments.each do |segment|
@@ -227,7 +228,6 @@ module EPUB
               segment == '..' ? clean_segments.pop : clean_segments << segment
             end
             target_iri = Addressable::URI.parse(clean_segments.join(Addressable::URI::SLASH))
-            target_iri.fragment = nil
             manifest.items.find { |item| item.href == target_iri}
           end
 

data/lib/epub/searcher/xhtml.rb

@@ -87,6 +87,7 @@ module EPUB
                 # TODO: Consider block level elements
                 content_length = content.length
                 sub_indices, sub_content = build_indices(child)
+                # TODO: Pass content_length and child_step to build_indices and remove this block
                 sub_indices.each_pair do |sub_pos, child_steps|
                   indices[content_length + sub_pos] = [child_step] + child_steps
                 end

data/test/helper.rb

@@ -1,7 +1,7 @@
 Encoding.default_external = 'UTF-8'
 require 'simplecov'
 SimpleCov.start do
-  add_filter '/test|deps/'
+  add_filter /test|deps/
 end
 
 require 'pp'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: epub-parser
 version: !ruby/object:Gem::Version
-  version: 0.3.6
+  version: 0.3.7
 platform: ruby
 authors:
 - KITAITI Makoto
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-03-10 00:00:00.000000000 Z
+date: 2018-05-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -206,6 +206,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: asciidoctor
+  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: archive-zip
   requirement: !ruby/object:Gem::Requirement
@@ -286,6 +300,7 @@ description: Parse EPUB 3 book loosely
 email:
 - KitaitiMakoto@gmail.com
 executables:
+- epub-cover
 - epub-open
 - epubinfo
 extensions: []
@@ -295,23 +310,26 @@ files:
 - ".gitignore"
 - ".gitlab-ci.yml"
 - ".yardopts"
-- CHANGELOG.markdown
+- CHANGELOG.adoc
 - Gemfile
 - MIT-LICENSE
-- README.markdown
+- README.adoc
 - Rakefile
+- bin/epub-cover
 - bin/epub-open
 - bin/epubinfo
 - docs/AggregateContentsFromWeb.markdown
+- docs/EpubCover.adoc
 - docs/EpubOpen.markdown
 - docs/Epubinfo.markdown
+- docs/Examples.adoc
 - docs/FixedLayout.markdown
-- docs/Home.markdown
+- docs/Home.adoc
 - docs/Item.markdown
 - docs/MultipleRenditions.markdown
 - docs/Navigation.markdown
 - docs/Publication.markdown
-- docs/Searcher.markdown
+- docs/Searcher.adoc
 - docs/UnpackedArchive.markdown
 - docs/yard-forwardable_def_delegators_handler.rb
 - epub-parser.gemspec
@@ -391,7 +409,7 @@ files:
 - test/test_parser_publication.rb
 - test/test_publication.rb
 - test/test_searcher.rb
-homepage: http://www.rubydoc.info/gems/epub-parser/file/docs/Home.markdown
+homepage: https://kitaitimakoto.gitlab.io/epub-parser/file.Home.html
 licenses:
 - MIT
 metadata: {}
@@ -411,7 +429,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.7.4
+rubygems_version: 2.7.6
 signing_key: 
 specification_version: 4
 summary: EPUB 3 Parser

data/README.markdown

@@ -1,219 +0,0 @@
-EPUB Parser
-===========
-[![build status](https://gitlab.com/KitaitiMakoto/epub-parser/badges/master/build.svg)](https://gitlab.com/KitaitiMakoto/epub-parser/commits/master)
-[![Dependency Status](https://gemnasium.com/KitaitiMakoto/epub-parser.png)](https://gemnasium.com/KitaitiMakoto/epub-parser)
-[![Gem Version](https://badge.fury.io/rb/epub-parser.svg)](http://badge.fury.io/rb/epub-parser)
-[![coverage report](https://gitlab.com/KitaitiMakoto/epub-parser/badges/master/coverage.svg)](https://gitlab.com/KitaitiMakoto/epub-parser/commits/master)
-
-* [Homepage][homepage]
-* [Documentation][rubydoc]
-* [Source Code][]
-
-[Source Code]: https://gitlab.com/KitaitiMakoto/epub-parser
-
-INSTALLATION
--------
-
-    gem install epub-parser
-
-USAGE
------
-
-### As a library
-
-    require 'epub/parser'
-    
-    book = EPUB::Parser.parse('book.epub')
-    book.metadata.titles # => Array of EPUB::Publication::Package::Metadata::Title. Main title, subtitle, etc...
-    book.metadata.title # => Title string including all titles
-    book.metadata.creators # => Creators(authors)
-    book.each_page_on_spine do |page|
-      page.media_type # => "application/xhtml+xml"
-      page.entry_name # => "OPS/nav.xhtml" entry name in EPUB package(zip archive)
-      page.read # => raw content document
-      page.content_document.nokogiri # => Nokogiri::XML::Document. The same to Nokogiri.XML(page.read)
-      # do something more
-      #    :
-    end
-
-See document's {file:docs/Home.markdown} or [API Documentation][rubydoc] for more info.
-
-[rubydoc]: http://www.rubydoc.info/gems/epub-parser
-
-### `epubinfo` command-line tool
-
-`epubinfo` tool extracts and shows the metadata of specified EPUB book.
-
-    $ epubinfo ~/Documebts/Books/build_awesome_command_line_applications_in_ruby.epub
-    Title:              Build Awesome Command-Line Applications in Ruby (for KITAITI MAKOTO)
-    Identifiers:        978-1-934356-91-3
-    Titles:             Build Awesome Command-Line Applications in Ruby (for KITAITI MAKOTO)
-    Languages:          en
-    Contributors:       
-    Coverages:          
-    Creators:           David Bryant Copeland
-    Dates:              
-    Descriptions:       
-    Formats:            
-    Publishers:         The Pragmatic Bookshelf, LLC (338304)
-    Relations:          
-    Rights:             Copyright © 2012 Pragmatic Programmers, LLC
-    Sources:            
-    Subjects:           Pragmatic Bookshelf
-    Types:              
-    Unique identifier:  978-1-934356-91-3
-    Epub version:       2.0
-
-See {file:docs/Epubinfo.markdown} for more info.
-
-### `epub-open` command-line tool
-
-`epub-open` tool provides interactive shell(IRB) which helps you research about EPUB book.
-
-    epub-open path/to/book.epub
-
-IRB starts. `self` becomes the EPUB book and can access to methods of `EPUB`.
-
-    title
-    => "Title of the book"
-    metadata.creators
-    => [Author 1, Author2, ...]
-    resources.first.properties
-    => #<Set: {"nav"}> # You know that first resource of this book is nav document
-    nav = resources.first
-    => ...
-    nav.href
-    => #<Addressable::URI:0x15ce350 URI:nav.xhtml>
-    nav.media_type
-    => "application/xhtml+xml"
-    puts nav.read
-    <?xml version="1.0"?>
-    <html xmlns="http://www.w3.org/1999/xhtml" xmlns:epub="http://www.idpf.org/2007/ops">
-        :
-        :
-        :
-    </html>
-    => nil
-    exit # Enter "exit" when exit the session
-
-See {file:docs/EpubOpen.markdown} for more info.
-
-DOCUMENTATION
--------------
-
-Documentation is available in [homepage][].
-
-If you installed EPUB Parser by gem command, you can also generate documentaiton yourself([rubygems-yardoc][] gem is needed):
-
-    $ gem install epub-parser
-    $ gem yardoc epub-parser
-    ...
-    Files:          33
-    Modules:        20 (   20 undocumented)
-    Classes:        45 (   44 undocumented)
-    Constants:      31 (   31 undocumented)
-    Methods:       292 (   88 undocumented)
-    52.84% documented
-    YARD documentation is generated to:
-    /path/to/gempath/ruby/2.2.0/doc/epub-parser-0.2.0/yardoc
-
-It will show you path to generated documentation(`/path/to/gempath/ruby/2.2.0/doc/epub-parser-0.2.0/yardoc` here) at the end.
-
-Or, generating by yardoc command is possible, too:
-
-    $ git clone https://gitlab.com/KitaitiMakoto/epub-parser.git
-    $ cd epub-parser
-    $ bundle install --path=deps
-    $ bundle exec rake doc:yard
-    ...
-    Files:          33
-    Modules:        20 (   20 undocumented)
-    Classes:        45 (   44 undocumented)
-    Constants:      31 (   31 undocumented)
-    Methods:       292 (   88 undocumented)
-    52.84% documented
-
-Then documentation will be available in `doc` directory.
-
-[homepage]: http://www.rubydoc.info/gems/epub-parser/file/docs/Home.markdown
-[rubygems-yardoc]: https://rubygems.org/gems/rubygems-yardoc
-
-REQUIREMENTS
-------------
-* Ruby 2.3.0 or later
-* `patch` command to install Nokogiri
-* C compiler to compile Nokogiri
-
-SIMILAR EFFORTS
----------------
-* [gepub](https://github.com/skoji/gepub) - a generic EPUB library for Ruby
-* [epubinfo](https://github.com/chdorner/epubinfo) - Extracts metadata information from EPUB files. Supports EPUB2 and EPUB3 formats.
-* [ReVIEW](https://github.com/kmuto/review) - ReVIEW is a easy-to-use digital publishing system for books and ebooks.
-* [epzip](https://github.com/takahashim/epzip) - epzip is EPUB packing tool. It's just only doing 'zip.' :)
-* [eeepub](https://github.com/jugyo/eeepub) - EeePub is a Ruby ePub generator
-* [epub-maker](https://gitlab.com/KitaitiMakoto/epub-maker) - This library supports making and editing EPUB books based on this EPUB Parser library
-* [epub-cfi](https://gitlab.com/KitaitiMakoto/epub-cfi) - EPUB CFI library extracted this EPUB Parser library.
-
-If you find other gems, please tell me or request a pull request.
-
-RECENT CHANGES
---------------
-
-### 0.3.6
-
-* [BUG FIX]Ignore fragment when find item by relative IRI
-* Disable [PrettyBacktrace][] by default
-
-[PrettyBacktrace]: https://github.com/ko1/pretty_backtrace
-
-
-### 0.3.5
-
-* [BUG FIX]Fix a bug that {EPUB::ContentDocument::Navigation::Item#item} is `nil` when `href` includes double dots(`..`)(Thanks [aelkiss][]!)
-
-### 0.3.4
-
-* Add {EPUB::Publication::Package#full_path} and {EPUB::Publication::Package#rootfile}
-* [BUG FIX]Fix a bug that {EPUB::ContentDocument::Navigation::Item#item} doesn't return correct {EPUB::Publication::Package::Manifest::Item Item}(Thanks [aelkiss][]!)
-
-[aelkiss]: https://gitlab.com/aelkiss
-
-### 0.3.3
-
-* [BUG FIX]Use UnpackedURI adapter for URI
-* [BREAKING CHANGE]Remove deprecated second argument from `EPUB::Parser::Publication#initialize`
-* Add `detect_encoding` keyword argument to `Publication::Package::Manifest::Item#read` and `ContentDocument::XHTML#read`
-
-See {file:CHANGELOG.markdown} for older changelogs and details.
-
-TODOS
------
-* Consider to implement IRI feature instead of to use Addressable
-* EPUB 3.0.1
-* EPUB 3.1
-* Help features for `epub-open` tool
-* Vocabulary Association Mechanisms
-* Implementing navigation document and so on
-* Media Overlays
-* Content Document
-* Digital Signature
-* Using SAX on parsing
-* Abstraction of XML parser(making it possible to use REXML, standard bundled XML library of Ruby)
-* Handle with encodings other than UTF-8
-
-DONE
-----
-* Simple inspect for `epub-open` tool
-* Using zip library instead of `unzip` command, which has security issue
-* Modify methods around fallback to see `bindings` element in the package
-* Content Document(only for Navigation Documents)
-* Fixed Layout
-* Vocabulary Association Mechanisms(only for itemref)
-* Archive library abstraction
-* Extracting and organizing common behavior from some classes to modules
-* Multiple rootfiles
-
-LICENSE
--------
-This library is distribuetd under the term of the MIT License.
-See MIT-LICENSE file for more info.

data/docs/Home.markdown

@@ -1,196 +0,0 @@
-EPUB Parser
-===========
-
-EPUB Parser gem parses EPUB 3 book loosely.
-
-Installation
-------------
-
-    gem install epub-parser
-
-Usage
------
-
-### As command-line tools
-
-#### epubinfo
-
-`epubinfo` tool extracts and shows the metadata of specified EPUB book.
-
-See {file:docs/Epubinfo.markdown}.
-
-#### epub-open
-
-`epub-open` tool provides interactive shell(IRB) which helps you research about EPUB book.
-
-See {file:docs/EpubOpen.markdown}.
-
-### As a library
-
-Use `EPUB::Parser.parse` at first:
-
-    require 'epub/parser'
-    
-    book = EPUB::Parser.parse('/path/to/book.epub')
-
-This book object can yield page by spine's order(spine defines the order to read that the author determines):
-
-    book.each_page_on_spine do |page|
-      # do something...
-    end
-
-`page` above is an {EPUB::Publication::Package::Manifest::Item} object and you can call {EPUB::Publication::Package::Manifest::Item#href #href} to see where is the page file:
-
-    book.each_page_on_spine do |page|
-      file = page.href # => path/to/page/in/zip/archive
-      html = Zip::Archive.open('/path/to/book.epub') {|zip|
-        zip.fopen(file.to_s) {|file| file.read}
-      }
-    end
-
-And {EPUB::Publication::Package::Manifest::Item Item} provides syntax suger {EPUB::Publication::Package::Manifest::Item#read #read} for above:
-
-    html = page.read
-    doc = Nokogiri.HTML(html)
-    # do something with Nokogiri as always
-
-For several utilities of Item, see {file:docs/Item.markdown} page.
-
-By the way, although `book` above is a {EPUB::Book} object, all features are provided by {EPUB::Book::Features} module. Therefore YourBook class can include the features of {EPUB::Book::Features}:
-
-    require 'epub'
-    
-    class YourBook < ActiveRecord::Base
-        include EPUB::Book::Features
-    end
-    
-    book = EPUB::Parser.parse(
-      'uploaded-book.epub',
-      :class => YourBook # *************** pass YourBook class
-    )
-    book.instance_of? YourBook # => true
-    book.required = 'value for required field'
-    book.save!
-    book.each_page_on_spine do |epage|
-      page = YouBookPage.create(
-        :some_attr    => 'some attr',
-        :content      => epage.read,
-        :another_attr => 'another attr'
-      )
-      book.pages << page
-    end
-
-You are also able to find YourBook object for the first:
-
-    book = YourBook.find params[:id]
-    ret = EPUB::Parser.parse(
-      'uploaded-book.epub',
-      :book => book # ******************* pass your book instance
-    ) # => book
-    ret == book # => true; this API is not good I feel... Welcome suggestion!
-    # do something with your book
-
-#### Switching ZIP library
-
-EPUB Parser uses [Archive::Zip][], a pure Ruby ZIP library, by default. You can use [Zip/Ruby][], a Ruby bindings for [libzip][] if you have already installed Zip/Ruby gem by RubyGems or Bundler.
-
-Globally:
-
-    EPUB::OCF::PhysicalContainer.adapter = :Zipruby
-    book = EPUB::Parser.parse("path/to/book.epub")
-
-For each EPUB book:
-
-    book = EPUB::Parser.parse("path/to/book.epub", container_adapter: :Zipruby)
-
-[Archive::Zip]: https://github.com/javanthropus/archive-zip
-[Zip/Ruby]: https://bitbucket.org/winebarrel/zip-ruby/wiki/Home
-[libzip]: https://nih.at/libzip/
-
-Documentation
--------------
-
-More documentations are avaiable in:
-
-* {file:docs/Publication.markdown}
-* {file:docs/Item.markdown}
-* {file:docs/FixedLayout.markdown}
-* {file:docs/Navigation.markdown}
-* {file:docs/Searcher.markdown}
-* {file:docs/UnpackedArchive.markdown}
-* {file:docs/AggregateContentsFromWeb.markdown}
-* {file:docs/MultipleRenditions.markdown}
-
-If you installed EPUB Parser via gem command, you can also generate documentaiton by your own([rubygems-yardoc][] gem is needed):
-
-    $ gem install epub-parser
-    $ gem yardoc epub-parser
-    ...
-    Files:          33
-    Modules:        20 (   20 undocumented)
-    Classes:        45 (   44 undocumented)
-    Constants:      31 (   31 undocumented)
-    Methods:       292 (   88 undocumented)
-    52.84% documented
-    YARD documentation is generated to:
-    /path/to/gempath/ruby/2.2.0/doc/epub-parser-0.2.0/yardoc
-
-It will show you path to generated documentation(`/path/to/gempath/ruby/2.2.0/doc/epub-parser-0.2.0/yardoc` here) at the end.
-
-Or, generating yardoc command is possible, too:
-
-    $ git clone https://gitlab.com/KitaitiMakoto/epub-parser.git
-    $ cd epub-parser
-    $ bundle install --path=deps
-    $ bundle exec rake doc:yard
-    ...
-    Files:          33
-    Modules:        20 (   20 undocumented)
-    Classes:        45 (   44 undocumented)
-    Constants:      31 (   31 undocumented)
-    Methods:       292 (   88 undocumented)
-    52.84% documented
-
-Then documentation will be available in `doc` directory.
-
-[homepage]: http://www.rubydoc.info/gems/epub-parser/file/docs/Home.markdown
-[rubygems-yardoc]: https://rubygems.org/gems/rubygems-yardoc
-
-Requirements
-------------
-
-* Ruby 2.2.0 or later
-* `patch` command to install Nokogiri
-* C compiler to compile Zip/Ruby and Nokogiri
-
-History
--------
-
-See {file:CHANGELOG.markdown}.
-
-Note
-----
-
-This library is still in work.
-Only a few features are implemented and APIs might be changed in the future.
-Note that.
-
-Currently implemented:
-
-* container.xml of [EPUB Open Container Format (OCF) 3.0][]
-* [EPUB Publications 3.0][]
-* EPUB Navigation Documents of [EPUB Content Documents 3.0][]
-* [EPUB 3 Fixed-Layout Documents][]
-* metadata.xml of [EPUB Multiple-Rendition Publications][]
-
-[EPUB Open Container Format (OCF) 3.0]:http://idpf.org/epub/30/spec/epub30-ocf.html#sec-container-metainf-container.xml
-[EPUB Publications 3.0]:http://idpf.org/epub/30/spec/epub30-publications.html
-[EPUB Content Documents 3.0]:http://www.idpf.org/epub/30/spec/epub30-contentdocs.html
-[EPUB 3 Fixed-Layout Documents]:http://www.idpf.org/epub/fxl/
-[EPUB Multiple-Rendition Publications]: http://www.idpf.org/epub/renditions/multiple/
-
-License
--------
-
-This library is distributed under the term of the MIT Licence.
-See {file:MIT-LICENSE} file for more info.