epub-reader 0.0.9

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 310b2d309ca3ea509ad9c56afdcbaf53b1a7bc9a
+  data.tar.gz: a4ae809a633232d45737abd0363e954709bffd04
+SHA512:
+  metadata.gz: a87eb9670787d8411fb22d0971b7e8e1bcaf4e5694fc814f2991faac2cd94521fffe87b81ca3ebe3cce526bd85728cab34985a469fc7e6d24efdd01e5c3ba9eb
+  data.tar.gz: d7e1a1cc73c277912c119522535fdf34e77e0b0365da5cbf39af553995d9c06b8ad5f1e6edc8e5bc81d752695e32b7a67ce16667e3711a9dd613909def788b99

data/.gitignore

@@ -0,0 +1,4 @@
+*.gem
+.bundle
+Gemfile.lock
+pkg/*

data/.rbenv-gemsets

@@ -0,0 +1 @@
+epub-reader

data/.rspec

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

data/.ruby-version

@@ -0,0 +1 @@
+2.0.0-p247

data/Gemfile

@@ -0,0 +1,7 @@
+source "http://rubygems.org"
+
+gemspec
+
+group :development, :test do
+  gem "rspec"
+end

data/README.md

@@ -0,0 +1,65 @@
+# Overview
+
+EPUB Reader is a Ruby library which helps you to parse EPUB files conforming
+as much as possible the specification from IDPF.
+
+# Installation
+
+The recommended installation method is via Rubygems.
+
+    gem install epub-reader
+
+# Usage
+
+Begin by creating a Epub::Reader instance that points to a EPUB file. Document
+level information (metadata, toc, page count, etc) is available via this object.
+
+    reader = Epub::Reader.open("somefile.epub")
+    puts reader.epub_version
+    puts reader.title
+    puts reader.author
+    puts reader.publication_date
+    puts reader.language
+    reader.pages.each do |page|
+      puts page.title
+      puts page.content
+    end
+
+# Exceptions
+
+There are two key exceptions that you will need to watch out for when processing a
+EPUB file:
+
+FileNotFoundError - The argument passed to Epub::Reader.open('file.epub') is a file
+path. If the file does not exist the FileNotFoundError is thrown.
+
+MalformedEpubError - The EPUB appears to be corrupt in some way. If you believe the
+file should be valid, or that a corrupt file didn't raise an exception, please
+forward a copy of the file to the maintainers using the Bitbucket issue tracker
+and we will attempt to improve the code.
+
+MalformedEpubError has some subclasses if you want to detect finer grained issues. If you
+don't, 'rescue MalformedEpubError' will catch all the subclassed errors as well.
+
+Any other exceptions should be considered bugs in either Epub::Reader (please
+report it!).
+
+# Mantainers
+
+- Fernando Almeida <fernando@fernandoalmeida.net>
+
+# Licensing
+
+This is a proprietary library and all rights are reserved to eBookPlus.com.
+
+# References
+
+[What is EPUB 3?](http://shop.oreilly.com/product/0636920022442.do)
+
+[EPUB Publications Specifications](http://idpf.org/epub/30/spec/epub30-publications.html)
+
+[EPUB Content Documents Specifications](http://idpf.org/epub/30/spec/epub30-contentdocs.html)
+
+[EPUB Open Container Formats Specifications](http://idpf.org/epub/30/spec/epub30-ocf.html)
+
+[Shared Workspace for Emerging Specifications and Schemas for EPUB 3](http://code.google.com/p/epub-revision/downloads/list)

data/Rakefile

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

data/epub-reader.gemspec

@@ -0,0 +1,23 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "epub-reader/version"
+
+Gem::Specification.new do |s|
+  s.name        = "epub-reader"
+  s.version     = Epub::Reader::VERSION
+  s.authors     = ["Fernando Almeida"]
+  s.email       = ["fernando@fernandoalmeida.net"]
+  s.homepage    = "http://bitbucket.com/fernandoalmeida/epub-reader"
+  s.summary     = "A library for accessing the content of EPUB files"
+  s.description = "The epub-reader library implements a EPUB parser conforming as much as possible to the EPUB 3 specification from IDPF"
+
+  s.rubyforge_project = "epub-reader"
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+
+  s.add_dependency('rubyzip')
+  s.add_dependency('nokogiri')
+end

data/lib/epub-reader.rb

@@ -0,0 +1,14 @@
+require 'zip/zipfilesystem'
+require 'nokogiri'
+require "epub-reader/version"
+require "epub-reader/reader"
+require "epub-reader/epubfile"
+require "epub-reader/container"
+require "epub-reader/package"
+require "epub-reader/toc"
+require "epub-reader/page"
+
+module Epub
+  class FileNotFoundError  < StandardError; end
+  class MalformedFileError < StandardError; end
+end

data/lib/epub-reader/container.rb

@@ -0,0 +1,35 @@
+module Epub
+  class Container
+    
+    attr_reader :packages
+    
+    def initialize(reader)
+      @reader    = reader
+      @container = get_container_content
+      @xml       = Nokogiri::XML(@container)
+      @packages  = []
+      @xml.css('container rootfiles rootfile').each do |rootfile|
+        @packages << Package.new(rootfile, @reader.file)
+      end
+    end
+
+    def raw
+      @container.to_s
+    end
+
+    def package(index = 0)
+      @packages[index]
+    end
+    
+    private
+
+    def get_container_content
+      begin
+        @reader.file.get_input_stream('META-INF/container.xml').read
+      rescue
+        nil
+      end
+    end
+
+  end
+end

data/lib/epub-reader/epubfile.rb

@@ -0,0 +1,7 @@
+module Epub
+  class EpubFile < Zip::ZipFile
+    def initialize(f)
+      super
+    end
+  end
+end

data/lib/epub-reader/package.rb

@@ -0,0 +1,255 @@
+module Epub
+  class Package
+
+    def initialize(rootfile, file)
+      @rootfile = rootfile
+      @file     = file
+      @package  = get_package_content(file)
+      @xml = Nokogiri::XML(@package).remove_namespaces!
+    end
+
+    def raw
+      @package.to_s
+    end
+
+    def path
+      @rootfile.attr('full-path').to_s
+    end
+
+    def relative_content_path
+      i   = path.rindex('/').to_i
+      i > 0 ? path[0,i+1] : ""
+    end
+
+    def mediatype
+      @rootfile.attr('media-type')
+    end
+
+    def version
+      root.attr('version').to_s.to_i
+    end
+
+    def identifier
+      identifiers.css("[id=#{unique_identifier}]").text
+    end
+
+    # TODO: identify language
+    # TODO: identify subtitles
+    def title
+      titles.first.text
+    end
+
+    def language
+      languages.first.text
+    end
+
+    # TODO: identify role
+    # TODO: identify file-as
+    # TODO: identify alternate-script
+    # TODO: identify display-seq
+    def creator
+      creators.size > 0 ? creators.first.text : ""
+    end
+
+    # TODO: equal to creator
+    def contributor
+      contributors.size > 0 ? contributors.first.text : ""
+    end
+
+    def date
+      d = metadata.css('data')
+      d.size > 0 ? d.text : ""
+    end
+
+    def source
+      s = metadata.css('source')
+      s.size > 0 ? s.text : ""
+    end
+
+    def type
+      t = metadata.css('type')
+      t.size > 0 ? t.text : ""
+    end
+
+    def resources
+      manifest.css('item')
+    end
+
+    def images
+      resources.select{|resource| resource.attr('media-type').to_s.match(/^image\/(gif|jpeg|svg\+xml)/)}
+    end
+
+    def html
+      resources.css('[media-type="application/xhtml+xml"]')
+    end
+
+    def stylesheets
+      resources.css('[media-type="text/css"]')
+    end
+
+    def javascripts
+      resources.css('[media-type="text/javascript"]')
+    end
+
+    def fonts
+      resources.select{|resource| resource.attr('media-type').to_s.match(/application\/(vnd\.ms-opentype|font-woff)/)}
+    end
+
+    def audios
+      resources.select{|resource| resource.attr('media-type').to_s.match(/^audio\/(mpeg|mp4)/)}
+    end
+
+    def toc
+      toc_item_id       = spine.attr("toc")
+      toc_item_mimetype = "application/x-dtbncx+xml"
+      toc_item_selector = toc_item_id ? "##{toc_item_id.to_s}" : '[media-type="#{toc_item_mimetype}"]'
+      relative_content_path + resources.css(toc_item_selector).attr('href').to_s
+    end
+
+    def cover
+      begin
+        cover_meta     = metadata.css('[name="cover"]')
+        meta_content   = cover_meta.size == 1 ? cover_meta.attr('content') : nil
+        cover_content  = meta_content || manifest.css('[properties="cover-image"]').attr('id').to_s
+        cover_path     = (cover_content.to_s.match(/\.(gif|jpe?g|png)/) ? cover_content : resources.css("##{cover_content}").attr('href').to_s)
+        if cover_exist?(relative_content_path + cover_path)
+          relative_content_path + cover_path
+        elsif cover_exist?(relative_content_path + "Images/" + cover_path)
+          relative_content_path + "Images/" + cover_path
+        else
+          ""
+        end
+      rescue
+        ""
+      end
+    end
+
+    # TODO: to parse
+    # guide    [optional/deprecated]
+    # bindings [optional]
+
+    def reading_order
+      spine_items.map do |item|
+        item_id = item.attr('idref').to_s
+        manifest.css("##{item_id}") if item_id
+      end
+    end
+
+    protected
+
+    def spine_items
+      spine.css('itemref')
+    end
+
+    def get_package_content(file)
+      begin
+        file.get_input_stream(path)
+      rescue
+        nil
+      end
+    end
+
+    def cover_exist?(path)
+      begin
+        !!@file.find_entry(path)
+      rescue
+        false
+      end
+    end
+
+    def root
+      @xml.css('package')
+    end
+
+    def unique_identifier
+      root.attr('unique-identifier').to_s
+    end
+
+    def prefix
+      root.attr('prefix').to_s
+    end
+
+    def lang
+      root.attr('xml:lang').to_s
+    end
+
+    def dir
+      (spine.attr('page-progression-direction') || root.attr('dir')).to_s
+    end
+
+    def id
+      root.attr('id').to_s
+    end
+
+    # TODO: to do parse of
+    # DCMES Optional Elements [0 or more]
+    #   contributor
+    #   coverage
+    #   creator
+    #   date
+    #   description
+    #   format
+    #   publisher
+    #   relation
+    #   rights
+    #   source
+    #   subject
+    #   type
+    # meta [1 or more]
+    # OPF2 meta [0 or more]
+    # link [0 or more]
+
+    ############
+    # Metadata #
+    ############
+    def metadata
+      root.css('metadata')
+    end
+
+    def identifiers
+      metadata.css('identifier')
+    end
+
+    def titles
+      metadata.css('title')
+    end
+
+    def languages
+      metadata.css('language')
+    end
+
+    def creators
+      metadata.css('creator')
+    end
+
+    def contributors
+      metadata.css('contributor')
+    end
+
+    def meta
+      metadata.css('meta')
+    end
+
+    def link
+      metadata.css('link')
+    end
+
+    ############
+    # Manifest #
+    ############
+    def manifest
+      root.css('manifest')
+    end
+
+    ############
+    #  Spine   #
+    ############
+    def spine
+      root.css('spine')
+    end
+
+    def reading_order_selectors
+      reading_order.map{|item| "##{item.attr('idref')}"}
+    end
+  end
+end

data/lib/epub-reader/page.rb

@@ -0,0 +1,26 @@
+module Epub
+  class Page
+    def initialize(title, path, file)
+      @title = title
+      @path  = path
+      @file  = file
+    end
+    
+    attr_reader :title, :path
+    
+    def content
+      @content ||= get_page_content
+    end
+
+    private
+
+    def get_page_content
+      begin
+        @file.get_input_stream(@path).read.force_encoding(Encoding::UTF_8)
+      rescue
+        ""
+      end
+    end
+
+  end
+end

data/lib/epub-reader/reader.rb

@@ -0,0 +1,118 @@
+module Epub
+  class Reader
+
+    EPUB_MIMETYPE     = "application/epub+zip"
+    PACKAGE_MEDIATYPE = "application/oebps-package+xml"
+
+    attr_reader :filepath, :file
+    
+    def initialize(f)
+      raise(FileNotFoundError, "File not found") unless File.exists?(f)
+      @filepath  = f.to_s
+      @file      = EpubFile.new(f)
+      raise(MalformedFileError, "Invalid EPUB file format") unless valid?
+    end
+    
+    def Reader.open(f)
+      reader = Reader.new(f)
+      if block_given?
+        yield reader
+      else
+        reader
+      end
+    end
+
+    def mimetype
+      @mimetype ||= begin
+        file.get_input_stream('mimetype').read
+      rescue
+        nil
+      end
+    end
+
+    def epub_version
+      @version ||= package.version
+    end
+
+    def uid
+      @uid ||= package.identifier
+    end
+
+    def title
+      @title ||= package.title
+    end
+
+    def author
+      @author ||= package.creator
+    end
+
+    def publication_date
+      @publication_date ||= package.date
+    end
+
+    def language
+      @language ||= package.language
+    end
+
+    def toc
+      @toc ||= Toc.new(package.toc, self)
+    end
+
+    def pages
+      @pages ||= toc.pages
+    end
+    
+    def container
+      @container ||= Container.new(self)
+    end
+
+    def cover
+      @cover ||= package.cover
+    end
+
+    # TODO: To parse other META-INF files
+    # signatures.xml [optional]
+    # Contains digital signatures for various assets.
+
+    # encryption.xml [optional]
+    # Contains information about the encryption of Publication resources. (This file is required if font obfuscation is used.)
+
+    # metadata.xml [optional]
+    # Used to store metadata about the container.
+
+    # rights.xml [optional]
+    # Used to store information about digital rights.
+
+    # manifest.xml [allowed]
+    # A manifest of container contents as allowed by Open Document Format [ODF]. 
+
+    # Convenient method
+    def package(index = 0)
+      container.package(index)
+    end
+
+    private
+
+    def valid?
+      valid_mimetype? && valid_container? && valid_package? && valid_toc?
+    end
+
+    def valid_mimetype?
+      /application\/epub\+zip/.match(mimetype)
+    end
+
+    def valid_container?
+      !container.nil?
+    end
+
+    def valid_package?
+      package.path.match(/\.opf$/) && package.mediatype == PACKAGE_MEDIATYPE
+    end
+
+    # TODO: validates TOC
+    def valid_toc?
+      true
+    end
+
+  end
+end

data/lib/epub-reader/toc.rb

@@ -0,0 +1,130 @@
+module Epub
+  class Toc
+
+    def initialize(tocfile, reader)
+      @tocfile = tocfile
+      @reader  = reader
+      @file    = @reader.file
+      @content = get_toc_content
+      @xml     = Nokogiri::XML(@content).remove_namespaces!
+    end
+
+    def content
+      if ncx?
+        if has_toc?
+          ncx_to_html
+        else
+          spine_to_html
+        end
+      else
+        @content
+      end
+    end
+    
+    def pages
+      points = @xml.css("ncx navMap navPoint")
+      items  = @reader.package.reading_order
+      if ncx? && has_toc? && points.size > 1
+        points.map do |point|
+          title = point.css('navLabel > text').first.text
+          file_path  = @reader.package.relative_content_path + point.css('content').attr('src').to_s
+          Page.new(title, file_path, @reader.file)
+        end
+      else
+        items.map do |item|
+          title = ""
+          file_path  = @reader.package.relative_content_path + item.attr('href').to_s
+          Page.new(title, file_path, @reader.file)
+        end
+      end
+    end
+    
+    private
+      
+    def ncx?
+      @tocfile.match(/(\.ncx)$/)
+    end
+
+    def has_toc?
+      @xml.css('navMap > navPoint').size > 0
+    end
+
+    def get_toc_content
+      begin
+        @reader.file.get_input_stream(@tocfile).read
+      rescue
+        ""
+      end
+    end
+
+    # TODO: Add Stylesheets
+    # TODO: Convert nested navigation
+    # TODO: Refactoring to DRY with spine_to_html
+    def ncx_to_html
+      html     = <<EOF
+<?xml version="1.0" encoding="UTF-8"?>
+<html xmlns="http://www.w3.org/1999/xhtml" profile="http://www.idpf.org/epub/30/profile/content/">
+  <head>
+    <meta http-equiv="content-type" content="text/html; charset=utf-8"/>
+    <title>#{title}</title>
+  </head>
+  <body>
+    <section>
+      <nav id="toc" epub:type="toc">
+        <ol>
+EOF
+          selector = "ncx > navMap > navPoint"
+          @xml.css(selector).each do |point|
+            html += "<li id=\"#{point.attr('id').to_s}\"><a href=\"#{point.css('content').attr('src').to_s}\">#{point.css('navLabel text').text}</a></li>"
+          end
+          html += <<EOF
+        </ol>
+      </nav>
+    </section>
+  </body>
+</html>
+EOF
+      html
+    end
+
+    def spine_to_html
+      html     = <<EOF
+<?xml version="1.0" encoding="UTF-8"?>
+<html xmlns="http://www.w3.org/1999/xhtml" profile="http://www.idpf.org/epub/30/profile/content/">
+  <head>
+    <meta http-equiv="content-type" content="text/html; charset=utf-8"/>
+    <title>#{title}</title>
+  </head>
+  <body>
+    <section>
+      <nav id="toc" epub:type="toc">
+        <ol>
+EOF
+      @reader.package.reading_order.each do |item|
+        link = item.attr('href').to_s
+        html += "<li id=\"#{item.attr('id').to_s}\"><a href=\"#{link}\">#{link[0,link.rindex('.')]}</a></li>"        
+      end
+      html += <<EOF
+        </ol>
+      </nav>
+    </section>
+  </body>
+</html>
+EOF
+      html
+    end
+
+    def title
+      root.css('docTitle > text').text
+    end
+    
+    def root
+      @xml.css('ncx')
+    end
+
+    def navmap
+      root.css('navMap')
+    end
+
+  end
+end

data/lib/epub-reader/version.rb

@@ -0,0 +1,5 @@
+module Epub
+  class Reader
+    VERSION = "0.0.9"
+  end
+end

data/spec/container_spec.rb

@@ -0,0 +1,22 @@
+require 'spec_helper'
+
+describe Epub::Container do
+
+  before(:all) do
+    @file = 'spec/data/valid.epub'
+    @epub = Epub::Reader.open(@file)
+  end
+
+  it 'get raw content' do
+    @epub.container.raw.should_not be_empty
+  end
+
+  it 'get package documents' do
+    @epub.container.packages.should_not be_empty
+  end
+
+  it 'get default package document' do
+    @epub.container.package.should be_a(Epub::Package)
+  end
+
+end

data/spec/package_spec.rb

@@ -0,0 +1,101 @@
+require 'spec_helper'
+
+describe Epub::Package do
+
+  before(:all) do
+    @file = 'spec/data/valid.epub'
+    @reader = Epub::Reader.open(@file)
+  end
+
+  it 'get raw content' do
+    @reader.package.raw.should_not be_empty
+  end
+
+  it 'get file path' do
+    @reader.package.path.should_not be_empty
+  end
+
+  it 'get media type' do
+    @reader.package.mediatype.should eq("application/oebps-package+xml")
+  end
+
+  it 'get the epub version' do
+    @reader.package.version.should eq(3)
+  end
+
+  it 'get the unique identifier' do
+    @reader.package.identifier.should eq("urn:isbn:9780316000000")
+  end
+
+  it 'get the content language' do
+    @reader.package.language.should eq("en-US")
+  end
+
+  it 'get the content title' do
+    @reader.package.title.should eq("Moby-Dick")
+  end
+
+  it 'get the content creator' do
+    @reader.package.creator.should eq("Herman Melville")
+  end
+
+  it 'get the content contributor' do
+    @reader.package.contributor.should be_empty
+  end
+
+  it 'get the publication date' do
+    @reader.package.date.should be_empty
+  end
+
+  it 'get the publication source' do
+    @reader.package.source.should be_empty
+  end
+
+  it 'get the content type' do
+    @reader.package.source.should be_empty
+  end
+
+  it 'get the full resource list' do
+    @reader.package.resources.should_not be_empty
+  end
+
+  it 'get the image list' do
+    @reader.package.images.size.should eq(2)
+  end
+
+  it 'get the html list' do
+    @reader.package.html.size.should eq(143)
+  end
+
+  it 'get the stylesheet list' do
+    @reader.package.stylesheets.size.should eq(1)
+  end
+
+  it 'get the javascript list' do
+    @reader.package.javascripts.should be_empty
+  end
+
+  it 'get the font list' do
+    @reader.package.fonts.should be_empty
+  end
+
+  it 'get the audio list' do
+    @reader.package.audios.should be_empty
+  end
+
+  it 'get the table of content (toc)' do
+    @reader.package.toc.should eq("OPS/toc.ncx")
+  end
+
+  it 'get the reading order' do
+    list = @reader.package.reading_order
+    list.size.should eq(142)
+    list[0].attr('href').to_s.should eq('cover.xhtml')
+    list[1].attr('href').to_s.should eq('titlepage.xhtml')
+  end
+
+  it 'get the book cover' do
+    @reader.package.cover.should eq("OPS/images/9780316000000.jpg")
+  end
+
+end

data/spec/page_spec.rb

@@ -0,0 +1,24 @@
+require 'spec_helper'
+
+describe Epub::Page do
+
+  before(:all) do
+    file   = 'spec/data/valid.epub'
+    reader = Epub::Reader.open(file)
+    @toc   = Epub::Toc.new(reader.package.toc, reader)
+    @page  = @toc.pages.last
+  end
+
+  it 'get page title' do
+    @page.title.should eq('Copyright Page')
+  end
+
+  it 'get page path' do
+    @page.path.should eq('OPS/copyright.xhtml')
+  end
+
+  it 'get page content' do
+    @page.content.should match('<html.*>')
+    @page.content.should match('Produced by Daniel Lazarus and Jonesey')
+  end
+end

data/spec/reader_spec.rb

@@ -0,0 +1,61 @@
+require 'spec_helper'
+
+describe Epub::Reader do
+
+  before(:all) do
+    @file = 'spec/data/valid.epub'
+    @reader = Epub::Reader.open(@file)
+  end
+
+  it 'open a epub file' do
+    @reader.should_not be_nil
+  end
+
+  it 'raises an exception if file not found' do
+    lambda {Epub::Reader.open('not_found.epub')}.should raise_error
+  end
+
+  it 'raises an exception if malformed file' do
+    lambda {Epub::Reader.open('spec/data/invalid.epub')}.should raise_error
+  end
+
+  it 'get epub file path' do
+    @reader.filepath.should eq(@file)
+  end
+
+  it 'get epub mime type' do
+    @reader.mimetype.should eq("application/epub+zip")
+  end
+
+  it 'get the epub version' do
+    @reader.epub_version.should eq(3)
+  end
+
+  it 'get the epub unique identifier' do
+    @reader.uid.should eq("urn:isbn:9780316000000")
+  end
+
+  it 'get the title' do
+    @reader.title.should eq("Moby-Dick")
+  end
+
+  it 'get the author' do
+    @reader.author.should eq("Herman Melville")
+  end
+
+  it 'get the publication date' do
+    @reader.publication_date.should be_empty
+  end
+
+  it 'get the language' do
+    @reader.language.should eq("en-US")
+  end
+
+  it 'get the TOC' do
+    @reader.toc.should be_a(Epub::Toc)
+  end
+
+  it 'get the pages list' do
+    @reader.pages.size.should eq(142)
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,8 @@
+$: << File.join(File.dirname(__FILE__), "/../lib")
+
+require "rspec"
+require "epub-reader"
+
+RSpec.configure do |c|
+  c.mock_with :rspec
+end

data/spec/toc_spec.rb

@@ -0,0 +1,28 @@
+# -*- coding: utf-8 -*-
+require 'spec_helper'
+
+describe Epub::Toc do
+
+  before(:all) do
+    file    = 'spec/data/valid.epub'
+    @reader = Epub::Reader.open(file)
+    @toc    = Epub::Toc.new(@reader.package.toc, @reader)
+    @html   = Nokogiri::XML(@toc.content)
+  end
+
+  it 'convert <ncx>      to <html>' do
+    @html.css('html').size.should eq(1)
+  end
+
+  it 'convert <docTitle> to <title>' do
+    @html.css('head > title').text.should eq("Moby-Dick")
+  end
+
+  it 'convert <navMap>   to <nav>' do
+    @html.css('nav').size.should eq(1)
+  end
+
+  it 'convert <navPoint> to <a>' do
+    @html.css('li > a').size.should eq(142)
+  end
+end

data/teste.rb

@@ -0,0 +1,9 @@
+# `rake install`
+require 'rubygems'
+require 'epub-reader'
+
+hd = '/home/fernando/Dropbox/trabalho/livros_e_apostilas/EPUB/e_book_Marketing.epub'
+
+f1 = Epub::Reader.open(hd)
+
+puts f1.cover

metadata

@@ -0,0 +1,97 @@
+--- !ruby/object:Gem::Specification
+name: epub-reader
+version: !ruby/object:Gem::Version
+  version: 0.0.9
+platform: ruby
+authors:
+- Fernando Almeida
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-09-20 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rubyzip
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: The epub-reader library implements a EPUB parser conforming as much as
+  possible to the EPUB 3 specification from IDPF
+email:
+- fernando@fernandoalmeida.net
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- .rbenv-gemsets
+- .rspec
+- .ruby-version
+- Gemfile
+- README.md
+- Rakefile
+- epub-reader.gemspec
+- lib/epub-reader.rb
+- lib/epub-reader/container.rb
+- lib/epub-reader/epubfile.rb
+- lib/epub-reader/package.rb
+- lib/epub-reader/page.rb
+- lib/epub-reader/reader.rb
+- lib/epub-reader/toc.rb
+- lib/epub-reader/version.rb
+- spec/container_spec.rb
+- spec/data/invalid.epub
+- spec/data/valid.epub
+- spec/package_spec.rb
+- spec/page_spec.rb
+- spec/reader_spec.rb
+- spec/spec_helper.rb
+- spec/toc_spec.rb
+- teste.rb
+homepage: http://bitbucket.com/fernandoalmeida/epub-reader
+licenses: []
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: epub-reader
+rubygems_version: 2.0.3
+signing_key: 
+specification_version: 4
+summary: A library for accessing the content of EPUB files
+test_files: []