epub-parser 0.0.8 → 0.0.9

data/README.markdown

@@ -10,24 +10,24 @@ USAGE
 
 ### As a command line tool
 
-	epubinfo path/to/book.epub
+    epubinfo path/to/book.epub
 
 For more info:
 
-	epubinfo -h
+    epubinfo -h
 
 ### As a library
 
     require 'epub/parser'
     
-    book = EPUB::Parser.parse 'book.epub', 'working/directory'
+    book = EPUB::Parser.parse 'book.epub'
     book.each_page_on_spine do |page|
       # do somethong...
     end
 
 See the [wiki][] for more info.
 
-[wiki]:https://gitorious.org/epub/pages/EpubParser
+[wiki]:https://github.com/KitaitiMakoto/epub-parser/wiki
 
 REQUIREMENTS
 ------------
@@ -37,12 +37,15 @@ REQUIREMENTS
 TODOS
 -----
 * Adding tests
-* Implementing metadata/link, navigation document and so on
-* Using zip library instead of `unzip` command, which has security issue
+* Implementing navigation document and so on
 * Using SAX on parsing
 * Extracting and organizing common behavior from some classes to modules
 * Abstraction of XML parser(making it possible to use REXML, standard bundled XML library of Ruby)
 
+DONE
+----
+* Using zip library instead of `unzip` command, which has security issue
+
 LICENSE
 -------
 This library is distribuetd under the term of the MIT License.

data/Rakefile

@@ -1,6 +1,8 @@
 require 'bundler/gem_tasks'
 require 'rake/testtask'
 require 'yard'
+require 'cucumber'
+require 'cucumber/rake/task'
 
 task :default => :test
 
@@ -11,6 +13,8 @@ end
 
 YARD::Rake::YardocTask.new
 
+Cucumber::Rake::Task.new
+
 namespace :sample do
   desc 'Build the test fixture EPUB'
   task :build do

data/bin/epubinfo

@@ -1,9 +1,6 @@
-require 'tmpdir'
 require 'optparse'
 require 'epub/parser'
 
-Version = EPUB::Parser::VERSION
-
 options = {:format => :line}
 opt = OptionParser.new do |opt|
   opt.banner = <<EOB
@@ -12,6 +9,7 @@ Show metadata of an EPUB file
 Usage: epubinfo [options] EPUBFILE
 
 EOB
+  opt.version = EPUB::Parser::VERSION
   opt.on '-f', '--format=FORMAT', [:line, :json, :yaml], 'format of output(line, json or yaml), defaults to line(for console)' do |format|
     options[:format] = format
   end
@@ -22,22 +20,20 @@ file = ARGV.shift
 unless file
   $stdout.puts "error: you must supply an EPUB file name"
   $stdout.puts opt.help
-  exit!
+  abort
 end
 
-Dir.mktmpdir('epub-parser') do |dir|
-  book = EPUB::Parser.parse file, dir
-  data = {'Title' => [book.title]}
-  data.merge!(book.package.metadata.to_hash)
-  data['Unique identifier'] = [book.package.metadata.unique_identifier]
-  data['EPUB Version'] = [book.package.version]
-  if options[:format] == :line
-    key_width = data.keys.map {|k| k.length}.max + 3
-    data.each_pair do |k, v|
-      puts (k.to_s.capitalize + ':').ljust(key_width) + v.join(', ')
-    end
-  else
-    require options[:format].to_s
-    puts data.__send__("to_#{options[:format]}")
+book = EPUB::Parser.parse file
+data = {'Title' => [book.title]}
+data.merge!(book.package.metadata.to_hash)
+data['Unique identifier'] = [book.package.metadata.unique_identifier]
+data['EPUB Version'] = [book.package.version]
+if options[:format] == :line
+  key_width = data.keys.map {|k| k.length}.max + 3
+  data.each_pair do |k, v|
+    puts (k.to_s.capitalize + ':').ljust(key_width) + v.join(', ')
   end
+else
+  require options[:format].to_s
+  puts data.__send__("to_#{options[:format]}")
 end

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    = "https://gitorious.org/epub/parser"
+  s.homepage    = "https://github.com/KitaitiMakoto/epub-parser"
   s.summary     = %q{EPUB 3 Parser}
   s.description = %q{Parse EPUB 3 book loosely}
   s.license     = 'MIT'
@@ -19,12 +19,14 @@ Gem::Specification.new do |s|
   s.test_files    = `git ls-files -- {test,spec,features}/**/*.rb`.split("\n") 
   s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
   s.require_paths = ["lib"]
+  s.has_rdoc = 'yard'
 
   s.add_development_dependency 'rubygems-test'
   s.add_development_dependency 'rake'
   s.add_development_dependency 'pry'
   s.add_development_dependency 'pry-doc'
-  s.add_development_dependency 'test-unit', '~> 2'
+  s.add_development_dependency 'pry-nav'
+  s.add_development_dependency 'test-unit-full'
   s.add_development_dependency 'simplecov'
   s.add_development_dependency 'thin'
   s.add_development_dependency 'yard'
@@ -34,7 +36,7 @@ Gem::Specification.new do |s|
   s.add_development_dependency 'epubcheck'
   s.add_development_dependency 'epub_validator'
   s.add_development_dependency 'zipruby'
-  s.add_development_dependency 'rubyzip'
+  s.add_development_dependency 'aruba'
 
   s.add_runtime_dependency 'enumerabler'
   s.add_runtime_dependency 'nokogiri'

data/lib/epub.rb

@@ -6,6 +6,7 @@ require 'epub/parser'
 module EPUB
   modules = [ :ocf, :package, :content_document ]
   attr_reader *modules
+  attr_reader :epub_file
   modules.each do |mod|
     define_method "#{mod}=" do |obj|
       instance_variable_set "@#{mod}", obj
@@ -14,6 +15,7 @@ module EPUB
   end
 
   def parse(file, dir, options = {})
+    @epub_file = file
     options = options.merge({:book => self})
     Parser.parse(file, dir, options)
   end

data/lib/epub/parser.rb

@@ -3,53 +3,35 @@ require 'epub/parser/version'
 require 'epub/parser/ocf'
 require 'epub/parser/publication'
 require 'epub/parser/content_document'
-require 'shellwords'
+require 'zipruby'
 require 'nokogiri'
 
 module EPUB
   class Parser
     class << self
-      def parse(file, dir, options = {})
-        new(file, dir, options).parse
+      def parse(file, options = {})
+        new(file, options).parse
       end
     end
 
-    def initialize(filepath, root_directory, options = {})
+    def initialize(filepath, options = {})
       raise "File #{filepath} not readable" unless File.readable_real? filepath
-      raise "File #{root_directory} already exists" if File.file? root_directory
-        
-      @filepath = File.realpath filepath
-      Dir.mkdir(root_directory) unless File.directory? root_directory
-      @dir = File.realpath root_directory
 
+      @filepath = File.realpath filepath
       @book = create_book options
-
-      unzip_cmd = options['unzip-command'] || 'unzip'
-      unzip_cmd << " #{@filepath.to_s.shellescape} -d #{@dir.to_s.shellescape} 1>/dev/null"
-      system unzip_cmd
     end
 
     def parse
-      @book.ocf = parse_ocf
-      @book.package = parse_publication
-      # @book.content_document =??? parse_content_document
-      # ...
+      Zip::Archive.open @filepath do |zip|
+        @book.ocf = OCF.parse(zip)
+        @book.package = Publication.parse(zip, @book.rootfile_path)
+        # @book.content_document =??? parse_content_document
+        # ...
+      end
 
       @book
     end
 
-    def parse_ocf
-      OCF.parse @dir
-    end
-
-    def parse_publication
-      Publication.parse File.join(@dir, @book.rootfile_path)
-    end
-
-    def parse_content_document
-      # ContentDocument.parse @dir
-    end
-
     private
 
     def create_book(params)

data/lib/epub/parser/content_document.rb

@@ -35,9 +35,7 @@ module EPUB
         # And if so, where should the namespaces be defined?
         # nav.type = element['epub:type']
         element.namespaces['epub'] = "http://www.idpf.org/2007/ops"
-        p element.namespaces
         nav.type = element['epub:type']
-        p nav.type
 
         nav
       end

data/lib/epub/parser/ocf.rb

@@ -1,5 +1,6 @@
 require 'epub/constants'
 require 'epub/ocf'
+require 'zipruby'
 require 'nokogiri'
 
 module EPUB
@@ -9,13 +10,13 @@ module EPUB
       EPUB::OCF::MODULES.each {|m| self.const_set "#{m.upcase}_FILE", "#{m}.xml"}
 
       class << self
-        def parse(root_directory)
-          new(root_directory).parse
+        def parse(zip_archive)
+          new(zip_archive).parse
         end
       end
 
-      def initialize(root_directory)
-        @dir = root_directory
+      def initialize(zip_archive)
+        @zip = zip_archive
         @ocf = EPUB::OCF.new
       end
 
@@ -28,8 +29,8 @@ module EPUB
 
       def parse_container
         container = EPUB::OCF::Container.new
-        doc = Nokogiri.XML open(File.join @dir, DIRECTORY, CONTAINER_FILE)
-
+        entry  = @zip.fopen(File.join(DIRECTORY, CONTAINER_FILE))
+        doc = Nokogiri.XML(entry.read)
         doc.xpath('/ocf:container/ocf:rootfiles/ocf:rootfile', EPUB::NAMESPACES).each do |elem|
           rootfile = EPUB::OCF::Container::Rootfile.new
           %w[full-path media-type].each do |attr|

data/lib/epub/parser/publication.rb

@@ -1,3 +1,4 @@
+require 'zipruby'
 require 'nokogiri'
 require 'addressable/uri'
 require 'epub/publication'
@@ -7,15 +8,16 @@ module EPUB
   class Parser
     class Publication
       class << self
-        def parse(file)
-          new(file).parse
+        def parse(zip_archive, file)
+          new(zip_archive, file).parse
         end
       end
 
-      def initialize(file)
+      def initialize(zip_archive, file)
         @package = EPUB::Publication::Package.new
-        @rootfile = Addressable::URI.parse File.realpath(file)
-        @doc = Nokogiri.XML open(file)
+        @rootfile = Addressable::URI.parse(file)
+        entry = zip_archive.fopen(file)
+        @doc = Nokogiri.XML(entry.read)
       end
 
       def parse

data/lib/epub/parser/version.rb

@@ -1,5 +1,5 @@
 module EPUB
   class Parser
-    VERSION = "0.0.8"
+    VERSION = "0.0.9"
   end
 end

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

@@ -47,7 +47,9 @@ module EPUB
           end
 
           def read
-            open(iri) {|file| file.read}
+            Zip::Archive.open(manifest.package.book.epub_file) {|zip|
+              zip.fopen(iri.to_s).read
+            }
           end
 
           # To do: Handle circular fallback chain

data/test/helper.rb

@@ -5,3 +5,4 @@ end
 
 gem 'test-unit'
 require 'test/unit'
+require 'test/unit/rr'

data/test/test_parser.rb

@@ -1,16 +1,10 @@
 require File.expand_path 'helper', File.dirname(__FILE__)
 require 'epub/parser'
 require 'fileutils'
-require 'tmpdir'
 
 class TestParser < Test::Unit::TestCase
   def setup
-    @rootdir = Dir.mktmpdir 'epub-parser'
-    @parser = EPUB::Parser.new 'test/fixtures/book.epub', @rootdir
-  end
-
-  def teardown
-    FileUtils.remove_entry_secure @rootdir
+    @parser = EPUB::Parser.new 'test/fixtures/book.epub'
   end
 
   def test_parse

data/test/test_parser_content_document.rb

@@ -15,4 +15,3 @@ class TestParserContentDocument < Test::Unit::TestCase
     assert_equal 'Table of Contents', navs.first.heading
   end
 end
-

data/test/test_parser_ocf.rb

@@ -4,7 +4,13 @@ require 'epub/parser/ocf'
 
 class TestParserOCF < Test::Unit::TestCase
   def setup
-    @parser = EPUB::Parser::OCF.new 'test/fixtures/book'
+    file = 'test/fixtures/book.epub'
+    @zip = Zip::Archive.open(file)
+    @parser = EPUB::Parser::OCF.new(@zip)
+  end
+
+  def teardown
+    @zip.close
   end
 
   def test_parsed_container_has_one_rootfile

data/test/test_parser_publication.rb

@@ -4,10 +4,17 @@ require 'epub/parser/publication'
 
 class TestParserPublication < Test::Unit::TestCase
   def setup
-    @parser = EPUB::Parser::Publication.new 'test/fixtures/book/OPS/ルートファイル.opf'
+    file = 'test/fixtures/book.epub'
+    root_file = 'OPS/ルートファイル.opf'
+    @zip = Zip::Archive.open(file)
+    @parser = EPUB::Parser::Publication.new(@zip, root_file)
     @package = @parser.parse_package
   end
 
+  def teardown
+    @zip.close
+  end
+
   def test_parse_package
     assert_equal '3.0', @package.version
   end
@@ -41,10 +48,8 @@ class TestParserPublication < Test::Unit::TestCase
       assert_equal 8, @manifest.items.length
     end
 
-    def test_item_has_full_path_as_iri_attribute
-      actual = File.expand_path 'fixtures/book/OPS/nav.xhtml', File.dirname(__FILE__)
-
-      assert_equal actual, @manifest['nav'].iri.to_s
+    def test_item_has_relative_path_as_iri_attribute
+      assert_equal 'OPS/nav.xhtml', @manifest['nav'].iri.to_s
     end
 
     def test_fallback_attribute_of_item_should_be_item_object
@@ -55,6 +60,10 @@ class TestParserPublication < Test::Unit::TestCase
     end
 
     def test_item_is_readable
+      book = Object.new
+      mock(@package).book {book}
+      mock(book).epub_file {'test/fixtures/book.epub'}
+
       item = @manifest.items.first
       doc = Nokogiri.XML item.read
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: epub-parser
 version: !ruby/object:Gem::Version
-  version: 0.0.8
+  version: 0.0.9
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-03-11 00:00:00.000000000Z
+date: 2012-08-13 00:00:00.000000000Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rubygems-test
-  requirement: &11201540 !ruby/object:Gem::Requirement
+  requirement: &7153000 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,10 +21,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *11201540
+  version_requirements: *7153000
 - !ruby/object:Gem::Dependency
   name: rake
-  requirement: &11189400 !ruby/object:Gem::Requirement
+  requirement: &7150920 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -32,10 +32,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *11189400
+  version_requirements: *7150920
 - !ruby/object:Gem::Dependency
   name: pry
-  requirement: &11186320 !ruby/object:Gem::Requirement
+  requirement: &7149860 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -43,10 +43,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *11186320
+  version_requirements: *7149860
 - !ruby/object:Gem::Dependency
   name: pry-doc
-  requirement: &11185640 !ruby/object:Gem::Requirement
+  requirement: &7148720 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -54,21 +54,32 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *11185640
+  version_requirements: *7148720
 - !ruby/object:Gem::Dependency
-  name: test-unit
-  requirement: &11184560 !ruby/object:Gem::Requirement
+  name: pry-nav
+  requirement: &7166500 !ruby/object:Gem::Requirement
     none: false
     requirements:
-    - - ~>
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *7166500
+- !ruby/object:Gem::Dependency
+  name: test-unit-full
+  requirement: &7165380 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
       - !ruby/object:Gem::Version
-        version: '2'
+        version: '0'
   type: :development
   prerelease: false
-  version_requirements: *11184560
+  version_requirements: *7165380
 - !ruby/object:Gem::Dependency
   name: simplecov
-  requirement: &11183620 !ruby/object:Gem::Requirement
+  requirement: &7163980 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -76,10 +87,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *11183620
+  version_requirements: *7163980
 - !ruby/object:Gem::Dependency
   name: thin
-  requirement: &11182540 !ruby/object:Gem::Requirement
+  requirement: &7162800 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -87,10 +98,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *11182540
+  version_requirements: *7162800
 - !ruby/object:Gem::Dependency
   name: yard
-  requirement: &11181840 !ruby/object:Gem::Requirement
+  requirement: &7162000 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -98,10 +109,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *11181840
+  version_requirements: *7162000
 - !ruby/object:Gem::Dependency
   name: gem-man
-  requirement: &11122520 !ruby/object:Gem::Requirement
+  requirement: &7161220 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -109,10 +120,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *11122520
+  version_requirements: *7161220
 - !ruby/object:Gem::Dependency
   name: ronn
-  requirement: &11120840 !ruby/object:Gem::Requirement
+  requirement: &7160400 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -120,10 +131,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *11120840
+  version_requirements: *7160400
 - !ruby/object:Gem::Dependency
   name: epzip
-  requirement: &11119120 !ruby/object:Gem::Requirement
+  requirement: &7159780 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -131,10 +142,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *11119120
+  version_requirements: *7159780
 - !ruby/object:Gem::Dependency
   name: epubcheck
-  requirement: &12151080 !ruby/object:Gem::Requirement
+  requirement: &7159180 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -142,10 +153,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *12151080
+  version_requirements: *7159180
 - !ruby/object:Gem::Dependency
   name: epub_validator
-  requirement: &12148200 !ruby/object:Gem::Requirement
+  requirement: &7177540 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -153,10 +164,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *12148200
+  version_requirements: *7177540
 - !ruby/object:Gem::Dependency
   name: zipruby
-  requirement: &11234320 !ruby/object:Gem::Requirement
+  requirement: &7176860 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -164,10 +175,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *11234320
+  version_requirements: *7176860
 - !ruby/object:Gem::Dependency
-  name: rubyzip
-  requirement: &11232240 !ruby/object:Gem::Requirement
+  name: aruba
+  requirement: &7176200 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -175,10 +186,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *11232240
+  version_requirements: *7176200
 - !ruby/object:Gem::Dependency
   name: enumerabler
-  requirement: &11227260 !ruby/object:Gem::Requirement
+  requirement: &7175580 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -186,10 +197,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *11227260
+  version_requirements: *7175580
 - !ruby/object:Gem::Dependency
   name: nokogiri
-  requirement: &11365900 !ruby/object:Gem::Requirement
+  requirement: &7174900 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -197,10 +208,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *11365900
+  version_requirements: *7174900
 - !ruby/object:Gem::Dependency
   name: addressable
-  requirement: &11363620 !ruby/object:Gem::Requirement
+  requirement: &7174140 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -208,7 +219,7 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *11363620
+  version_requirements: *7174140
 description: Parse EPUB 3 book loosely
 email:
 - KitaitiMakoto@gmail.com
@@ -264,7 +275,7 @@ files:
 - test/test_parser_ocf.rb
 - test/test_parser_publication.rb
 - test/fixtures/book/OPS/ルートファイル.opf
-homepage: https://gitorious.org/epub/parser
+homepage: https://github.com/KitaitiMakoto/epub-parser
 licenses:
 - MIT
 post_install_message: 
@@ -279,7 +290,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -1773548056502971517
+      hash: 3117642784575544251
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -288,7 +299,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -1773548056502971517
+      hash: 3117642784575544251
 requirements: []
 rubyforge_project: 
 rubygems_version: 1.8.8
@@ -296,4 +307,4 @@ signing_key:
 specification_version: 3
 summary: EPUB 3 Parser
 test_files: []
-has_rdoc: 
+has_rdoc: yard