epub-parser 0.1.5 → 0.1.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 4451be8049a35f2aa4ca54da4d89445f6269c967
-  data.tar.gz: d254d043d0e356d062f7a422d8f0dbe28bd3be0b
+  metadata.gz: 65f7f0d3749c5bf1d34ab527c94ac0905a3fa30f
+  data.tar.gz: d88e97de68e8b5d81c27d5921ce2fbe3ebd99e7f
 SHA512:
-  metadata.gz: 4b36dd1a28d7a4249a6be8487e41210e1d9b29c00eddb7ada281035540199fcb263cec36b2b74ce55c4771225d24e1b04a3611227e06870a1b33d5544a30246f
-  data.tar.gz: 0619e36858b236585f330d5272aa90469481771445bb383086d1686026216fe066dc3bcaf2624fe6b55877072875a4a8ed5c8cc335f0015a5447e3b9329ccfe4
+  metadata.gz: 1e2a88587ff96a480845cee7a99b624b4ee86d373ac659ace2f89b1cd597fed87156c9ffb487ee37b7a87f81a225f0f86b0f47c17d45c4150a70b594638afbdc
+  data.tar.gz: b7634902c0e838a66e4852c62d1356d8cfeb9b9ab84b371a8cba654057fd2c440f8b14e1a92e14311c42670c9557ac3f51e2638d118abdf330de9d750417d7a0

data/.travis.yml

@@ -1,3 +1,4 @@
 rvm:
   - "1.9.3"
   - "2.0.0"
+  - "2.1.0"

data/.yardopts

@@ -2,7 +2,9 @@
 CHANGELOG.markdown
 MIT-LICENSE
 docs/Home.markdown
+docs/Publication.markdown
 docs/Item.markdown
 docs/FixedLayout.markdown
 docs/Epubinfo.markdown
 docs/EpubOpen.markdown
+docs/Navigation.markdown

data/CHANGELOG.markdown

@@ -1,5 +1,23 @@
 CHANGELOG
 =========
+0.1.6
+-----
+* Remove `EPUB.parse` method
+* Remove `EPUB::Publication::Package::Metadata#to_hash`
+* Add `EPUB::Publication::Package::Metadata::Identifier` for ad-hoc `scheme` attribute and `#isbn?` method
+* Remove `MethodDecorators::Deprecated`
+* Make `EPUB::Parser::OCF::CONTAINER_FILE` and other constants deprecated
+* Make `EPUB::Publication::Package::Metadata::Link#rel` a `Set`
+* Add exception class `EPUB::Constants::MediaType::UnsupportedMediaType`
+* Make `EPUB::Constants::MediaType::UnsupportedError` deprecated. Use `UnsupportedMediatType` instead
+* Add `EPUB::Publication::Package::Item#cover_image?`
+* Add `EPUB::Book::Features` module and move methods of `EPUB` module to it(Thanks, [takahashim][]!)
+* Make including `EPUB` deprecated
+* Parse `hidden` attribute of `nav` elements
+* [Experimental]Add `EPUB::ContentDocument::Navigation::Item#traverse`
+
+[takahashim]: https://github.com/takahashim
+
 0.1.5
 -----
 * Add `ContentDocument::XHTML#title`

data/README.markdown

@@ -1,6 +1,7 @@
 EPUB Parser
 ===========
 [![Build Status](https://secure.travis-ci.org/KitaitiMakoto/epub-parser.png?branch=master)](http://travis-ci.org/KitaitiMakoto/epub-parser)
+[![Dependency Status](https://gemnasium.com/KitaitiMakoto/epub-parser.png)](https://gemnasium.com/KitaitiMakoto/epub-parser)
 
 INSTALLATION
 -------
@@ -15,9 +16,12 @@ USAGE
     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.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
@@ -67,7 +71,7 @@ IRB starts. `self` becomes the EPUB book and can access to methods of `EPUB`.
     metadata.creators
     => [Author 1, Author2, ...]
     resources.first.properties
-    => ["nav"] # You know that first resource of this book is nav document
+    => #<Set: {"nav"}> # You know that first resource of this book is nav document
     nav = resources.first
     => ...
     nav.href
@@ -88,18 +92,47 @@ See {file:docs/EpubOpen} for more info.
 
 REQUIREMENTS
 ------------
-* Ruby 1.9.2 or later
+* Ruby 1.9.3 or later
 * C compiler to compile Zip/Ruby and Nokogiri
 
+Related Gems
+------------
+* [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://github.com/KitaitiMakoto/epub-maker) - This library supports making and editing EPUB books based on this EPUB Parser library
+
+If you find other gems, please tell me or request a pull request.
+
 RECENT CHANGES
 --------------
+### 0.1.6
+* Remove `EPUB.parse` method
+* Remove `EPUB::Publication::Package::Metadata#to_hash`
+* Add `EPUB::Publication::Package::Metadata::Identifier`
+* Remove `MethodDecorators::Deprecated`
+* Make `EPUB::Parser::OCF::CONTAINER_FILE` and other constants deprecated
+* Make `EPUB::Publication::Package::Metadata::Link#rel` a `Set`
+* Add exception class `EPUB::Constants::MediaType::UnsupportedMediaType`
+* Make `EPUB::Constants::MediaType::UnsupportedError` deprecated
+* Add `EPUB::Publication::Package::Item#find_item_by_relative_iri`
+* Add `EPUB::Publication::Package::Item#cover_image?`
+* Add `EPUB::Book::Features` module and move methods of `EPUB` module to it.(Thanks, [takahashim][]!)
+* Make including `EPUB` deprecated
+* Parse `hidden` attribute of `nav` elements
+* [Experimental]Add `EPUB::ContentDocument::Navigation::Item#traverse`
+
+[takahashim]: https://github.com/takahashim
+
 ### 0.1.5
 * Add `ContentDocument::XHTML#title`
 * Add `Manifest::Item#xhtml?`
 * Add `--words` and `--char` options to `epubinfo` command
 * API change: `OCF::Container::Rootfile#full_path` became Addressable::URI object rather than `String`
 * Add `ContentDocument::XHTML#rexml` and `#nokogiri`
-* Inspect more readbly
+* Inspect more readably
 
 ### 0.1.4
 * [Fixed-Layout Documents][fixed-layout] support
@@ -109,17 +142,12 @@ RECENT CHANGES
 
 [fixed-layout]: http://www.idpf.org/epub/fxl/
 
-### 0.1.3
-* Add a command-line tool `epub-open`
-* Add support for XHTML Navigation Document
-* Make `EPUB::Publication::Package::Metadata#to_hash` obsolete. Use `#to_h` instead
-* Add utility methods `EPUB#description`, `EPUB#date` and `EPUB#unique_identifier`
-
 See {file:CHANGELOG.markdown} for older changelogs and details.
 
 TODOS
 -----
-* Simple inspect for `epub-open` tool
+* EPUB 3.0.1
+* Multiple rootfiles
 * Help features for `epub-open` tool
 * Vocabulary Association Mechanisms
 * Implementing navigation document and so on
@@ -133,6 +161,7 @@ TODOS
 
 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)

data/bin/epub-open

@@ -19,7 +19,7 @@ EOB
 }.parse!
 
 $0 = File.basename($PROGRAM_NAME)
-include EPUB
+include EPUB::Book::Features
 EPUB::Parser.parse(ARGV.shift, :book => self)
 $stderr.puts "Enter \"exit\" to exit #{shell}"
 shell.start

data/bin/epubinfo

@@ -11,9 +11,7 @@ Usage: epubinfo [options] EPUBFILE
 EOB
   opt.version = EPUB::Parser::VERSION
   formats = [:line, :json, :yaml]
-  nl_formats = formats.dup
-  nl_last = nl_formats.pop
-  opt.on '-f', '--format=FORMAT', formats, "format of output(#{nl_formats.join(', ')} or #{nl_last}), defaults to line(for console)" do |format|
+  opt.on '-f', '--format=FORMAT', formats, "format of output(#{formats[0..-2].join(', ')} or #{formats.last}), defaults to line(for console)" do |format|
     options[:format] = format
   end
   opt.on '--words', 'count words of content documents' do
@@ -38,21 +36,23 @@ data.merge!(book.metadata.to_h)
 data['Unique identifier'] = [book.metadata.unique_identifier]
 data['EPUB Version'] = [book.package.version]
 counts = {:chars => 0, :words => 0}
-book.resources.select(&:xhtml?).each do |xhtml|
-  begin
-    doc = Nokogiri.XML(xhtml.read)
-    body = doc.search('body').first
-    content = body.content
-    if body
-      counts[:words] += content.scan(/\S+/).length
-      counts[:chars] += content.gsub(/\r|\n/, '').length
+if options[:words] or options[:chars]
+  book.resources.select(&:xhtml?).each do |xhtml|
+    begin
+      doc = xhtml.content_document.nokogiri
+      body = doc.search('body').first
+      content = body.content
+      if body
+        counts[:words] += content.scan(/\S+/).length
+        counts[:chars] += content.gsub(/\r|\n/, '').length
+      end
+    rescue => error
+      warn "#{xhtml.href}: #{error}"
     end
-  rescue => error
-    warn "#{xhtml.href}: #{error}"
   end
 end
 data['Words'] = [counts[:words]] if options[:words]
-data['Charactors'] = [counts[:chars]] if options[:chars]
+data['Characters'] = [counts[:chars]] if options[:chars]
 if options[:format] == :line
   key_width = data.keys.map {|k| k.length}.max + 3
   data.each_pair do |k, v|

data/docs/Home.markdown

@@ -61,7 +61,7 @@ By the way, although `book` above is a {EPUB::Book} object, all features are pro
     require 'epub'
     
     class YourBook < ActiveRecord::Base
-        include EPUB
+        include EPUB::Book::Features
     end
     
     book = EPUB::Parser.parse(
@@ -92,13 +92,14 @@ You are also able to find YourBook object for the first:
 
 More documentations are avaiable in:
 
+* {file:docs/Publication.markdown}
 * {file:docs/Item.markdown}
 * {file:docs/FixedLayout.markdown}
 
 Requirements
 ------------
 
-* libxml2 and libxslt for Nokogiri gem
+* Ruby 1.9.3 or later
 * C compiler to compile Zip/Ruby and Nokogiri
 
 Note

data/docs/Item.markdown

@@ -66,15 +66,15 @@ Also you can use {EPUB::Publication::Package::Manifest::Item#use_fallback_chain
 
 If item's media type is, for instance, 'image/x-eps', the fallback is used.
 If the fallback item's media type is 'image/png', `png` variable means the item, if not, "fallback of fallback" will be checked.
-Finally you can use the item you want, or {EPUB::Constants::MediaType::UnsupportedError EPUB::MediaType::UnsupportedError} exception will be raised(if no item you can accept found).
+Finally you can use the item you want, or {EPUB::Constants::MediaType::UnsupportedMediaType EPUB::MediaType::UnsupportedMediaType} exception will be raised(if no item you can accept found).
 Therefore, you should `rescue` clause:
 
     # :unsupported option can also be used
-    # fallback chain will be followed until EPUB's Core Media Types found or UnsupportedError raised
+    # fallback chain will be followed until EPUB's Core Media Types found or UnsupportedMediaType raised
     begin
       item.use_fallback_chain :unsupported => 'application/pdf' do |page|
         # do something with item with core media type
       end
-    rescue EPUB::MediaType::UnsupportedError => evar
+    rescue EPUB::MediaType::UnsupportedMediaType => evar
       # error handling
     end

data/docs/Navigation.markdown

@@ -0,0 +1,58 @@
+{file:docs/Home.markdown} > **{file:docs/Navigation.markdown}**
+
+Traversing
+==========
+
+Example to show tree of Table of Contents:
+
+    nav = book.manifest.navs.first.content_document # => EPUB::ContentDocument::Navigation
+    toc = nav.toc # => EPUB::ContentDocument::Navigation::Navigation
+    toc_tree = ''
+    toc.traverse do |item, depth|
+      item # => EPUB::ContentDocument::Navigation::Item
+      depth # => Integer
+      toc_tree << "#{' ' * depth * 2}#{item.text}\n"
+    end
+    puts toc_tree
+    THE CONTENTS
+      SECTION IV FAIRY STORIES—MODERN FANTASTIC TALES
+        BIBLIOGRAPHY
+        INTRODUCTORY
+        Abram S. Isaacs
+          190 A FOUR-LEAVED CLOVER
+            
+    												I. The Rabbi and the Diadem
+    											
+            
+    												II. Friendship
+    											
+            
+    												III. True Charity
+    											
+            
+    												IV. An Eastern Garden
+    											
+        Samuel Taylor Coleridge
+          191 THE LORD HELPETH MAN AND BEAST
+        Hans Christian Andersen
+          192 THE REAL PRINCESS
+          193 THE EMPEROR'S NEW CLOTHES
+          194 THE NIGHTINGALE
+          195 THE FIR TREE
+          196 THE TINDER-BOX
+          197 THE HARDY TIN SOLDIER
+          198 THE UGLY DUCKLING
+        Frances Browne
+          199 THE STORY OF FAIRYFOOT
+        Oscar Wilde
+          200 THE HAPPY PRINCE
+        Raymond MacDonald Alden
+          201 THE KNIGHTS OF THE SILVER SHIELD
+        Jean Ingelow
+          202 THE PRINCE'S DREAM
+        Frank R. Stockton
+          203 OLD PIPES AND THE DRYAD
+        John Ruskin
+          204 THE KING OF THE GOLDEN RIVER OR THE BLACK BROTHERS
+
+**NOTE**: This API is not stable.

data/docs/Publication.markdown

@@ -0,0 +1,54 @@
+{file:docs/Home.markdown} > **{file:docs/Publication.markdow}**
+
+Publication(Information about EPUB book)
+========================================
+
+EPUB Publications is information about EPUB books.
+
+EPUB Parser represents it as {EPUB::Publication} module and classes under the namespace and you can access them such like `EPUB::Parser.parse("path/to/book.epub").package`
+
+Let
+
+    book = EPUB::Parser.parse("path/to/book.epub")
+
+for continuing.
+
+Five Models
+-----------
+
+`book.package` is a package document, a root of information tree about the book, and it has attributes to access five major models of the publication; {EPUB::Publication::Package::Metadata Metadata}, {EPUB::Publication::Package::Manifest Manifest}, {EPUB::Publication::Package::Spine Spine}, {EPUB::Publication::Package::Guide Guide} and {EPUB::Publication::Package::Bindings Bindings}.
+
+Each of them has information the book in the way its own.
+
+Metadata
+--------
+
+{EPUB::Publication::Package::Metadata Metadata} is literally metadata of the book, including identifiers, titles, languages, links and so on.
+
+You can access them by:
+
+    md = book.package.metadata # => EPUB::Publication::Package::Metadata
+    md.titles # => [#<EPUB::Publication::Package::Metadata::Title...>, #<EPUB::Publication::Package::Metadata::Title...>, ...]
+    # ...
+
+Manifest
+--------
+
+Spine
+-----
+
+Guide
+-----
+
+Bindings
+--------
+
+Package
+-------
+
+References
+----------
+
+* [EPUB Publications 3.0][publications] on IDPF site
+
+[publications]: http://www.idpf.org/epub/30/spec/epub30-publications.html

data/epub-parser.gemspec

@@ -45,6 +45,5 @@ Gem::Specification.new do |s|
   s.add_runtime_dependency 'enumerabler'
   s.add_runtime_dependency 'zipruby'
   s.add_runtime_dependency 'nokogiri', '~> 1.6'
-  s.add_runtime_dependency 'addressable'
-  s.add_runtime_dependency 'method_decorators', '0.9.3'
+  s.add_runtime_dependency 'addressable', '>= 2.3.5'
 end

data/lib/epub.rb

@@ -1,92 +1,14 @@
-require 'method_decorators/deprecated'
 require 'epub/inspector'
 require 'epub/ocf'
 require 'epub/publication'
 require 'epub/content_document'
+require 'epub/book/features'
 
 module EPUB
-  modules = [ :ocf, :package, :content_document ]
-  attr_reader *modules
-  attr_accessor :epub_file
-  modules.each do |mod|
-    define_method "#{mod}=" do |obj|
-      instance_variable_set "@#{mod}", obj
-      obj.book = self
+  class << self
+    def included(base)
+      warn 'Including EPUB module is deprecated. Include EPUB::Book::Features instead.'
+      base.__send__ :include, EPUB::Book::Features
     end
   end
-
-  def parse(file, options = {})
-    @epub_file = file
-    options = options.merge({:book => self})
-    Parser.parse(file, options)
-  end
-
-  Publication::Package::CONTENT_MODELS.each do |model|
-    define_method model do
-      package.__send__(model)
-    end
-  end
-
-  %w[ title main_title subtitle short_title collection_title edition_title extended_title description date unique_identifier ].each do |met|
-    define_method met do
-      metadata.__send__(met)
-    end
-  end
-
-  %w[nav].each do |met|
-    define_method met do
-      manifest.__send__ met
-    end
-  end
-
-  # @overload each_page_on_spine(&blk)
-  #   iterate over items in order of spine when block given
-  #   @yieldparam item [Publication::Package::Manifest::Item]
-  # @overload each_page_on_spine
-  #   @return [Enumerator] which iterates over {Publication::Package::Manifest::Item}s in order of spine when block not given
-  def each_page_on_spine(&blk)
-    enum = package.spine.items
-    if block_given?
-      enum.each &blk
-    else
-      enum
-    end
-  end
-
-  def each_page_on_toc(&blk)
-    raise NotImplementedError
-  end
-
-  # @overload each_content(&blk)
-  #   iterate all items over when block given
-  #   @yieldparam item [Publication::Package::Manifest::Item]
-  # @overload each_content
-  #   @return [Enumerator] which iterates over all {Publication::Package::Manifest::Item}s in EPUB package when block not given
-  def each_content(&blk)
-    enum = manifest.items
-    if block_given?
-      enum.each &blk
-    else
-      enum.to_enum
-    end
-  end
-
-  def other_navigation
-    raise NotImplementedError
-  end
-
-  # @return [Array<Publication::Package::Manifest::Item>] All {Publication::Package::Manifest::Item}s in EPUB package
-  def resources
-    manifest.items
-  end
-
-  # Syntax sugar
-  def rootfile_path
-    ocf.container.rootfile.full_path.to_s
-  end
-
-  # Syntax sugar
-  def cover_image
-    manifest.cover_image
-  end
 end