epub-parser-io 0.1.6a

data/.gitignore

@@ -0,0 +1,12 @@
+*.gem
+.bundle
+Gemfile.lock
+pkg/*
+vendor/*
+.yardoc/
+coverage/*
+samples/*
+doc/*
+NOTE
+test/fixtures/book.epub
+*~

data/.gitmodules

@@ -0,0 +1,3 @@
+[submodule "wiki"]
+	path = wiki
+	url = git://github.com/KitaitiMakoto/epub-parser.wiki.git

data/.travis.yml

@@ -0,0 +1,4 @@
+rvm:
+  - "1.9.3"
+  - "2.0.0"
+  - "2.1.0"

data/.yardopts

@@ -0,0 +1,10 @@
+-
+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

@@ -0,0 +1,61 @@
+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`
+* Add `Manifest::Item#xhtml?`
+* Add `--words` and `--chars` options to `epubinfo` command which count words and charactors of XHTMLs in EPUB file
+* API change: `OCF::Container::Rootfile#full_path` became Addressable::URI object rather than `String`. `EPUB#rootfile_path` still returns `String`
+* Add `ContentDocument::XHTML#rexml` which returns document as `REXML::Document` object
+* Add `ContentDocument::XHTML#nokogiri` which returns document as `Nokogiri::XML::Document` object
+* Inspect more readbly
+
+0.1.4
+-----
+* [Fixed-Layout Documents][fixed-layout] support
+* Define `ContentDocument::XHTML#top_level?`
+* Define `Spine::Itemref#page_spread` and `#page_spread=`
+* Define some utility methods around `Manifest::Item` and `Spine::Itemref`
+  * `Manifest::Item#itemref`
+  * `Spine::Itemref#item=`
+
+[fixed-layout]: http://www.idpf.org/epub/fxl/
+
+0.1.3
+-----
+* Add `EPUB::Parser::Utils` module
+* 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`
+
+0.1.2
+-----
+* Fix a bug that `Item#read` couldn't read file when `href` is percent-encoded(Thanks, [gambhiro][]!)
+
+[gambhiro]: https://github.com/gambhiro
+
+0.1.1
+-----
+* Parse package@prefix and attach it as `Package#prefix`
+* `Manifest::Item#iri` was removed. It have existed for files in unzipped epub books but now EPUB Parser retrieves files from zip archive directly. `#href` now returns `Addressable::URI` object.
+* `Metadata::Link#iri`: ditto.
+* `Guide::Reference#iri`: ditto.

data/Gemfile

@@ -0,0 +1,2 @@
+source "https://rubygems.org"
+gemspec

data/MIT-LICENSE

@@ -0,0 +1,7 @@
+Copyright (c) 2011, 2012, 2013 KITAITIMAKOTO <KitaitiMakoto@gmail.com>
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.markdown

@@ -0,0 +1,174 @@
+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
+-------
+
+    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://rubydoc.info/gems/epub-parser/frames
+
+### `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} 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} for more info.
+
+REQUIREMENTS
+------------
+* 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 readably
+
+### 0.1.4
+* [Fixed-Layout Documents][fixed-layout] support
+* Define `ContentDocument::XHTML#top_level?`
+* Define `Spine::Itemref#page_spread` and `#page_spread=`
+* Define some utility methods around `Manifest::Item` and `Spine::Itemref`
+
+[fixed-layout]: http://www.idpf.org/epub/fxl/
+
+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
+* Media Overlays
+* Content Document
+* Digital Signature
+* 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)
+* 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)
+
+LICENSE
+-------
+This library is distribuetd under the term of the MIT License.
+See MIT-LICENSE file for more info.

data/Rakefile

@@ -0,0 +1,68 @@
+require 'bundler/gem_helper'
+require 'rake/clean'
+require 'rake/testtask'
+require 'yard'
+require 'rdoc/task'
+require 'cucumber'
+require 'cucumber/rake/task'
+require 'epub/parser/version'
+require 'zipruby'
+
+task :default => :test
+task :test => 'test:default'
+
+namespace :test do
+  task :default => [:build, :test]
+
+  desc 'Run all tests'
+  task :all => [:build, :test, :cucumber]
+
+  desc 'Build test fixture EPUB file'
+  task :build => :clean do
+    input_dir  = 'test/fixtures/book'
+    sh "epzip #{input_dir}"
+    small_file = File.read("#{input_dir}/OPS/case-sensitive.xhtml")
+    Zip::Archive.open "#{input_dir}.epub" do |archive|
+      archive.add_buffer 'OPS/CASE-SENSITIVE.xhtml', small_file.sub('small file name', 'LARGE FILE NAME')
+    end
+  end
+
+  Rake::TestTask.new do |task|
+    task.test_files = FileList['test/**/test_*.rb']
+    task.warning = true
+    task.options = '--no-show-detail-immediately --verbose'
+  end
+
+  Cucumber::Rake::Task.new
+end
+
+task :doc => 'doc:default'
+
+namespace :doc do
+  task :default => [:yard, :rdoc]
+
+  YARD::Rake::YardocTask.new
+  Rake::RDocTask.new do |rdoc|
+    rdoc.rdoc_files = FileList['lib/**/*.rb']
+    rdoc.rdoc_files.include 'README.markdown'
+    rdoc.rdoc_files.include 'MIT-LICENSE'
+    rdoc.rdoc_files.include 'docs/**/*.md'
+  end
+end
+
+namespace :gem do
+  desc "Build epub-parser-#{EPUB::Parser::VERSION}.gem into the pkg directory."
+  task :build do
+    Bundler::GemHelper.new.build_gem
+  end
+
+  desc "Build and install epub-parser-#{EPUB::Parser::VERSION}.gem into system gems."
+  task :install do
+    Bundler::GemHelper.new.install_gem
+  end
+
+  desc "Create tag v#{EPUB::Parser::VERSION} and build and push epub-parser-#{EPUB::Parser::VERSION}.gem to Rubygems"
+  task :release => :test do
+    Bundler::GemHelper.new.release_gem
+  end
+end

data/bin/epub-open

@@ -0,0 +1,25 @@
+require 'English'
+require 'optparse'
+require 'irb'
+require 'epub/parser'
+
+shell = IRB
+
+OptionParser.new {|opt|
+  opt.banner = <<EOB
+Open EPUB file in IRB
+
+Usage: #{File.basename($PROGRAM_NAME)} EPUBFILE
+
+EOB
+  opt.on '--pry', 'Use Pry instead of IRB as shell' do
+    require 'pry'
+    shell = Pry
+  end
+}.parse!
+
+$0 = File.basename($PROGRAM_NAME)
+include EPUB::Book::Features
+EPUB::Parser.parse(ARGV.shift, :book => self)
+$stderr.puts "Enter \"exit\" to exit #{shell}"
+shell.start

data/bin/epubinfo

@@ -0,0 +1,64 @@
+require 'optparse'
+require 'epub/parser'
+
+options = {:format => :line}
+opt = OptionParser.new do |opt|
+  opt.banner = <<EOB
+Show metadata of an EPUB file
+
+Usage: epubinfo [options] EPUBFILE
+
+EOB
+  opt.version = EPUB::Parser::VERSION
+  formats = [:line, :json, :yaml]
+  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
+    options[:words] = true
+  end
+  opt.on '--chars', 'count charactors of content documents' do
+    options[:chars] = true
+  end
+end
+opt.parse!(ARGV)
+
+file = ARGV.shift
+unless file
+  $stdout.puts "error: you must supply an EPUB file name"
+  $stdout.puts opt.help
+  abort
+end
+
+book = EPUB::Parser.parse(file)
+data = {'Title' => [book.title]}
+data.merge!(book.metadata.to_h)
+data['Unique identifier'] = [book.metadata.unique_identifier]
+data['EPUB Version'] = [book.package.version]
+counts = {:chars => 0, :words => 0}
+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
+  end
+end
+data['Words'] = [counts[:words]] if options[:words]
+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|
+    puts (k.to_s.capitalize + ':').ljust(key_width) + v.join(', ')
+  end
+else
+  require options[:format].to_s
+  puts data.__send__("to_#{options[:format]}")
+end