epub-parser 0.2.2 → 0.2.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 5064ac374ce37d6547455f140004939cc0fb6beb
-  data.tar.gz: 210f062f461f4ae37f84709953e1f1f029ddba44
+  metadata.gz: db9a8abb6d8ece39b51e5432c33caffdbd5efc65
+  data.tar.gz: bd9eb66c3af2ad86c1def37514c60db5d687a26d
 SHA512:
-  metadata.gz: 726184ddb137eaceed9774eb81bcf3ea36b9896495b247a115dbc89d12f628af2ccc7d0f8abb87baec30e8fa44c0bcd4f40b0175297f5e21922d7f3696c58628
-  data.tar.gz: 0d5c3e0d8a4afc8410088ef77daeb59d28f37caf1a349ddfd4eeeb693d0364dce61a19e3cc69c6d79032f51fc3b24c8b20fb5303f389aa6e6f975111edf983d9
+  metadata.gz: ab94d4c2c5104e966d6f2ed8368491189ca5a215a687bd6fdd2a43424b02935c44c36f8b14f39514858d2ad92c283e6ae7780041339f28f63dc283e1c8f72c30
+  data.tar.gz: 4d8c2f4f3a8dc584386cf55a4a6be890856c466b9ae1e7c2d6dfbe4cf31362730b1cbadf89c125910f9ab86ee27ccd7776fa099efefbeee4727698e140629cac

data/.gitignore

@@ -7,6 +7,8 @@ vendor/*
 coverage/*
 samples/*
 doc/*
+html/*
 NOTE
 test/fixtures/book.epub
 *~
+lib/epub/parser/cfi.tab.rb

data/.travis.yml

@@ -1,4 +1,4 @@
 rvm:
-  - "2.0.0"
-  - "2.1.0"
-  - "2.2.0"
+  - "2.1.8"
+  - "2.2.4"
+  - "2.3.0"

data/.yardopts

@@ -11,3 +11,4 @@ docs/Navigation.markdown
 docs/Searcher.markdown
 docs/UnpackedArchive.markdown
 docs/AggregateContentsFromWeb.markdown
+examples/aggregate-contents-from-web.rb

data/CHANGELOG.markdown

@@ -1,6 +1,18 @@
 CHANGELOG
 =========
 
+0.2.3
+-----
+
+* Change the name of physical container adapter for file system: :File -> :UnpackedDirectory
+* Add `EPUB::Publication::Package::Manifest::Item#full_path`
+* Make #href= acceptable String
+* Implement `EPUB::CFI` and `EPUB::Parser::CFI`
+* Remove [nokogumbo][] from dependencies. It ommits `head` and `body` elements
+* Remove Cucumber and Cucumber features
+* Add `EPUB::Publication::Package::Metadata#modified` and `EPUB::Book::Features#modified`
+* Add `EPUB::Book::Features#release_identifier`
+
 0.2.2
 -----
 

data/README.markdown

@@ -2,6 +2,7 @@ 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)
+[![Gem Version](https://badge.fury.io/rb/epub-parser.svg)](http://badge.fury.io/rb/epub-parser)
 
 INSTALLATION
 -------
@@ -95,7 +96,7 @@ DOCUMENTATION
 
 Documentation is available in [homepage][].
 
-If you installed EPUB Parser by gem command, you can also generate documentaiton by your own([rubygems-yardoc][] gem is needed):
+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
@@ -150,6 +151,19 @@ If you find other gems, please tell me or request a pull request.
 RECENT CHANGES
 --------------
 
+### 0.2.3
+
+* Change the name of physical container adapter for file system: :File -> :UnpackedDirectory
+* Add `EPUB::Publication::Package::Manifest::Item#full_path`
+* Make #href= acceptable String
+* Implement `EPUB::CFI` and `EPUB::Parser::CFI`
+* Remove [nokogumbo][] from dependencies. It ommits `head` and `body` elements
+* Remove Cucumber and Cucumber features
+* Add `EPUB::Publication::Package::Metadata#modified` and `EPUB::Book::Features#modified`
+* Add `EPUB::Book::Features#release_identifier`
+
+[nokogumbo]: https://github.com/rubys/nokogumbo/
+
 ### 0.2.2
 
 * [BUGFIX]Item#entry_name returns normalized IRI
@@ -167,16 +181,6 @@ RECENT CHANGES
 
 * Make it possible to parse file system directory as an EPUB file. See {file:docs/UnpackedArchive.markdown} for details.
 
-### 0.1.9
-
-* Introduce [Nokogumbo][] for XHTML Content Documents
-* Stop support for Ruby 1.9
-* Remove `EPUB.included` method. Now including `EPUB` module empowers nothing of EPUB features. Include `EPUB::Book::Features` instead.
-* Add `EPUB::Searcher::XHTML::Seamless` and make it default searcher
-* Add `EPUB::Publication::Package::Manifest#each_nav`
-
-[nokogumbo]: https://github.com/rubys/nokogumbo/
-
 See {file:CHANGELOG.markdown} for older changelogs and details.
 
 TODOS

data/Rakefile

@@ -3,22 +3,28 @@ require 'rake/clean'
 require 'rake/testtask'
 require 'yard'
 require 'rdoc/task'
-require 'cucumber'
-require 'cucumber/rake/task'
 require 'epub/parser/version'
 require 'zipruby'
 
+CFI_TAB = 'lib/epub/parser/cfi.tab.rb'
+CFI_Y =  'lib/epub/parser/cfi.y'
+CLEAN.include(CFI_TAB)
+
 task :default => :test
 task :test => 'test:default'
 
+file CFI_TAB do
+  sh "racc #{CFI_Y}"
+end
+
 namespace :test do
   task :default => [:build, :test]
 
   desc 'Run all tests'
-  task :all => [:build, :test, :cucumber]
+  task :all => [:build, :test]
 
   desc 'Build test fixture EPUB file'
-  task :build => :clean do
+  task :build => [:clean, CFI_TAB] do
     input_dir  = 'test/fixtures/book'
     sh "epzip #{input_dir}"
     small_file = File.read("#{input_dir}/OPS/case-sensitive.xhtml")
@@ -32,8 +38,6 @@ namespace :test do
     task.warning = true
     task.options = '--no-show-detail-immediately --verbose'
   end
-
-  Cucumber::Rake::Task.new
 end
 
 task :doc => 'doc:default'
@@ -52,4 +56,5 @@ end
 
 namespace :gem do
   Bundler::GemHelper.install_tasks
+  task :build => [:clean, CFI_TAB]
 end

data/bin/epub-open

@@ -21,7 +21,7 @@ EOB
 $0 = File.basename($PROGRAM_NAME)
 include EPUB::Book::Features
 file = ARGV.shift
-EPUB::OCF::PhysicalContainer.adapter = :File if File.directory? file
+EPUB::OCF::PhysicalContainer.adapter = :UnpackedDirectory if File.directory? file
 unless File.readable? file
   uri = URI.parse(file) rescue nil
   if uri

data/bin/epubinfo

@@ -30,7 +30,7 @@ unless file
   abort
 end
 
-EPUB::OCF::PhysicalContainer.adapter = :File if File.directory? file
+EPUB::OCF::PhysicalContainer.adapter = :UnpackedDirectory if File.directory? file
 unless File.readable? file
   uri = URI.parse(file) rescue nil
   if uri

data/docs/AggregateContentsFromWeb.markdown

@@ -21,7 +21,7 @@ EPUB Parser can treat the URI as EPUB book file path and parse contents from it
 The trick is to set {EPUB::OCF::PhysicalContainer.adapter container adapter} to {EPUB::OCF::PhysicalContainer::UnpackedURI :UnpackedURI}. It makes it possible to parse EPUB book from the web.
 Now we can play with EPUB books as always!
 
-As an example, I will show you a script to download all the files of specified EPUB book to local directory(source code is available in repository's examples/aggregate-contents-from-web.rb).
+As an example, I will show you a script to download all the files of specified EPUB book to local directory(source code is available in repository's {file:examples/aggregate-contents-from-web.rb}).
 
 {include:file:examples/aggregate-contents-from-web.rb}
 

data/docs/UnpackedArchive.markdown

@@ -45,7 +45,7 @@ To load EPUB books from directory, you need specify file adapter via {EPUB::OCF:
 
     require 'epub/parser'
     
-    EPUB::OCF::PhysicalContainer.adapter = :File
+    EPUB::OCF::PhysicalContainer.adapter = :UnpackedDirectory
 
 And then, directory path as EPUB path:
 
@@ -67,7 +67,7 @@ If set {EPUB::OCF::PhysicalContainer.adapter}, it is used every time EPUB Parser
     archived_book = EPUB::Parser.parse('./page-blanche.epub') # => EPUB::Book
     # From directory
     File.ftype './page-blanche' # => "directory"
-    unpacked_book = EPUB::Parser.parse('./page-blanche', container_adapter: :File) # => EPUB::Book
+    unpacked_book = EPUB::Parser.parse('./page-blanche', container_adapter: :UnpackedDirectory) # => EPUB::Book
 
 Command-line tools
 ------------------

data/epub-parser.gemspec

@@ -14,6 +14,7 @@ Gem::Specification.new do |s|
   s.required_ruby_version = '> 2'
 
   s.files         = `git ls-files`.split("\n")
+                    .push('lib/epub/parser/cfi.tab.rb')
                     .push('test/fixtures/book/OPS/ルートファイル.opf')
                     .push('test/fixtures/book/OPS/日本語.xhtml')
                     .push(Dir['docs/*.md'])
@@ -37,11 +38,11 @@ Gem::Specification.new do |s|
   s.add_development_dependency 'gem-man'
   s.add_development_dependency 'ronn'
   s.add_development_dependency 'epzip'
-  s.add_development_dependency 'aruba'
+  s.add_development_dependency 'racc'
+  s.add_development_dependency 'nokogiri-diff'
 
   s.add_runtime_dependency 'zipruby'
   s.add_runtime_dependency 'nokogiri', '~> 1.6'
-  s.add_runtime_dependency 'nokogumbo'
   s.add_runtime_dependency 'addressable', '>= 2.3.5'
   s.add_runtime_dependency 'rchardet', '>= 1.6.1'
 end

data/lib/epub/book/features.rb

@@ -17,7 +17,7 @@ module EPUB
         end
       end
 
-      %w[title main_title subtitle short_title collection_title edition_title extended_title description date unique_identifier].each do |met|
+      %w[title main_title subtitle short_title collection_title edition_title extended_title description date unique_identifier modified].each do |met|
         define_method met do
           metadata.__send__(met)
         end
@@ -29,6 +29,10 @@ module EPUB
         end
       end
 
+      def release_identifier
+        "#{unique_identifier}@#{modified}"
+      end
+
       def container_adapter
         @adapter || OCF::PhysicalContainer.adapter
       end

data/lib/epub/cfi.rb

@@ -0,0 +1,301 @@
+module EPUB
+  module CFI
+    SPECIAL_CHARS = '^[](),;=' # "5E", "5B", "5D", "28", "29", "2C", "3B", "3D"
+    RE_ESCAPED_SPECIAL_CHARS = Regexp.escape(SPECIAL_CHARS)
+
+    class << self
+      def escape(string)
+        string.gsub(/([#{RE_ESCAPED_SPECIAL_CHARS}])/o, '^\1')
+      end
+
+      def unescape(string)
+        string.gsub(/\^([#{RE_ESCAPED_SPECIAL_CHARS}])/o, '\1')
+      end
+    end
+
+    class Location
+      attr_reader :paths
+
+      def initialize(paths=[])
+        @paths = paths
+      end
+
+      def initialize_copy(original)
+        @paths = original.paths.collect(&:dup)
+      end
+
+      def type
+        @paths.last.type
+      end
+
+      def <=>(other)
+        index = 0
+        other_paths = other.paths
+        cmp = nil
+        paths.each do |path|
+          other_path = other_paths[index]
+          return 1 unless other_path
+          cmp = path <=> other_path
+          break unless cmp == 0
+          index += 1
+        end
+
+        unless cmp == 0
+          if cmp == 1 and other_paths[index + 1]
+            return nil
+          else
+            return cmp
+          end
+        end
+
+        return nil if paths.last.offset && other_paths[index]
+
+        return -1 if other_paths[index]
+
+        0
+      end
+
+      def to_s
+        paths.join('!')
+      end
+
+      def to_fragment
+       "epubcfi(#{self})"
+      end
+
+      def join(*other_paths)
+        new_paths = paths.dup
+        other_paths.each do |path|
+          new_paths << path
+        end
+        self.class.new(new_paths)
+      end
+    end
+
+    class Path
+      attr_reader :steps, :offset
+
+      def initialize(steps=[], offset=nil)
+        @steps, @offset = steps, offset
+      end
+
+      def initialize_copy(original)
+        @steps = original.steps.collect(&:dup)
+        @offset = original.offset.dup if original.offset
+      end
+
+      def to_s
+        @string_cache ||= (steps.join + offset.to_s).freeze
+      end
+
+      def to_fragment
+        @fragment_cache ||= "epubcfi(#{self})".freeze
+      end
+
+      def <=>(other)
+        other_steps = other.steps
+        index = 0
+        steps.each do |step|
+          other_step = other_steps[index]
+          return 1 unless other_step
+          cmp = step <=> other_step
+          return cmp unless cmp == 0
+          index += 1
+        end
+
+        return -1 if other_steps[index]
+
+        other_offset = other.offset
+        if offset
+          if other_offset
+            offset <=> other_offset
+          else
+            1
+          end
+        else
+          if other_offset
+            -1
+          else
+            0
+          end
+        end
+      end
+
+      def each_step_with_instruction
+        yield [step, nil]
+        local_path.each_step_with_instruction do |s, instruction|
+          yield [s, instruction]
+        end
+        self
+      end
+    end
+
+    class Range < ::Range
+      attr_accessor :parent, :start, :end
+
+      # @todo consider the case subpaths are redirected path
+      # @todo FIXME: too dirty
+      class << self
+        def from_parent_and_start_and_end(parent_path, start_subpath, end_subpath)
+          start_str = start_subpath.join
+          end_str = end_subpath.join
+
+          first_paths = parent_path.collect(&:dup)
+          if start_subpath
+            offset_of_first = start_subpath.last.offset
+            offset_of_first = offset_of_first.dup if offset_of_first
+            last_of_first_paths = first_paths.pop
+            first_paths << last_of_first_paths
+            last_of_first_paths.steps.concat start_subpath.shift.steps
+            first_paths.concat start_subpath
+            first_paths.last.instance_variable_set :@offset, offset_of_first
+          end
+          offset_of_last = end_subpath.last.offset
+          offset_of_last = offset_of_last.dup if offset_of_last
+          last_paths = parent_path.collect(&:dup)
+          last_of_last_paths = last_paths.pop
+          last_paths << last_of_last_paths
+          last_of_last_paths.steps.concat end_subpath.shift.steps
+          last_paths.concat end_subpath
+          last_paths.last.instance_variable_set :@offset, offset_of_last
+
+          first = CFI::Location.new(first_paths)
+          last = CFI::Location.new(last_paths)
+
+          new_range = new(first, last)
+
+          new_range.parent = Location.new(parent_path)
+          new_range.start = start_str
+          new_range.end = end_str
+
+          new_range
+        end
+      end
+
+      def to_s
+        @string_cache ||= (first.to_fragment + (exclude_end? ? '...' : '..') + last.to_fragment).freeze
+      end
+
+      def to_fragment
+        @fragment_cache ||= "epubcfi(#{@parent},#{@start},#{@end})".freeze
+      end
+    end
+
+    class Step
+      attr_reader :step, :assertion
+
+      def initialize(step, assertion=nil)
+        @step, @assertion = step, assertion
+        @string_cache = nil
+      end
+
+      def initialize_copy(original)
+        @step = original.step
+        @assertion = original.assertion.dup if original.assertion
+      end
+
+      def to_s
+        @string_cache ||= "/#{step}#{assertion}".freeze # need escape?
+      end
+
+      def <=>(other)
+        step <=> other.step
+      end
+    end
+
+    class IDAssertion
+      attr_reader :id, :parameters
+
+      def initialize(id, parameters={})
+        @id, @parameters = id, parameters
+        @string_cache = nil
+      end
+
+      def to_s
+        return @string_cache if @string_cache
+        @string_cache = '['
+        @string_cache << CFI.escape(id) if id
+        parameters.each_pair do |key, values|
+          value = values.join(',')
+          @string_cache << ";#{CFI.escape(key)}=#{CFI.escape(value)}"
+        end
+        @string_cache << ']'
+        @string_cache.freeze
+      end
+    end
+
+    class TextLocationAssertion
+      attr_reader :preceded, :followed, :parameters
+
+      def initialize(preceded=nil, followed=nil, parameters={})
+        @preceded, @followed, @parameters = preceded, followed, parameters
+        @string_cache = nil
+      end
+
+      def to_s
+        return @string_cache if @string_cache
+        @string_cache = '['
+        @string_cache << CFI.escape(preceded) if preceded
+        @string_cache << ',' << CFI.escape(followed) if followed
+        parameters.each_pair do |key, values|
+          value = values.join(',')
+          @string_cache << ";#{CFI.escape(key)}=#{CFI.escape(value)}"
+        end
+        @string_cache << ']'
+        @string_cache.freeze
+      end
+    end
+
+    class CharacterOffset
+      attr_reader :offset, :assertion
+
+      def initialize(offset, assertion=nil)
+        @offset, @assertion = offset, assertion
+        @string_cache = nil
+      end
+
+      def to_s
+        @string_cache ||= ":#{offset}#{assertion}".freeze # need escape?
+      end
+
+      def <=>(other)
+        offset <=> other.offset
+      end
+    end
+
+    class TemporalSpatialOffset
+      attr_reader :temporal, :x, :y, :assertion
+
+      def initialize(temporal=nil, x=nil, y=nil, assertion=nil)
+        raise RangeError, "dimension must be in 0..100 but passed #{x}" unless (0.0..100.0).cover?(x) if x
+        raise RangeError, "dimension must be in 0..100 but passed #{y}" unless (0.0..100.0).cover?(y) if y
+        warn "Assertion is passed to #{__class__} but cannot know how to handle with it: #{assertion}" if assertion
+        @temporal, @x, @y, @assertion = temporal, x, y, assertion
+        @string_cache
+      end
+
+      def to_s
+        return @string_cache if @string_cache
+        @string_cache = ''
+        @string_cache << "~#{temporal}" if temporal
+        @string_cache << "@#{x}:#{y}" if x or y
+        @string_cache.freeze
+      end
+
+      # @note should split the class to spatial offset and temporal-spatial offset?
+      def <=>(other)
+        return -1 if temporal.nil? and other.temporal
+        return 1 if temporal and other.temporal.nil?
+        cmp = temporal <=> other.temporal
+        return cmp unless cmp == 0
+        return -1 if y.nil? and other.y
+        return 1 if y and other.y.nil?
+        cmp = y <=> other.y
+        return cmp unless cmp == 0
+        return -1 if x.nil? and other.x
+        return 1 if x and other.x.nil?
+        cmp = x <=> other.x
+      end
+    end
+  end
+end