All Files ( 94.65% covered at 121.75 hits/line )
43 files in total.
1459 relevant lines,
1381 lines covered and
78 lines missed.
(
94.65%
)
-
1
require 'epub/inspector'
-
1
require 'epub/ocf'
-
1
require 'epub/publication'
-
1
require 'epub/content_document'
-
1
require 'epub/book/features'
-
1
require 'epub'
-
-
1
module EPUB
-
1
class Book
-
1
include EPUB::Book::Features
-
end
-
end
-
1
require 'forwardable'
-
-
1
module EPUB
-
1
class Book
-
1
module Features
-
1
extend Forwardable
-
1
attr_reader :ocf
-
1
attr_accessor :epub_file
-
-
# When writing, sets +ocf.book+ to self.
-
# @param [OCF]
-
1
def ocf=(mod)
-
27
@ocf = mod
-
27
mod.book = self
-
27
mod
-
end
-
-
# @return [Array<OCF::Container::Rootfile>]
-
1
def rootfiles
-
105
ocf.container.rootfiles
-
end
-
-
# @return [Array<Publication::Package>]
-
1
def packages
-
105
rootfiles.map(&:package)
-
end
-
1
alias renditions packages
-
-
# First +package+ in +packages+
-
# @return [Package|nil]
-
1
def default_rendition
-
21
packages.first
-
end
-
1
alias package default_rendition
-
-
# @!parse def_delegators :package, :metadata, :manifest, :spine, :guide, :bindings
-
1
def_delegators :package, *Publication::Package::CONTENT_MODELS
-
1
def_delegators :metadata, :title, :main_title, :subtitle, :short_title, :collection_title, :edition_title, :extended_title, :description, :date, :unique_identifier, :modified, :release_identifier, :package_identifier
-
1
def_delegators :manifest, :nav
-
-
1
def container_adapter
-
43
@adapter || OCF::PhysicalContainer.adapter
-
end
-
-
1
def container_adapter=(adapter)
-
2
@adapter = OCF::PhysicalContainer.find_adapter(adapter)
-
end
-
-
# Cover image defined in EPUB 3 or used in EPUB 2
-
# @return [EPUB::Publication::Package::Manifest::Item]
-
1
def cover_image
-
manifest.cover_image || metadata.cover_image
-
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
-
1
def each_page_on_spine(&blk)
-
3
enum = package.spine.items
-
3
if block_given?
-
1
enum.each &blk
-
else
-
2
enum.each
-
end
-
end
-
-
1
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
-
1
def each_content(&blk)
-
3
enum = manifest.items
-
3
if block_given?
-
1
enum.each &blk
-
else
-
2
enum.to_enum
-
end
-
end
-
-
1
def other_navigation
-
raise NotImplementedError
-
end
-
-
# @return [Array<Publication::Package::Manifest::Item>] All {Publication::Package::Manifest::Item}s in EPUB package
-
1
def resources
-
manifest.items
-
end
-
-
# Syntax sugar
-
# @return String
-
1
def rootfile_path
-
ocf.container.rootfile.full_path.to_s
-
end
-
end
-
end
-
end
-
1
module EPUB
-
NAMESPACES = {
-
1
'xml' => 'http://www.w3.org/XML/1998/namespace',
-
'dc' => 'http://purl.org/dc/elements/1.1/',
-
'ocf' => 'urn:oasis:names:tc:opendocument:xmlns:container',
-
'opf' => 'http://www.idpf.org/2007/opf',
-
'xhtml' => 'http://www.w3.org/1999/xhtml',
-
'epub' => 'http://www.idpf.org/2007/ops',
-
'm' => 'http://www.w3.org/1998/Math/MathML',
-
'svg' => 'http://www.w3.org/2000/svg',
-
'smil' => 'http://www.w3.org/ns/SMIL',
-
'metadata' => 'http://www.idpf.org/2013/metadata'
-
}
-
-
1
module MediaType
-
1
class UnsupportedMediaType < StandardError; end
-
-
1
EPUB = 'application/epub+zip'
-
1
ROOTFILE = 'application/oebps-package+xml'
-
IMAGE = %w[
-
1
image/gif
-
image/jpeg
-
image/png
-
image/svg+xml
-
]
-
APPLICATION = %w[
-
1
application/xhtml+xml
-
application/x-dtbncx+xml
-
application/vnd.ms-opentype
-
application/font-woff
-
application/smil+xml
-
application/pls+xml
-
]
-
AUDIO = %w[
-
1
audio/mpeg
-
audio/mp4
-
]
-
TEXT = %w[
-
1
text/css
-
text/javascript
-
]
-
1
CORE = IMAGE + APPLICATION + AUDIO + TEXT
-
end
-
-
# @see https://idpf.github.io/epub-vocabs/structure/
-
1
module Type
-
DOCUMENT_NAVIGATION = %w[
-
1
toc
-
landmarks
-
]
-
PAGINATION = %w[
-
1
pagebreak
-
page_list
-
]
-
1
TYPES = DOCUMENT_NAVIGATION + PAGINATION
-
end
-
end
-
1
require 'epub/content_document/xhtml'
-
1
require 'epub/content_document/navigation'
-
1
require "epub/content_document/typable"
-
-
1
module EPUB
-
1
module ContentDocument
-
1
class Navigation < XHTML
-
1
include Typable
-
-
1
attr_accessor :navigations
-
-
1
def initialize
-
12
@navigations = []
-
12
@hidden = false
-
12
@parent = nil
-
12
super
-
end
-
-
1
def toc
-
2
navigations.find(&:toc?)
-
end
-
-
1
def page_list
-
navigations.find(&:page_list?)
-
end
-
-
1
def landmarks
-
1
navigations.find(&:landmarks?)
-
end
-
-
# Enumerator version of toc
-
1
def contents
-
1
enum_for(:each_content).to_a
-
end
-
-
# Enumerator version of page_list
-
# Usage: navigation.enum_for(:pages)
-
1
def pages
-
raise NotImplementedError
-
end
-
-
# @todo Enumerator version of landmarks
-
-
# iterator for #toc
-
1
def each_content
-
1
toc.traverse do |content, _|
-
7
yield content
-
end
-
end
-
-
# iterator for #page_list
-
1
def each_page
-
raise NotImplementedError
-
end
-
-
# iterator for #landmark
-
1
def each_landmark
-
raise NotImplementedError
-
end
-
-
1
def navigation
-
2
navigations.first
-
end
-
-
1
module Hidable
-
1
attr_accessor :hidden, :parent
-
-
1
def hidden?
-
8
if @hidden.nil?
-
4
@parent ? @parent.hidden? : false
-
else
-
4
true
-
end
-
end
-
end
-
-
1
class Item
-
1
include Hidable
-
1
include Typable
-
-
1
attr_accessor :items, :text,
-
:content_document, :item
-
1
attr_reader :href
-
-
1
def initialize
-
112
@items = ItemList.new
-
112
@items.parent = self
-
end
-
-
1
def href=(iri)
-
72
@href = iri.kind_of?(Addressable::URI) ? iri : Addressable::URI.parse(iri)
-
end
-
-
1
def traverse(depth=0, &block)
-
10
block.call self, depth
-
10
items.each do |item|
-
8
item.traverse depth + 1, &block
-
end
-
end
-
-
# For backward compatibility
-
1
def type
-
8
types.find {|t|
-
8
Type::TYPES.include? t
-
}
-
end
-
-
# For backward compatibility
-
1
def type=(t)
-
1
types << t
-
end
-
-
1
%w[toc page_list landmarks].each do |type|
-
3
define_method "#{type}?" do
-
4
types.include? type
-
end
-
end
-
end
-
-
# @todo Implement method to represent navigation structure
-
1
class Navigation < Item
-
1
module Type
-
1
TOC = 'toc'
-
1
PAGE_LIST = 'page_list'
-
1
LANDMARKS = 'landmarks'
-
end
-
-
1
alias navigations items
-
1
alias navigations= items=
-
1
alias heading text
-
1
alias heading= text=
-
end
-
-
1
class ItemList < Array
-
1
include Hidable
-
-
1
def <<(item)
-
45
super
-
45
item.parent = self
-
end
-
end
-
end
-
end
-
end
-
1
require "set"
-
-
1
module EPUB
-
1
module ContentDocument
-
1
module Typable
-
1
attr_reader :types
-
-
1
def types
-
16
@types ||= Set.new
-
end
-
-
1
def types=(ts)
-
104
@types = ts.kind_of?(Set) ? ts : Set.new(ts)
-
end
-
end
-
end
-
end
-
1
module EPUB
-
1
module ContentDocument
-
1
class XHTML
-
1
attr_accessor :item
-
-
# @param [Boolean] detect_encoding See {Publication::Package::Manifest::Item#read}
-
# @return [String] Returns the content string.
-
1
def read(detect_encoding: true)
-
10
item.read(detect_encoding: detect_encoding)
-
end
-
1
alias raw_document read
-
-
# @return [true|false] Whether referenced directly from spine or not.
-
1
def top_level?
-
2
!! item.itemref
-
end
-
-
# @return [String] Returns the value of title element.
-
# If none, returns empty string
-
1
def title
-
2
title_elem = rexml.get_elements('.//title').first
-
2
if title_elem
-
1
title_elem.text
-
else
-
1
warn 'title element not found'
-
1
''
-
end
-
end
-
-
# @return [REXML::Document] content as REXML::Document object
-
1
def rexml
-
3
@rexml ||= REXML::Document.new(raw_document)
-
end
-
-
# @return [Oga::XML::Document] content as Oga::XML::Document object
-
1
def oga
-
require "oga"
-
@oga ||= Oga.parse_xml(raw_document)
-
end
-
-
# @return [Nokogiri::XML::Document] content as Nokogiri::XML::Document object
-
1
def nokogiri
-
3
require 'nokogiri'
-
3
@nokogiri ||= Nokogiri.XML(raw_document)
-
end
-
end
-
end
-
end
-
1
module EPUB
-
1
module Inspector
-
1
INSTANCE_VARIABLES_OPTION = {:exclude => []}
-
1
SIMPLE_TEMPLATE = "#<%{class}:%{object_id}>"
-
-
1
def inspect_simply
-
5
SIMPLE_TEMPLATE % {
-
:class => self.class,
-
:object_id => inspect_object_id
-
}
-
end
-
-
1
def inspect_object_id
-
13
(__id__ << 1).to_s(16)
-
end
-
-
1
def inspect_instance_variables(options={})
-
8
options = INSTANCE_VARIABLES_OPTION.merge(options)
-
8
exclude = options[:exclude]
-
-
8
(instance_variables - exclude).map {|name|
-
45
value = instance_variable_get(name)
-
45
"#{name}=#{value.inspect}"
-
}.join(' ')
-
end
-
-
1
module PublicationModel
-
1
class << self
-
1
def included(mod)
-
5
mod.__send__ :include, Inspector
-
end
-
end
-
-
1
def inspect
-
3
template % {
-
:class => self.class,
-
3
:package => (package && package.inspect_simply),
-
:object_id => inspect_object_id,
-
:attributes => inspect_instance_variables(exclude: [:@package])
-
}
-
end
-
-
1
def template
-
3
t = "#<%{class}:%{object_id}"
-
3
t << " @package=%{package}" if package
-
3
t << " %{attributes}>"
-
end
-
end
-
end
-
end
-
1
require 'set'
-
-
1
module EPUB
-
1
class Metadata
-
1
include Inspector::PublicationModel
-
-
1
DC_ELEMS = [:identifiers, :titles, :languages] +
-
[:contributors, :coverages, :creators, :dates, :descriptions, :formats, :publishers,
-
:relations, :rights, :sources, :subjects, :types]
-
# Used for CFI
-
1
attr_reader :children
-
1
attr_accessor :package, :unique_identifier, :metas, :links,
-
16
*(DC_ELEMS.collect {|elem| "dc_#{elem}"})
-
1
DC_ELEMS.each do |elem|
-
15
alias_method elem, "dc_#{elem}"
-
15
alias_method "#{elem}=", "dc_#{elem}="
-
end
-
-
1
def initialize
-
171
(DC_ELEMS + [:metas, :links]).each do |elem|
-
2907
__send__ "#{elem}=", []
-
end
-
171
@children = []
-
end
-
-
1
def release_identifier
-
1
"#{unique_identifier}@#{modified}"
-
end
-
1
alias package_identifier release_identifier
-
-
1
def title
-
4
return extended_title unless extended_title.empty?
-
6
compositted = titles.select {|title| title.display_seq}.sort.join("\n")
-
2
return compositted unless compositted.empty?
-
1
return main_title unless main_title.empty?
-
titles.sort.join("\n")
-
end
-
-
1
%w[main short collection edition extended].each do |type|
-
5
define_method "#{type}_title" do
-
42
titles.select {|title| title.title_type.to_s == type}.sort.join(' ')
-
end
-
end
-
-
1
def subtitle
-
titles.select {|title| title.title_type.to_s == 'subtitle'}.sort.join(' ')
-
end
-
-
1
def description
-
descriptions.join(' ')
-
end
-
-
1
def date
-
dates.first
-
end
-
-
1
def language
-
languages.first
-
end
-
-
1
def modified
-
4
metas.find {|meta|
-
7
meta.property == 'dcterms:modified' &&
-
meta.refiners.empty?
-
}
-
end
-
-
# Cover image used in EPUB 2
-
# @return [EPUB::Publication::Package::Manifest::Item]
-
1
def cover_image
-
cover_image_meta = metas.find {|meta| meta.name == "cover"}
-
return unless cover_image_meta
-
package.manifest[cover_image_meta.meta_content]
-
end
-
-
1
def to_h
-
DC_ELEMS.inject({}) do |hsh, elem|
-
hsh[elem] = __send__(elem)
-
hsh
-
end
-
end
-
-
1
def primary_metas
-
metas.select {|meta| meta.primary_expression?}
-
end
-
-
1
module Refinee
-
1
PROPERTIES = %w[alternate-script display-seq file-as group-position identifier-type meta-auth role title-type]
-
-
1
attr_writer :refiners
-
-
1
def refiners
-
848
@refiners ||= Set.new
-
end
-
-
1
PROPERTIES.each do |voc|
-
8
met = voc.gsub(/-/, '_')
-
8
attr_writer met
-
8
define_method met do
-
128
refiners.find {|refiner| refiner.property == voc}
-
end
-
end
-
end
-
-
1
class DCMES
-
1
include Refinee
-
-
1
attr_accessor :content, :id, :lang, :dir
-
-
1
def to_s
-
13
content.to_s
-
end
-
end
-
-
1
class Identifier < DCMES
-
# @note This is ad-hoc
-
# @todo Define and include OPF module for opf:scheme attribute
-
# @todo Define general way to handle with identifier-type refiners
-
1
attr_accessor :scheme
-
-
# @note This is ad-hoc
-
# @todo Define and include OPF module for opf:scheme attribute
-
# @todo Define general way to handle with identifier-type refiners
-
1
def isbn?
-
5
scheme == 'ISBN' or
-
content.to_s.downcase.start_with? 'urn:isbn' or
-
refiners.any? {|refiner|
-
2
refiner.property == 'identifier-type' and
-
refiner.scheme == 'onix:codelist5' and
-
%w[02 15].include? refiner.content
-
}
-
end
-
end
-
-
1
class Title < DCMES
-
1
include Comparable
-
-
1
def <=>(other)
-
5
return 1 if other.display_seq.nil?
-
4
return -1 if display_seq.nil?
-
4
display_seq.to_s.to_i <=> other.display_seq.to_s.to_i
-
end
-
end
-
-
1
class Meta
-
1
include Refinee
-
-
1
attr_accessor :property, :id, :scheme, :content, :name, :meta_content
-
1
attr_reader :refines
-
-
1
def refines=(refinee)
-
740
refinee.refiners << self
-
740
@refines = refinee
-
end
-
-
1
def refines?
-
2
! refines.nil?
-
end
-
1
alias subexpression? refines?
-
-
1
def primary_expression?
-
1
! subexpression?
-
end
-
-
1
def inspect
-
5
ivs = instance_variables.map {|iv|
-
8
[iv, instance_variable_get(iv).inspect].join('=')
-
}.join(' ')
-
5
'<#%s:%#0x %s>' % [self.class, __id__, ivs]
-
end
-
-
1
def to_s
-
41
content.to_s
-
end
-
end
-
-
1
class Link
-
1
include Refinee
-
-
1
attr_accessor :href, :rel, :id, :media_type
-
1
attr_reader :refines
-
-
1
def refines=(refinee)
-
45
refinee.refiners << self
-
45
@refines = refinee
-
end
-
end
-
-
1
class UnsupportedModel
-
1
attr_accessor :raw_element
-
-
1
def initialize(raw_element)
-
@raw_element = raw_element
-
end
-
end
-
end
-
end
-
1
module EPUB
-
1
class OCF
-
1
MODULES = %w[container encryption manifest metadata rights signatures]
-
7
MODULES.each {|m| require "epub/ocf/#{m}"}
-
-
1
attr_accessor :book, *MODULES
-
end
-
end
-
1
module EPUB
-
1
class OCF
-
1
class Container
-
1
FILE = 'container.xml'
-
-
1
attr_reader :rootfiles
-
-
1
def initialize
-
34
@rootfiles = []
-
end
-
-
# syntax sugar
-
1
def rootfile
-
1
rootfiles.first
-
end
-
-
1
class Rootfile
-
1
attr_accessor :full_path, :media_type,
-
:package
-
-
# @param full_path [Addressable::URI|nil]
-
# @param media_type [String]
-
1
def initialize(full_path=nil, media_type=EPUB::MediaType::ROOTFILE)
-
100
@full_path, @media_type = full_path, media_type
-
end
-
end
-
end
-
end
-
end
-
1
module EPUB
-
1
class OCF
-
1
class Encryption
-
1
attr_accessor :content
-
end
-
end
-
end
-
1
module EPUB
-
1
class OCF
-
1
class Manifest
-
end
-
end
-
end
-
1
module EPUB
-
1
class OCF
-
1
class UnknownFormatMetadata
-
1
attr_accessor :content
-
end
-
end
-
end
-
1
require 'monitor'
-
1
require 'epub/ocf/physical_container/archive_zip'
-
1
require 'epub/ocf/physical_container/unpacked_directory'
-
1
require 'epub/ocf/physical_container/unpacked_uri'
-
-
1
module EPUB
-
1
class OCF
-
1
class PhysicalContainer
-
1
class NoEntry < StandardError
-
1
class << self
-
1
def from_error(error)
-
8
no_entry = new(error.message)
-
8
no_entry.set_backtrace error.backtrace
-
8
no_entry
-
end
-
end
-
end
-
-
1
@adapter = ArchiveZip
-
-
1
class << self
-
1
def find_adapter(adapter)
-
6
return adapter if adapter.instance_of? Class
-
3
if adapter == :Zipruby && ! const_defined?(adapter)
-
require 'epub/ocf/physical_container/zipruby'
-
end
-
3
const_get adapter
-
end
-
-
1
def adapter
-
71
raise NoMethodError, "undefined method `#{__method__}' for #{self}" unless self == PhysicalContainer
-
71
@adapter
-
end
-
-
1
def adapter=(adapter)
-
4
raise NoMethodError, "undefined method `#{__method__}' for #{self}" unless self == PhysicalContainer
-
4
@adapter = find_adapter(adapter)
-
end
-
-
1
def open(container_path)
-
56
_adapter.new(container_path).open do |container|
-
56
yield container
-
end
-
end
-
-
1
def read(container_path, path_name)
-
20
open(container_path) {|container|
-
20
container.read(path_name.to_s)
-
}
-
end
-
-
1
private
-
-
1
def _adapter
-
56
(self == PhysicalContainer) ? @adapter : self
-
end
-
end
-
-
1
def initialize(container_path)
-
71
@container_path = container_path
-
71
@monitor = Monitor.new
-
end
-
end
-
end
-
end
-
1
require 'archive/zip'
-
-
1
module EPUB
-
1
class OCF
-
1
class PhysicalContainer
-
1
class ArchiveZip < self
-
1
def initialize(container_path)
-
52
super
-
52
@entries = {}
-
52
@last_iterated_entry_index = 0
-
end
-
-
1
def open
-
56
Archive::Zip.open @container_path do |archive|
-
56
@monitor.synchronize do
-
56
@archive = archive
-
begin
-
56
yield self
-
ensure
-
56
@archive = nil
-
end
-
end
-
end
-
end
-
-
1
def read(path_name)
-
256
if @archive
-
250
target_index = @entries[path_name]
-
250
@archive.each.with_index do |entry, index|
-
3814
if target_index
-
1054
if target_index == index
-
102
return entry.file_data.read
-
else
-
952
next
-
end
-
end
-
2760
next if index < @last_iterated_entry_index
-
# We can force encoding UTF-8 because EPUB spec allows only UTF-8 filenames
-
836
entry_path = entry.zip_path.force_encoding('UTF-8')
-
836
@entries[entry_path] = index
-
836
@last_iterated_entry_index = index
-
836
if entry_path == path_name
-
44
return entry.file_data.read
-
end
-
end
-
-
104
raise NoEntry, "Entry not found: #{path_name}"
-
else
-
12
open {|container| container.read(path_name)}
-
end
-
end
-
end
-
end
-
end
-
end
-
1
module EPUB
-
1
class OCF
-
1
class PhysicalContainer
-
1
class UnpackedDirectory < self
-
1
def open
-
8
yield self
-
end
-
-
1
def read(path_name)
-
24
::File.read(::File.join(@container_path, path_name))
-
rescue ::Errno::ENOENT => error
-
8
raise NoEntry.from_error(error)
-
end
-
end
-
end
-
end
-
end
-
1
require 'open-uri'
-
-
1
module EPUB
-
1
class OCF
-
1
class PhysicalContainer
-
1
class UnpackedURI < self
-
# EPUB URI: http://example.net/path/to/book/
-
# container.xml: http://example.net/path/to/book/META-INF/container.xml
-
# @param [URI, String] container_path URI of EPUB container's root directory.
-
# For exapmle, <code>"http://example.net/path/to/book/"</code>, which
-
# should contain <code>"http://example.net/path/to/book/META-INF/container.xml"</code> as its container.xml file. Note that this should end with "/"(slash).
-
1
def initialize(container_path)
-
2
super(URI(container_path))
-
end
-
-
1
def open
-
yield self
-
end
-
-
1
def read(path_name)
-
1
(@container_path + path_name).read
-
rescue ::OpenURI::HTTPError => error
-
raise NoEntry.from_error(error)
-
end
-
end
-
end
-
end
-
end
-
1
require 'zipruby'
-
-
1
module EPUB
-
1
class OCF
-
1
class PhysicalContainer
-
1
class Zipruby < self
-
1
def open
-
5
Zip::Archive.open @container_path do |archive|
-
5
@monitor.synchronize do
-
begin
-
5
@archive = archive
-
5
yield self
-
rescue ::Zip::Error => error
-
raise NoEntry.from_error(error)
-
ensure
-
5
@archive = nil
-
end
-
end
-
end
-
end
-
-
1
def read(path_name)
-
5
if @archive
-
8
@archive.fopen(path_name) {|entry| entry.read}
-
else
-
2
open {|container| container.read(path_name)}
-
end
-
rescue ::Zip::Error => error
-
raise NoEntry.from_error(error)
-
ensure
-
5
@archive = nil
-
end
-
end
-
end
-
end
-
end
-
1
module EPUB
-
1
class OCF
-
1
class Rights
-
end
-
end
-
end
-
1
module EPUB
-
1
class OCF
-
1
class Signatures
-
end
-
end
-
end
-
1
require 'epub'
-
1
require 'epub/constants'
-
1
require 'epub/book'
-
-
1
module EPUB
-
1
class Parser
-
1
class << self
-
# Parse an EPUB file
-
#
-
# @example
-
# EPUB::Parser.parse('path/to/book.epub') # => EPUB::Book object
-
#
-
# @example
-
# class MyBook
-
# include EPUB::Book::Feature
-
# end
-
# book = MyBook.new
-
# parsed_book = EPUB::Parser.parse('path/to/book.epub', book: book) # => #<MyBook:0x000000019760e8 @epub_file=..>
-
# parsed_book.equal? book # => true
-
#
-
# @example
-
# book = EPUB::Parser.parse('path/to/book.epub', class: MyBook) # => #<MyBook:0x000000019b0568 @epub_file=...>
-
# book.instance_of? MyBook # => true
-
#
-
# @param [String] filepath
-
# @param [Hash] options the type of return is specified by this argument.
-
# If no options, returns {EPUB::Book} object.
-
# For details of options, see below.
-
# @option options [EPUB] :book instance of class which includes {EPUB} module
-
# @option options [Class] :class class which includes {EPUB} module
-
# @option options [EPUB::OCF::PhysicalContainer, Symbol] :container_adapter OCF physical container adapter to use when parsing EPUB container
-
# When class passed, it is used. When symbol passed, it is considered as subclass name of {EPUB::OCF::PhysicalContainer}.
-
# If omitted, {EPUB::OCF::PhysicalContainer.adapter} is used.
-
# @return [EPUB] object which is an instance of class including {EPUB} module.
-
# When option :book passed, returns the same object whose attributes about EPUB are set.
-
# When option :class passed, returns the instance of the class.
-
# Otherwise returns {EPUB::Book} object.
-
1
def parse(filepath, container_adapter: nil, book: nil, initialize_with: nil, **options)
-
22
new(filepath, container_adapter: container_adapter, book: book, initialize_with: initialize_with, **options).parse
-
end
-
end
-
-
1
def initialize(filepath, container_adapter: nil, book: nil, initialize_with: nil, **options)
-
29
if filepath.to_s.encoding == Encoding::ASCII_8BIT
-
# On Windows and macOS, encoding of file name is set by Ruby,
-
# but on UNIX, always is ASCII-8BIT
-
# See https://docs.ruby-lang.org/ja/2.7.0/class/IO.html
-
filepath = filepath.to_s.dup
-
require "nkf"
-
filepath.force_encoding NKF.guess(filepath)
-
end
-
29
path_is_uri = (container_adapter == EPUB::OCF::PhysicalContainer::UnpackedURI or
-
container_adapter == :UnpackedURI or
-
EPUB::OCF::PhysicalContainer.adapter == EPUB::OCF::PhysicalContainer::UnpackedURI)
-
-
raise "File #{filepath} not found" if
-
29
!path_is_uri and !File.exist?(filepath)
-
-
29
@filepath = path_is_uri ? filepath : File.realpath(filepath)
-
29
@book = create_book(book: book, initialize_with: initialize_with, **options)
-
29
if path_is_uri
-
@book.container_adapter = :UnpackedURI
-
29
elsif File.directory? @filepath
-
2
@book.container_adapter = :UnpackedDirectory
-
end
-
29
@book.epub_file = @filepath
-
29
if options[:container_adapter]
-
@book.container_adapter = options[:container_adapter]
-
end
-
end
-
-
1
def parse
-
27
@book.container_adapter.open @filepath do |container|
-
27
@book.ocf = OCF.parse(container)
-
27
@book.ocf.container.rootfiles.each {|rootfile|
-
81
package = Publication.parse(container, rootfile.full_path.to_s)
-
81
rootfile.package = package
-
81
@book.packages << package
-
81
package.book = @book
-
}
-
end
-
-
27
@book
-
end
-
-
1
private
-
-
1
def create_book(book: nil, initialize_with: nil, **params)
-
case
-
29
when book
-
2
book
-
when params[:class]
-
2
if initialize_with
-
params[:class].new initialize_with
-
else
-
2
params[:class].new
-
end
-
else
-
25
Book.new
-
end
-
end
-
end
-
end
-
-
1
require 'epub/parser/version'
-
1
require 'epub/parser/xml_document'
-
1
require 'epub/parser/ocf'
-
1
require 'epub/parser/publication'
-
1
require 'epub/parser/content_document'
-
1
require 'epub/content_document'
-
1
require 'epub/constants'
-
1
require 'epub/parser/xml_document'
-
-
1
module EPUB
-
1
class Parser
-
1
class ContentDocument
-
1
using XMLDocument::Refinements
-
-
# @param [EPUB::Publication::Package::Manifest::Item] item
-
1
def initialize(item)
-
19
@item = item
-
end
-
-
1
def parse
-
17
content_document = case @item.media_type
-
when 'application/xhtml+xml'
-
17
if @item.nav?
-
11
EPUB::ContentDocument::Navigation.new
-
else
-
6
EPUB::ContentDocument::XHTML.new
-
end
-
when 'image/svg+xml'
-
EPUB::ContentDocument::SVG.new
-
else
-
nil
-
end
-
17
return content_document if content_document.nil?
-
17
content_document.item = @item
-
17
document = XMLDocument.new(@item.read)
-
# parse_content_document(document)
-
17
if @item.nav?
-
11
content_document.navigations = parse_navigations(document)
-
end
-
17
content_document
-
end
-
-
# @param [XMLDocument, REXML::Document, Oga::XML::Document, Nokogiri::HTML::Document] document HTML document or element including nav
-
# @return [Array<EPUB::ContentDocument::Navigation::Navigation>] navs array of Navigation object
-
1
def parse_navigations(document)
-
34
document.each_element_by_xpath('/xhtml:html/xhtml:body//xhtml:nav', EPUB::NAMESPACES).collect {|elem| parse_navigation elem}
-
end
-
-
# @param [REXML::Element, Oga::XML::Element, Nokogiri::XML::Element] element nav element
-
# @return [EPUB::ContentDocument::Navigation::Navigation] nav Navigation object
-
1
def parse_navigation(element)
-
22
nav = EPUB::ContentDocument::Navigation::Navigation.new
-
22
nav.text = find_heading(element)
-
22
hidden = element.attribute_with_prefix('hidden')
-
22
nav.hidden = hidden.nil? ? nil : true
-
22
nav.types = element.attribute_with_prefix('type', 'epub')&.split(/\s+/)
-
22
element.each_element_by_xpath('./xhtml:ol/xhtml:li', EPUB::NAMESPACES).map do |elem|
-
42
nav.items << parse_navigation_item(elem)
-
end
-
-
22
nav
-
end
-
-
# @param [REXML::Element, Oga::XML::Element, Nokogiri::XML::Element] element li element
-
1
def parse_navigation_item(element)
-
82
item = EPUB::ContentDocument::Navigation::Item.new
-
82
a_or_span = element.each_element_by_xpath('./xhtml:a[1]|xhtml:span[1]', EPUB::NAMESPACES).first
-
82
return a_or_span if a_or_span.nil?
-
-
82
item.text = a_or_span.content
-
82
item.types = a_or_span.attribute_with_prefix('type', 'epub')&.split(/\s+/)
-
82
if a_or_span.name == 'a'
-
72
if item.text.empty?
-
20
embedded_content = a_or_span.each_element_by_xpath('./xhtml:audio[1]|xhtml:canvas[1]|xhtml:embed[1]|xhtml:iframe[1]|xhtml:img[1]|xhtml:math[1]|xhtml:object[1]|xhtml:svg[1]|xhtml:video[1]', EPUB::NAMESPACES).first
-
20
unless embedded_content.nil?
-
20
case embedded_content.name
-
when 'audio', 'canvas', 'embed', 'iframe'
-
10
item.text = embedded_content.attribute_with_prefix('name') || embedded_content.attribute_with_prefix('srcdoc')
-
when 'img'
-
10
item.text = embedded_content.attribute_with_prefix('alt')
-
when 'math', 'object'
-
item.text = embedded_content.attribute_with_prefix('name')
-
when 'svg', 'video'
-
else
-
end
-
end
-
20
item.text = a_or_span.attribute_with_prefix('title').to_s if item.text.nil? || item.text.empty?
-
end
-
72
item.href = a_or_span.attribute_with_prefix('href')
-
72
item.item = @item.find_item_by_relative_iri(item.href)
-
end
-
122
item.items = element.each_element_by_xpath('./xhtml:ol[1]/xhtml:li', EPUB::NAMESPACES).map {|li| parse_navigation_item(li)}
-
-
82
item
-
end
-
-
1
private
-
-
# @param [REXML::Element, Oga::XML::Element, Nokogiri::XML::Element] element nav element
-
# @return [String] heading heading text
-
1
def find_heading(element)
-
22
heading = element.each_element_by_xpath('./xhtml:h1|xhtml:h2|xhtml:h3|xhtml:h4|xhtml:h5|xhtml:h6|xhtml:hgroup', EPUB::NAMESPACES).first
-
-
22
return nil if heading.nil?
-
20
return heading.content unless heading.name == 'hgroup'
-
-
10
(heading.each_element_by_xpath(".//xhtml:h1", EPUB::NAMESPACES) ||
-
heading.each_element_by_xpath(".//xhtml:h2", EPUB::NAMESPACES) ||
-
heading.each_element_by_xpath(".//xhtml:h3", EPUB::NAMESPACES) ||
-
heading.each_element_by_xpath(".//xhtml:h4", EPUB::NAMESPACES) ||
-
heading.each_element_by_xpath(".//xhtml:h5", EPUB::NAMESPACES) ||
-
heading.each_element_by_xpath(".//xhtml:h6", EPUB::NAMESPACES)).first.content
-
end
-
end
-
end
-
end
-
1
module EPUB
-
1
class Parser
-
1
module Metadata
-
1
using XMLDocument::Refinements
-
-
1
def parse_metadata(elem, unique_identifier_id, default_namespace)
-
127
metadata = EPUB::Publication::Package::Metadata.new
-
127
id_map = {}
-
-
127
default_namespace_uri = EPUB::NAMESPACES[default_namespace]
-
127
elem.each_element do |child|
-
2208
elem_name = child.name
-
-
model =
-
2208
case child.namespace_uri
-
when EPUB::NAMESPACES['dc']
-
847
case elem_name
-
when 'identifier'
-
171
identifier = build_model(child, :Identifier, ['id'])
-
171
metadata.identifiers << identifier
-
171
identifier.scheme = child.attribute_with_prefix('scheme', 'opf')
-
171
identifier
-
when 'title'
-
274
title = build_model(child, :Title)
-
274
metadata.titles << title
-
274
title
-
when 'language'
-
98
language = build_model(child, :DCMES, ['id'])
-
98
metadata.languages << language
-
98
language
-
when 'title', 'contributor', 'coverage', 'creator', 'date', 'description', 'format', 'publisher', 'relation', 'source', 'subject', 'rights', 'type'
-
304
attr = elem_name == 'rights' ? elem_name : elem_name + 's'
-
304
dcmes = build_model(child)
-
304
metadata.__send__(attr) << dcmes
-
304
dcmes
-
else
-
build_unsupported_model(child)
-
end
-
when default_namespace_uri
-
1361
case elem_name
-
when 'meta'
-
1229
meta = build_model(child, :Meta, %w[property id scheme content name])
-
1229
metadata.metas << meta
-
1229
meta
-
when 'link'
-
132
link = build_model(child, :Link, %w[id media-type])
-
132
metadata.links << link
-
132
link.href = child.attribute_with_prefix('href')
-
132
link.rel = Set.new(child.attribute_with_prefix('rel').split(/\s+/))
-
132
link
-
else
-
build_unsupported_model(child)
-
end
-
else
-
build_unsupported_model(child)
-
end
-
-
2208
metadata.children << model
-
-
2208
if model.kind_of?(EPUB::Metadata::Identifier) &&
-
model.id == unique_identifier_id
-
127
metadata.unique_identifier = model
-
end
-
-
2208
if model.respond_to?(:id) && model.id
-
651
id_map[model.id] = {refinee: model}
-
end
-
-
2208
refines = child.attribute_with_prefix('refines')
-
2208
if refines && refines.start_with?('#')
-
768
id = refines[1..-1]
-
768
id_map[id] ||= {}
-
768
id_map[id][:refiners] ||= []
-
768
id_map[id][:refiners] << model
-
end
-
end
-
-
127
id_map.values.each do |hsh|
-
651
next unless hsh[:refiners]
-
460
next unless hsh[:refinee]
-
1228
hsh[:refiners].each {|meta| meta.refines = hsh[:refinee]}
-
end
-
-
127
metadata
-
end
-
-
1
def build_model(elem, klass=:DCMES, attributes=%w[id lang dir])
-
2208
model = EPUB::Metadata.const_get(klass).new
-
2208
attributes.each do |attr|
-
8412
writer_name = (attr == "content") ? "meta_content=" : "#{attr.gsub('-', '_')}="
-
8412
namespace = (attr == "lang") ? "xml" : nil
-
8412
model.__send__ writer_name, elem.attribute_with_prefix(attr, namespace)
-
end
-
2208
model.content = elem.content unless klass == :Link
-
2208
model.content.strip! if klass == :Identifier
-
2208
model
-
end
-
-
1
def build_unsupported_model(elem)
-
EPUB::Metadata::UnsupportedModel.new(elem)
-
end
-
end
-
end
-
end
-
1
require 'epub/constants'
-
1
require 'epub/ocf'
-
1
require 'epub/ocf/physical_container'
-
1
require 'epub/parser/metadata'
-
1
require "epub/parser/xml_document"
-
-
1
module EPUB
-
1
class Parser
-
1
class OCF
-
1
using XMLDocument::Refinements
-
1
include Metadata
-
-
1
DIRECTORY = 'META-INF'
-
-
1
class << self
-
1
def parse(container)
-
27
new(container).parse
-
end
-
end
-
-
1
def initialize(container)
-
36
@container = container
-
36
@ocf = EPUB::OCF.new
-
end
-
-
1
def parse
-
28
EPUB::OCF::MODULES.each do |m|
-
begin
-
168
data = @container.read(File.join(DIRECTORY, "#{m}.xml"))
-
56
@ocf.__send__ "#{m}=", __send__("parse_#{m}", data)
-
rescue EPUB::OCF::PhysicalContainer::NoEntry
-
end
-
end
-
-
28
@ocf
-
end
-
-
1
def parse_container(xml)
-
33
container = EPUB::OCF::Container.new
-
33
doc = XMLDocument.new(xml)
-
33
doc.each_element_by_xpath "/ocf:container/ocf:rootfiles/ocf:rootfile", EPUB::NAMESPACES do |elem|
-
99
rootfile = EPUB::OCF::Container::Rootfile.new
-
99
rootfile.full_path = Addressable::URI.parse(elem.attribute_with_prefix('full-path'))
-
99
rootfile.media_type = elem.attribute_with_prefix('media-type')
-
99
container.rootfiles << rootfile
-
end
-
-
33
container
-
end
-
-
1
def parse_encryption(content)
-
1
encryption = EPUB::OCF::Encryption.new
-
1
encryption.content = content
-
1
encryption
-
end
-
-
1
def parse_manifest(content)
-
warn "Not implemented: #{self.class}##{__method__}" if $VERBOSE
-
end
-
-
1
def parse_metadata(content)
-
30
doc = XMLDocument.new(content)
-
30
unless multiple_rendition_metadata?(doc)
-
1
warn "Not implemented: #{self.class}##{__method__}" if $VERBOSE
-
1
metadata = EPUB::OCF::UnknownFormatMetadata.new
-
1
metadata.content = content
-
1
return metadata
-
end
-
29
super(doc.root, doc.root.attribute_with_prefix('unique-identifier'), 'metadata')
-
end
-
-
1
def parse_rights(content)
-
warn "Not implemented: #{self.class}##{__method__}" if $VERBOSE
-
end
-
-
1
def parse_signatures(content)
-
warn "Not implemented: #{self.class}##{__method__}" if $VERBOSE
-
end
-
-
1
private
-
-
1
def multiple_rendition_metadata?(doc)
-
30
doc.root &&
-
doc.root.name == 'metadata' &&
-
doc.root.namespaces['xmlns'] == EPUB::NAMESPACES['metadata']
-
end
-
end
-
end
-
end
-
1
require 'strscan'
-
1
require 'epub/publication'
-
1
require 'epub/constants'
-
1
require 'epub/parser/metadata'
-
-
1
module EPUB
-
1
class Parser
-
1
class Publication
-
1
using XMLDocument::Refinements
-
1
include Metadata
-
-
1
class << self
-
1
def parse(container, file)
-
81
opf = container.read(Addressable::URI.unencode(file))
-
-
81
new(opf).parse
-
end
-
end
-
-
1
def initialize(opf)
-
125
@doc = XMLDocument.new(opf)
-
end
-
-
1
def parse
-
90
package = parse_package(@doc)
-
90
(EPUB::Publication::Package::CONTENT_MODELS - [:bindings]).each do |model|
-
360
package.__send__ "#{model}=", __send__("parse_#{model}", @doc)
-
end
-
90
package.bindings = parse_bindings(@doc, package.manifest)
-
-
90
package
-
end
-
-
1
def parse_package(doc)
-
125
package = EPUB::Publication::Package.new
-
125
elem = doc.root
-
125
%w[version xml:lang dir id].each do |attr|
-
500
package.__send__ "#{attr.gsub(/\:/, '_')}=", elem.attribute_with_prefix(attr)
-
end
-
125
package.prefix = parse_prefix(elem.attribute_with_prefix('prefix'))
-
125
EPUB::Publication.__send__ :include, EPUB::Publication::FixedLayout if package.prefix.key? EPUB::Publication::FixedLayout::PREFIX_KEY
-
-
125
package
-
end
-
-
1
def parse_metadata(doc)
-
98
super(doc.each_element_by_xpath('/opf:package/opf:metadata', EPUB::NAMESPACES).first, doc.root.attribute_with_prefix('unique-identifier'), 'opf')
-
end
-
-
1
def parse_manifest(doc)
-
110
manifest = EPUB::Publication::Package::Manifest.new
-
110
elem = doc.each_element_by_xpath('/opf:package/opf:manifest', EPUB::NAMESPACES).first
-
110
manifest.id = elem.attribute_with_prefix('id')
-
-
110
fallback_map = {}
-
110
elem.each_element_by_xpath('./opf:item', EPUB::NAMESPACES).each do |e|
-
1199
item = EPUB::Publication::Package::Manifest::Item.new
-
1199
%w[id media-type media-overlay].each do |attr|
-
3597
item.__send__ "#{attr.gsub(/-/, '_')}=", e.attribute_with_prefix(attr)
-
end
-
1199
item.href = e.attribute_with_prefix('href')
-
1199
fallback = e.attribute_with_prefix('fallback')
-
1199
fallback_map[fallback] = item if fallback
-
1199
properties = e.attribute_with_prefix('properties')
-
1199
item.properties = properties.split(' ') if properties
-
1199
manifest << item
-
end
-
110
fallback_map.each_pair do |id, from|
-
112
from.fallback = manifest[id]
-
end
-
-
110
manifest
-
end
-
-
1
def parse_spine(doc)
-
90
spine = EPUB::Publication::Package::Spine.new
-
90
elem = doc.each_element_by_xpath('/opf:package/opf:spine', EPUB::NAMESPACES).first
-
90
%w[id toc page-progression-direction].each do |attr|
-
270
spine.__send__ "#{attr.gsub(/-/, '_')}=", elem.attribute_with_prefix(attr)
-
end
-
-
90
elem.each_element_by_xpath('./opf:itemref', EPUB::NAMESPACES).each do |e|
-
288
itemref = EPUB::Publication::Package::Spine::Itemref.new
-
288
%w[idref id].each do |attr|
-
576
itemref.__send__ "#{attr}=", e.attribute_with_prefix(attr)
-
end
-
288
itemref.linear = (e.attribute_with_prefix('linear') != 'no')
-
288
properties = e.attribute_with_prefix('properties')
-
288
itemref.properties = properties.split(' ') if properties
-
288
spine << itemref
-
end
-
-
90
spine
-
end
-
-
1
def parse_guide(doc)
-
93
guide = EPUB::Publication::Package::Guide.new
-
93
doc.each_element_by_xpath '/opf:package/opf:guide/opf:reference', EPUB::NAMESPACES do |ref|
-
39
reference = EPUB::Publication::Package::Guide::Reference.new
-
39
%w[type title].each do |attr|
-
78
reference.__send__ "#{attr}=", ref.attribute_with_prefix(attr)
-
end
-
39
reference.href = ref.attribute_with_prefix('href')
-
39
guide << reference
-
end
-
-
93
guide
-
end
-
-
1
def parse_bindings(doc, handler_map)
-
97
bindings = EPUB::Publication::Package::Bindings.new
-
97
doc.each_element_by_xpath '/opf:package/opf:bindings/opf:mediaType', EPUB::NAMESPACES do |elem|
-
43
media_type = EPUB::Publication::Package::Bindings::MediaType.new
-
43
media_type.media_type = elem.attribute_with_prefix('media-type')
-
43
media_type.handler = handler_map[elem.attribute_with_prefix('handler')]
-
43
bindings << media_type
-
end
-
-
97
bindings
-
end
-
-
1
def parse_prefix(str)
-
125
prefixes = {}
-
125
return prefixes if str.nil? or str.empty?
-
124
scanner = StringScanner.new(str)
-
124
scanner.scan /\s*/
-
124
while prefix = scanner.scan(/[^\:\s]+/)
-
193
scanner.scan /[\:\s]+/
-
193
iri = scanner.scan(/[^\s]+/)
-
193
if iri.nil? or iri.empty?
-
warn "no IRI detected for prefix `#{prefix}`"
-
else
-
193
prefixes[prefix] = iri
-
end
-
193
scanner.scan /\s*/
-
end
-
124
prefixes
-
end
-
end
-
end
-
end
-
1
module EPUB
-
1
class Parser
-
1
class XMLDocument
-
1
class << self
-
1
attr_accessor :backend
-
-
1
def new(xml)
-
259
case backend
-
when :Oga
-
65
Oga.parse_xml(xml)
-
when :Nokogiri
-
186
Nokogiri.XML(xml)
-
else
-
8
REXML::Document.new(xml)
-
end
-
end
-
end
-
end
-
end
-
end
-
-
1
%i[Nokogiri Oga REXML].each do |backend|
-
begin
-
3
require "epub/parser/xml_document/refinements/#{backend.downcase}"
-
3
EPUB::Parser::XMLDocument.backend ||= backend
-
rescue LoadError
-
end
-
end
-
1
require "nokogiri"
-
-
1
module EPUB
-
1
class Parser
-
1
class XMLDocument
-
1
module Refinements
-
1
module Nokogiri
-
1
refine ::Nokogiri::XML::Node do
-
1
def each_element_by_xpath(xpath, namespaces = nil, &block)
-
637
xpath(xpath, namespaces).each &block
-
end
-
-
1
def attribute_with_prefix(name, prefix = nil)
-
15669
attribute_with_ns(name, EPUB::NAMESPACES[prefix])&.value
-
end
-
-
1
def each_element(xpath = nil, &block)
-
95
element_children.each(&block)
-
end
-
-
1
alias elements element_children
-
-
1
def namespace_uri
-
1600
namespace.href
-
end
-
end
-
end
-
-
1
include Nokogiri
-
end
-
end
-
end
-
end
-
1
require "oga"
-
-
1
module EPUB
-
1
class Parser
-
1
class XMLDocument
-
1
module Refinements
-
1
module Oga
-
1
[::Oga::XML::Document, ::Oga::XML::Node].each do |klass|
-
2
refine klass do
-
[
-
2
[:document, ::Oga::XML::Document],
-
[:element, ::Oga::XML::Element],
-
[:text, ::Oga::XML::Text]
-
].each do |(type, klass)|
-
6
define_method "#{type}?" do
-
1044
kind_of? klass
-
end
-
end
-
-
2
def root
-
# Couldn't use find(&:element?) for Rubies under 2.6
-
215
root_node.children.find {|child| child.element?}
-
end
-
-
2
def elements
-
# Couldn't use find(&:element?) for Rubies under 2.6
-
548
children.select {|child| child.element?}
-
end
-
-
# Need for Rubies under 2.6
-
2
def respond_to?(name, include_all = false)
-
15
[:root, :elements].include?(name) || super
-
end
-
-
2
def each_element_by_xpath(xpath, namespaces = nil, &block)
-
286
xpath(xpath, namespaces: namespaces).each &block
-
end
-
end
-
end
-
-
1
refine ::Oga::XML::Element do
-
1
def attribute_with_prefix(name, prefix = nil)
-
5047
name = prefix ? "#{prefix}:#{name}" : name
-
5047
get(name)
-
end
-
-
1
def each_element(xpath = nil, &block)
-
27
each_node do |node|
-
1529
throw :skip_children unless node.kind_of?(::Oga::XML::Element)
-
516
block.call node
-
end
-
end
-
-
1
def namespace_uri
-
516
namespace&.uri
-
end
-
-
1
alias original_namespaces namespaces
-
1
def namespaces
-
5
original_namespaces.each_with_object({}) {|(name, namespace), nss|
-
10
nss[name] = namespace.uri
-
}
-
end
-
-
1
alias content text
-
end
-
-
1
refine ::Oga::XML::Text do
-
1
alias content text
-
end
-
end
-
-
1
include Oga
-
end
-
end
-
end
-
end
-
1
require "rexml/document"
-
-
1
module EPUB
-
1
class Parser
-
1
class XMLDocument
-
1
module Refinements
-
1
module REXML
-
1
[::REXML::Element, ::REXML::Text].each do |klass|
-
2
refine klass do
-
2
%i[document element text].each do |type|
-
6
define_method "#{type}?" do
-
node_type == type
-
end
-
end
-
end
-
end
-
-
1
refine ::REXML::Element do
-
1
def each_element_by_xpath(xpath, namespaces = nil, &block)
-
54
::REXML::XPath.each self, xpath, namespaces, &block
-
end
-
-
1
def attribute_with_prefix(name, prefix = nil)
-
859
attribute(name, EPUB::NAMESPACES[prefix])&.value
-
end
-
-
1
alias namespace_uri namespace
-
-
1
def content
-
98
each_child.inject("") {|text, node|
-
94
case node.node_type
-
when :document, :element
-
2
text << node.content
-
when :text
-
92
text << node.value
-
end
-
}
-
end
-
end
-
-
1
refine ::REXML::Text do
-
1
alias content value
-
end
-
end
-
-
1
include REXML
-
end
-
end
-
end
-
end
-
1
require 'epub/publication/package'
-
1
require 'epub/publication/fixed_layout'
-
1
module EPUB
-
1
module Publication
-
1
module FixedLayout
-
1
PREFIX_KEY = 'rendition'.freeze
-
1
PREFIX_VALUE = 'http://www.idpf.org/vocab/rendition/#'.freeze
-
-
RENDITION_PROPERTIES = {
-
1
'layout' => ['reflowable'.freeze, 'pre-paginated'.freeze].freeze,
-
'orientation' => ['auto'.freeze, 'landscape'.freeze, 'portrait'.freeze].freeze,
-
'spread' => ['auto'.freeze, 'none'.freeze, 'landscape'.freeze, 'portrait'.freeze, 'both'.freeze].freeze
-
}.freeze
-
-
1
class UnsupportedRenditionValue < StandardError; end
-
-
1
class << self
-
1
def included(package_class)
-
[
-
2
[Package, PackageMixin],
-
[Package::Metadata, MetadataMixin],
-
[Package::Spine::Itemref, ItemrefMixin],
-
[Package::Manifest::Item, ItemMixin],
-
[ContentDocument::XHTML, ContentDocumentMixin],
-
].each do |(base, mixin)|
-
10
base.__send__ :include, mixin
-
end
-
end
-
end
-
-
1
module Rendition
-
# @note Call after defining #rendition_xxx and #renditionn_xxx=
-
1
def def_rendition_methods
-
4
RENDITION_PROPERTIES.each_key do |property|
-
12
alias_method property, "rendition_#{property}"
-
12
alias_method "#{property}=", "rendition_#{property}="
-
end
-
4
def_rendition_layout_methods
-
end
-
-
1
def def_rendition_layout_methods
-
4
property = 'layout'
-
4
RENDITION_PROPERTIES[property].each do |value|
-
8
method_name_base = value.gsub('-', '_')
-
8
writer_name = "#{method_name_base}="
-
8
define_method writer_name do |new_value|
-
4
new_prop = new_value ? value : values.find {|l| l != value}
-
4
__send__ "rendition_#{property}=", new_prop
-
end
-
-
8
maker_name = "make_#{method_name_base}"
-
8
define_method maker_name do
-
5
__send__ "rendition_#{property}=", value
-
end
-
8
destructive_method_name = "#{method_name_base}!"
-
8
alias_method destructive_method_name, maker_name
-
-
8
predicate_name = "#{method_name_base}?"
-
8
define_method predicate_name do
-
13
__send__("rendition_#{property}") == value
-
end
-
end
-
end
-
end
-
-
1
module PackageMixin
-
# @return [true, false]
-
1
def using_fixed_layout
-
4
prefix.has_key? PREFIX_KEY and
-
prefix[PREFIX_KEY] == PREFIX_VALUE
-
end
-
1
alias using_fixed_layout? using_fixed_layout
-
-
# @param using_fixed_layout [true, false]
-
1
def using_fixed_layout=(using_fixed_layout)
-
2
if using_fixed_layout
-
1
prefix[PREFIX_KEY] = PREFIX_VALUE
-
else
-
1
prefix.delete PREFIX_KEY
-
end
-
end
-
end
-
-
1
module MetadataMixin
-
1
extend Rendition
-
-
1
RENDITION_PROPERTIES.each_pair do |property, values|
-
3
define_method "rendition_#{property}" do
-
45
meta = metas.find {|m| m.property == "rendition:#{property}"}
-
27
meta ? meta.content : values.first
-
end
-
-
3
define_method "rendition_#{property}=" do |new_value|
-
14
raise UnsupportedRenditionValue, new_value unless values.include? new_value
-
-
13
prefixed_property = "rendition:#{property}"
-
13
values_to_be_deleted = values - [new_value]
-
21
metas.delete_if {|meta| meta.property == prefixed_property && values_to_be_deleted.include?(meta.content)}
-
14
unless metas.any? {|meta| meta.property == prefixed_property && meta.content == new_value}
-
12
meta = Package::Metadata::Meta.new
-
12
meta.property = prefixed_property
-
12
meta.content = new_value
-
12
metas << meta
-
end
-
13
new_value
-
end
-
end
-
-
1
def_rendition_methods
-
end
-
-
1
module ItemrefMixin
-
1
extend Rendition
-
-
1
PAGE_SPREAD_PROPERTY = 'center'
-
1
PAGE_SPREAD_PREFIX = 'rendition:page-spread-'
-
-
1
class << self
-
# @todo Define using Module#prepend after Ruby 2.0 will become popular
-
1
def included(base)
-
2
return if base.instance_methods.include? :page_spread_without_fixed_layout
-
1
base.__send__ :alias_method, :page_spread_without_fixed_layout, :page_spread
-
1
base.__send__ :alias_method, :page_spread_writer_without_fixed_layout, :page_spread=
-
-
1
prefixed_page_spread_property = "#{PAGE_SPREAD_PREFIX}#{PAGE_SPREAD_PROPERTY}"
-
1
base.__send__ :define_method, :page_spread do
-
3
property = page_spread_without_fixed_layout
-
3
return property if property
-
2
properties.include?(prefixed_page_spread_property) ? PAGE_SPREAD_PROPERTY : nil
-
end
-
-
1
base.__send__ :define_method, :page_spread= do |new_value|
-
6
if new_value == PAGE_SPREAD_PROPERTY
-
2
page_spread_writer_without_fixed_layout nil
-
2
properties << prefixed_page_spread_property
-
else
-
4
page_spread_writer_without_fixed_layout new_value
-
end
-
6
new_value
-
end
-
end
-
end
-
-
1
RENDITION_PROPERTIES.each do |property, values|
-
3
rendition_property_prefix = "rendition:#{property}-"
-
-
3
reader_name = "rendition_#{property}"
-
3
define_method reader_name do
-
27
prop_value = properties.find {|prop| prop.start_with? rendition_property_prefix}
-
16
prop_value ? prop_value.gsub(/\A#{Regexp.escape(rendition_property_prefix)}/, '') :
-
spine.package.metadata.__send__(reader_name)
-
end
-
-
3
writer_name = "#{reader_name}="
-
3
define_method writer_name do |new_value|
-
12
if new_value.nil?
-
2
properties.delete_if {|prop| prop.start_with? rendition_property_prefix}
-
1
return new_value
-
end
-
-
11
raise UnsupportedRenditionValue, new_value unless values.include? new_value
-
-
27
values_to_be_deleted = (values - [new_value]).map {|value| "#{rendition_property_prefix}#{value}"}
-
14
properties.delete_if {|prop| values_to_be_deleted.include? prop}
-
11
new_property = "#{rendition_property_prefix}#{new_value}"
-
11
properties << new_property unless properties.include? new_property
-
11
new_value
-
end
-
end
-
-
1
def_rendition_methods
-
end
-
-
1
module ItemMixin
-
1
extend Rendition
-
-
1
RENDITION_PROPERTIES.each_key do |property|
-
3
define_method "rendition_#{property}" do
-
2
itemref.__send__ property
-
end
-
-
3
writer_name = "rendition_#{property}="
-
3
define_method writer_name do |value|
-
2
itemref.__send__ writer_name, value
-
end
-
end
-
-
1
def_rendition_methods
-
end
-
-
1
module ContentDocumentMixin
-
1
extend Rendition
-
-
1
RENDITION_PROPERTIES.each_key do |property|
-
3
reader_name = "rendition_#{property}"
-
3
define_method reader_name do
-
1
item.__send__ reader_name
-
end
-
-
3
writer_name = "rendition_#{property}="
-
3
define_method writer_name do |value|
-
1
item.__send__ writer_name, value
-
end
-
end
-
-
1
def_rendition_methods
-
end
-
end
-
end
-
end
-
1
module EPUB
-
1
module Publication
-
1
class Package
-
1
include Inspector
-
-
1
CONTENT_MODELS = [:metadata, :manifest, :spine, :guide, :bindings]
-
RESERVED_VOCABULARY_PREFIXES = {
-
1
'' => 'http://idpf.org/epub/vocab/package/#',
-
'dcterms' => 'http://purl.org/dc/terms/',
-
'marc' => 'http://id.loc.gov/vocabulary/',
-
'media' => 'http://www.idpf.org/epub/vocab/overlays/#',
-
'onix' => 'http://www.editeur.org/ONIX/book/codelists/current.html#',
-
'xsd' => 'http://www.w3.org/2001/XMLSchema#'
-
}
-
-
-
1
class << self
-
1
def define_content_model(model_name)
-
5
define_method "#{model_name}=" do |model|
-
524
current_model = __send__(model_name)
-
524
current_model.package = nil if current_model
-
524
model.package = self
-
524
instance_variable_set "@#{model_name}", model
-
end
-
end
-
end
-
-
1
attr_accessor :book,
-
:version, :prefix, :xml_lang, :dir, :id
-
1
attr_reader *CONTENT_MODELS
-
1
alias lang xml_lang
-
1
alias lang= xml_lang=
-
-
1
CONTENT_MODELS.each do |model|
-
5
define_content_model model
-
end
-
-
1
def initialize
-
162
@prefix = {}
-
end
-
-
# @return [EPUB::Metadata::Identifier] Unique Identifier
-
1
def unique_identifier
-
2
@metadata.unique_identifier
-
end
-
-
# Corresponding {Rootfile}
-
# @return [OCF::Container::Rootfile]
-
1
def rootfile
-
86
@book.ocf.container.rootfiles.find {|rf| rf.package == self}
-
end
-
-
# Full path in EPUB archive
-
# @return [Addressable::URI]
-
1
def full_path
-
18
rootfile.full_path if rootfile
-
end
-
-
1
def inspect
-
4
"#<%{class}:%{object_id} %{attributes} %{models}>" % {
-
:class => self.class,
-
:object_id => inspect_object_id,
-
20
:attributes => inspect_instance_variables(exclude: CONTENT_MODELS.map {|model| :"@#{model}"}),
-
:models => inspect_models
-
}
-
end
-
-
1
def inspect_models
-
4
CONTENT_MODELS.map {|name|
-
20
model = __send__(name)
-
20
representation = model.nil? ? model.inspect : model.inspect_simply
-
20
"@#{name}=#{representation}"
-
}.join(' ')
-
end
-
end
-
end
-
end
-
-
1
EPUB::Publication::Package::CONTENT_MODELS.each do |f|
-
5
require_relative "package/#{f}"
-
end
-
1
module EPUB
-
1
module Publication
-
1
class Package
-
1
class Bindings
-
1
include Inspector::PublicationModel
-
1
attr_accessor :package
-
-
1
def initialize
-
97
@media_types = {}
-
end
-
-
1
def <<(media_type)
-
43
@media_types[media_type.media_type] = media_type
-
end
-
-
1
def [](media_type)
-
6
_, mt = @media_types.detect {|key, _| key == media_type}
-
3
mt
-
end
-
-
1
def media_types
-
5
@media_types.values
-
end
-
-
1
class MediaType
-
1
attr_accessor :media_type, :handler
-
end
-
end
-
end
-
end
-
end
-
1
module EPUB
-
1
module Publication
-
1
class Package
-
1
class Guide
-
1
include Inspector::PublicationModel
-
1
attr_accessor :package, :references
-
-
1
def initialize
-
93
Reference::TYPES.each do |type|
-
1581
variable_name = '@' + type.gsub('-', '_')
-
1581
instance_variable_set variable_name, nil
-
end
-
93
@references = []
-
end
-
-
1
def <<(reference)
-
39
reference.guide = self
-
39
references << reference
-
end
-
-
1
class Reference
-
1
TYPES = %w[cover title-page toc index glossary acknowledgements bibliography colophon copyright-page dedication epigraph foreword loi lot notes preface text]
-
1
attr_accessor :guide,
-
:type, :title
-
1
attr_reader :href
-
-
1
def href=(iri)
-
39
@href = iri.kind_of?(Addressable::URI) ? iri : Addressable::URI.parse(iri)
-
end
-
-
1
def item
-
1
return @item if @item
-
-
1
request_uri = href.request_uri
-
1
@item = @guide.package.manifest.items.find {|item|
-
10
item.href.request_uri == request_uri
-
}
-
end
-
end
-
-
1
Reference::TYPES.each do |type|
-
17
method_name = type.gsub('-', '_')
-
17
define_method method_name do
-
3
var = instance_variable_get "@#{method_name}"
-
3
return var if var
-
-
4
var = references.find {|ref| ref.type == type}
-
2
instance_variable_set "@#{method_name}", var
-
end
-
end
-
end
-
end
-
end
-
end
-
1
require 'set'
-
1
require 'addressable/uri'
-
1
require 'rchardet'
-
1
require 'epub/constants'
-
1
require 'epub/parser/content_document'
-
-
1
module EPUB
-
1
module Publication
-
1
class Package
-
1
class Manifest
-
1
include Inspector::PublicationModel
-
-
1
attr_accessor :package,
-
:id
-
-
1
def initialize
-
140
@items = {}
-
end
-
-
# @param item [Item]
-
# @return [Manifest] self
-
1
def <<(item)
-
1291
item.manifest = self
-
1291
@items[item.id] = item
-
1291
self
-
end
-
-
1
def each_nav
-
3
if block_given?
-
1
each_item do |item|
-
4
yield item if item.nav?
-
end
-
else
-
2
each_item.lazy.select(&:nav?)
-
end
-
end
-
-
# @return [Array<Item>] item which includes "nav" as one of +properties+. It represents this item is a navigation of book.
-
1
def navs
-
9
items.select(&:nav?)
-
end
-
-
# @return [Item, nil] the first item of #navs
-
1
def nav
-
8
navs.first
-
end
-
-
# @return [Item, nil] item which includes "cover-image" as one of +properties+. It represents this item is cover image.
-
1
def cover_image
-
1
items.find(&:cover_image?)
-
end
-
-
# @overload each_item
-
# @yield [item]
-
# @yieldparam [Item]
-
# @overload each_item
-
# @return [Enumerator]
-
1
def each_item
-
4
if block_given?
-
1
@items.each_value do |item|
-
4
yield item
-
end
-
else
-
3
@items.each_value
-
end
-
end
-
-
1
def items
-
88
@items.values
-
end
-
-
# @param item_id [String]
-
# @return [Item, nil]
-
1
def [](item_id)
-
222
@items[item_id]
-
end
-
-
1
class Item
-
1
DUMMY_ROOT_IRI = Addressable::URI.parse('http://example.net/').freeze
-
-
1
include Inspector
-
-
# @!attribute [rw] manifest
-
# @return [Manifest] Returns the value of manifest
-
# @!attribute [rw] id
-
# @return [String] Returns the value of id
-
# @!attribute [rw] href
-
# @return [Addressable::URI] Returns the value of href,
-
# which is relative IRI from rootfile(OPF file)
-
# @!attribute [rw] media_type
-
# @return [String] Returns the value of media_type
-
# @!attribute [rw] properties
-
# @return [Set<String>] Returns the value of properties
-
# @!attribute [rw] media_overlay
-
# @return [String] Returns the value of media_overlay
-
# @!attribute [rw] fallback
-
# @return [Item] Returns the value of attribute fallback
-
1
attr_accessor :manifest,
-
:id, :media_type, :fallback, :media_overlay
-
1
attr_reader :properties, :href
-
-
1
def initialize
-
1298
@properties = Set.new
-
1298
@full_path = nil
-
end
-
-
1
def properties=(props)
-
281
@properties = props.kind_of?(Set) ? props : Set.new(props)
-
end
-
-
1
def href=(iri)
-
1211
@href = iri.kind_of?(Addressable::URI) ? iri : Addressable::URI.parse(iri)
-
end
-
-
# @todo Handle circular fallback chain
-
1
def fallback_chain
-
2
@fallback_chain ||= traverse_fallback_chain([])
-
end
-
-
# full path in archive
-
# @return [Addressable::URI]
-
1
def full_path
-
18
return @full_path if @full_path
-
18
path = DUMMY_ROOT_IRI + manifest.package.full_path + href
-
18
path.scheme = nil
-
18
path.host = nil
-
18
path.path = path.path[1..-1]
-
18
@full_path = path
-
end
-
-
# full path in archive
-
# @return [String]
-
1
def entry_name
-
16
Addressable::URI.unencode(full_path)
-
end
-
-
# Read content from EPUB archive
-
#
-
# @param detect_encoding [Boolean] Whether #read tries auto-detection of character encoding. The default value is +false+.
-
# @return [String] Content with encoding:
-
# US-ASCII when the content is not in text format such images.
-
# UTF-8 when the content is in text format and +detect_encoding+ is +false+.
-
# auto-detected encoding when the content is in text format and +detect_encoding+ is +true+.
-
1
def read(detect_encoding: false)
-
15
raw_content = manifest.package.book.container_adapter.read(manifest.package.book.epub_file, entry_name)
-
-
15
unless media_type.start_with?('text/') or
-
media_type.end_with?('xml') or
-
['application/json', 'application/javascript', 'application/ecmascript', 'application/xml-dtd'].include?(media_type)
-
return raw_content
-
end
-
15
if detect_encoding
-
# CharDet.detect doesn't raise Encoding::CompatibilityError
-
# that is caused when trying compare CharDet's internal
-
# ASCII-8BIT RegExp with a String with other encoding
-
# because Zip::File#read returns a String with encoding ASCII-8BIT.
-
# So, no need to rescue the error here.
-
3
encoding = CharDet.detect(raw_content)['encoding']
-
3
if encoding
-
3
raw_content.force_encoding(encoding)
-
else
-
warn "No encoding detected for #{entry_name}. Set to ASCII-8BIT" if $DEBUG || $VERBOSE
-
raw_content
-
end
-
else
-
12
raw_content.force_encoding("UTF-8");
-
end
-
end
-
-
1
def xhtml?
-
2
media_type == 'application/xhtml+xml'
-
end
-
-
1
def nav?
-
146
properties.include? 'nav'
-
end
-
-
1
def cover_image?
-
4
properties.include? 'cover-image'
-
end
-
-
# @todo Handle circular fallback chain
-
1
def use_fallback_chain(options = {})
-
7
supported = EPUB::MediaType::CORE
-
7
if ad = options[:supported]
-
1
supported = supported | (ad.respond_to?(:to_ary) ? ad : [ad])
-
end
-
7
if del = options[:unsupported]
-
3
supported = supported - (del.respond_to?(:to_ary) ? del : [del])
-
end
-
-
7
return yield self if supported.include? media_type
-
4
if (bindings = manifest.package.bindings) && (binding_media_type = bindings[media_type])
-
1
return yield binding_media_type.handler
-
end
-
6
return fallback.use_fallback_chain(options) {|fb| yield fb} if fallback
-
raise EPUB::MediaType::UnsupportedMediaType
-
end
-
-
1
def content_document
-
23
return nil unless %w[application/xhtml+xml image/svg+xml].include? media_type
-
16
@content_document ||= Parser::ContentDocument.new(self).parse
-
end
-
-
# @return [Package::Spine::Itemref]
-
# @return nil when no Itemref refers this Item
-
1
def itemref
-
14
manifest.package.spine.itemrefs.find {|itemref| itemref.idref == id}
-
end
-
-
# @param iri [Addressable::URI] relative iri
-
# @return [Item]
-
# @return [nil] when item not found
-
# @raise ArgumentError when +iri+ is not relative
-
# @raise ArgumentError when +iri+ starts with "/"(slash)
-
# @note Algorithm stolen form Rack::Utils#clean_path_info
-
1
def find_item_by_relative_iri(iri)
-
75
raise ArgumentError, "Not relative: #{iri.inspect}" unless iri.relative?
-
75
raise ArgumentError, "Start with slash: #{iri.inspect}" if iri.path.start_with? Addressable::URI::SLASH
-
74
target_href = href + iri
-
74
target_href.fragment = nil
-
74
segments = target_href.to_s.split(Addressable::URI::SLASH)
-
74
clean_segments = []
-
74
segments.each do |segment|
-
84
next if segment.empty? || segment == '.'
-
84
segment == '..' ? clean_segments.pop : clean_segments << segment
-
end
-
74
target_iri = Addressable::URI.parse(clean_segments.join(Addressable::URI::SLASH))
-
313
manifest.items.find { |item| item.href == target_iri}
-
end
-
-
1
def inspect
-
1
"#<%{class}:%{object_id} %{manifest} %{attributes}>" % {
-
:class => self.class,
-
:object_id => inspect_object_id,
-
:manifest => "@manifest=#{@manifest.inspect_simply}",
-
:attributes => inspect_instance_variables(exclude: [:@manifest])
-
}
-
end
-
-
1
protected
-
-
1
def traverse_fallback_chain(chain)
-
4
chain << self
-
4
return chain unless fallback
-
2
fallback.traverse_fallback_chain(chain)
-
end
-
end
-
end
-
end
-
end
-
end
-
1
require 'epub/metadata'
-
-
1
module EPUB
-
1
module Publication
-
1
class Package
-
1
Metadata = EPUB::Metadata
-
end
-
end
-
end
-
1
require 'set'
-
-
1
module EPUB
-
1
module Publication
-
1
class Package
-
1
class Spine
-
1
include Inspector::PublicationModel
-
1
attr_accessor :package,
-
:id, :toc, :page_progression_direction
-
1
attr_reader :itemrefs
-
-
1
def initialize
-
106
@itemrefs = []
-
end
-
-
# @return self
-
1
def <<(itemref)
-
304
itemref.spine = self
-
304
@itemrefs << itemref
-
304
self
-
end
-
-
# @yield [itemref]
-
# @yieldparam [Itemref] itemref
-
# @yieldreturn [Object] returns the last value of block
-
# @return [Object, Enumerator]
-
# returns the last value of block when block given, Enumerator when not
-
1
def each_itemref
-
18
if block_given?
-
72
itemrefs.each {|itemref| yield itemref}
-
else
-
6
enum_for :each_itemref
-
end
-
end
-
-
# @return [Enumerator] Enumerator which yeilds {Manifest::Item}
-
# referred by each of {#itemrefs}
-
1
def items
-
20
itemrefs.collect {|itemref| itemref.item}
-
end
-
-
1
class Itemref
-
1
PAGE_SPREAD_PROPERTIES = ['left'.freeze, 'right'.freeze].freeze
-
1
PAGE_SPREAD_PREFIX = 'page-spread-'.freeze
-
-
1
attr_accessor :spine,
-
:idref, :linear, :id
-
1
attr_reader :properties
-
-
1
def initialize
-
313
@properties = Set.new
-
end
-
-
1
def properties=(props)
-
4
@properties = props.kind_of?(Set) ? props : Set.new(props)
-
end
-
-
# @return [true|false]
-
1
def linear?
-
6
!! linear
-
end
-
-
# @return [Package::Manifest::Item] item referred by this object
-
1
def item
-
77
@item ||= @spine.package.manifest[idref]
-
end
-
-
1
def item=(item)
-
1
self.idref = item.id
-
1
item
-
end
-
-
1
def ==(other)
-
3
[:spine, :idref, :id].all? {|meth|
-
9
self.__send__(meth) == other.__send__(meth)
-
} and
-
3
(linear? == other.linear?) and
-
3
(properties == other.properties)
-
end
-
-
# @return ["left", "right", nil]
-
1
def page_spread
-
5
property = properties.find {|prop| prop.start_with? PAGE_SPREAD_PREFIX}
-
3
property ? property.gsub(/\A#{Regexp.escape(PAGE_SPREAD_PREFIX)}/, '') : nil
-
end
-
-
# @param new_value ["left", "right", nil]
-
1
def page_spread=(new_value)
-
6
if new_value.nil?
-
3
properties.delete_if {|prop| prop.start_with? PAGE_SPREAD_PREFIX}
-
2
return new_value
-
end
-
-
4
raise "Unsupported page-spread property: #{new_value}" unless PAGE_SPREAD_PROPERTIES.include? new_value
-
-
8
props_to_be_deleted = (PAGE_SPREAD_PROPERTIES - [new_value]).map {|prop| "#{PAGE_SPREAD_PREFIX}#{prop}"}
-
5
properties.delete_if {|prop| props_to_be_deleted.include? prop}
-
4
new_property = "#{PAGE_SPREAD_PREFIX}#{new_value}"
-
4
properties << new_property unless properties.include? new_property
-
4
new_value
-
end
-
end
-
end
-
end
-
end
-
end
-
1
require 'epub/searcher/result'
-
1
require 'epub/searcher/publication'
-
1
require 'epub/searcher/xhtml'
-
-
1
module EPUB
-
1
module Searcher
-
1
class << self
-
1
def search_text(epub, word, **options)
-
Publication.search_text(epub.package, word, options)
-
end
-
-
1
def search_element(epub, css: nil, xpath: nil, namespaces: {})
-
Publication.search_element(epub.package, css: css, xpath: xpath, namespaces: namespaces)
-
end
-
-
1
def search_by_cfi(epub, cfi)
-
Publication.search_by_cfi(epub.package, cfi)
-
end
-
end
-
end
-
end
-
1
require 'epub/publication'
-
1
require "epub/parser/xml_document"
-
-
1
module EPUB
-
1
module Searcher
-
1
class Publication
-
1
using Parser::XMLDocument::Refinements
-
-
1
class << self
-
1
def search_text(package, word, **options)
-
3
new(package).search_text(word, **options)
-
end
-
-
1
def search_element(package, css: nil, xpath: nil, namespaces: {})
-
3
new(package).search_element(css: css, xpath: xpath, namespaces: namespaces)
-
end
-
-
1
def search_by_cfi(package, cfi)
-
new(package).search_by_cfi(cfi)
-
end
-
end
-
-
1
def initialize(package)
-
6
@package = package
-
end
-
-
# @return [Array<Result>]
-
1
def search_text(word, algorithm: :seamless)
-
3
results = []
-
-
3
spine = @package.spine
-
3
spine_step = Result::Step.new(:element, 2, {:name => 'spine', :id => spine.id})
-
3
spine.each_itemref.with_index do |itemref, index|
-
15
itemref_step = Result::Step.new(:itemref, index, {:id => itemref.id})
-
15
XHTML::ALGORITHMS[algorithm].search_text(Parser::XMLDocument.new(itemref.item.read), word).each do |sub_result|
-
6
results << Result.new([spine_step, itemref_step] + sub_result.parent_steps, sub_result.start_steps, sub_result.end_steps)
-
end
-
end
-
-
3
results
-
end
-
-
# @todo: Refactoring
-
# @return [Array<Hash>] An array of rearch results. Each result is composed of:
-
# * +:element+: [REXML::Element, Oga::XML::Element, Nokogiri::XML::ELement] Found element
-
# * +:itemref+: [EPUB::Publication::Package::Spine::Itemref] Itemref that element's document belongs to
-
# * +:location+: [EPUB::CFI::Location] CFI that indicates the element
-
# * +:package+: [EPUB::Publication::Package] Package that the element belongs to
-
1
def search_element(css: nil, xpath: nil, namespaces: {})
-
3
raise ArgumentError, 'Both css and xpath are nil' if css.nil? && xpath.nil?
-
-
3
namespaces = EPUB::NAMESPACES.merge(namespaces)
-
3
results = []
-
-
3
spine_step = EPUB::CFI::Step.new((EPUB::Publication::Package::CONTENT_MODELS.index(:spine) + 1) * 2)
-
3
@package.spine.each_itemref.with_index do |itemref, index|
-
15
assertion = itemref.id ? EPUB::CFI::IDAssertion.new(itemref.id) : nil
-
15
itemref_step = EPUB::CFI::Step.new((index + 1) * 2, assertion)
-
15
path_to_itemref = EPUB::CFI::Path.new([spine_step, itemref_step])
-
15
content_document = itemref.item.content_document
-
15
next unless content_document
-
9
elems = if xpath
-
6
doc = Parser::XMLDocument.new(content_document.read)
-
6
doc.each_element_by_xpath(xpath, namespaces)
-
else
-
begin
-
3
doc = content_document.nokogiri
-
rescue LoadError
-
raise "#{self.class}##{__method__} with `css` argument requires Nokogiri gem for now. Install Nokogiri and then try again."
-
end
-
3
doc.css(css)
-
end
-
9
elems.each do |elem|
-
22
path = find_path(elem)
-
22
results << {
-
location: EPUB::CFI::Location.new([path_to_itemref, path]),
-
package: @package,
-
itemref: itemref,
-
element: elem
-
}
-
end
-
end
-
-
3
results
-
end
-
-
# @note Currenty can handle only location CFI without offset
-
# @todo Use XHTML module
-
# @todo Handle CFI with offset
-
# @todo Handle range CFI
-
# @param [EPUB::CFI] cfi
-
# @return [Array] Path in EPUB Rendition
-
1
def search_by_cfi(cfi)
-
path_in_package = cfi.paths.first
-
spine = @package.spine
-
model = [@package.metadata, @package.manifest, spine, @package.guide, @package.bindings].compact[path_in_package.steps.first.value / 2 - 1]
-
raise NotImplementedError, "Currently, #{__method__} supports spine only(#{cfi})" unless model == spine
-
raise ArgumentError, "Cannot identify <itemref>'s child" if path_in_package.steps.length > 2
-
-
step_to_itemref = path_in_package.steps[1]
-
itemref = spine.itemrefs[step_to_itemref.value / 2 - 1]
-
-
doc = itemref.item.content_document.nokogiri
-
path_in_doc = cfi.paths[1]
-
current_node = doc.root
-
path_in_doc.steps.each do |step|
-
if step.element?
-
current_node = current_node.elements.to_a[step.value / 2 - 1]
-
else
-
element_index = (step.value - 1) / 2 - 1
-
if element_index == -1
-
current_node = current_node.children.first
-
else
-
prev = current_node.elements.to_a[element_index]
-
break unless prev
-
current_node = prev.next_sibling
-
break unless current_node
-
end
-
end
-
end
-
-
raise NotImplementedError, "Currently, #{__method__} doesn't support deeper DOM tree such as including <iframe>" if cfi.paths[2]
-
-
[itemref, current_node]
-
end
-
-
1
private
-
-
1
def find_path(elem)
-
22
steps = []
-
22
until elem.parent.document?
-
148
index = elem.parent.elements.to_a.index(elem)
-
148
id_attr = elem.attribute_with_prefix("id")
-
148
assertion = id_attr ? EPUB::CFI::IDAssertion.new(id_attr) : nil
-
148
steps.unshift EPUB::CFI::Step.new((index + 1) * 2, assertion)
-
148
elem = elem.parent
-
end
-
22
EPUB::CFI::Path.new(steps)
-
end
-
end
-
end
-
end
-
1
require 'epub/cfi'
-
-
1
module EPUB
-
1
module Searcher
-
1
class Result
-
1
class << self
-
# @example
-
# Result.aggregate_step_intersection([a, b, c], [a, b, d]) # => [[a, b], [c], [d]]
-
# @example
-
# Result.aggregate_step_intersection([a, b, c], [a, d, c]) # => [[a], [b, c], [d, c]]
-
# # Note that c here is not included in the first element of returned value.
-
# @param steps1 [Array<Step>, Array<Array>]
-
# @param steps2 [Array<Step>, Array<Array>]
-
# @return [Array<Array<Array>>] Three arrays:
-
# 1. "intersection" of +steps1+ and +steps2+. "intersection" here is not the term of mathmatics
-
# 2. remaining steps of +steps1+
-
# 3. remaining steps of +steps2+
-
1
def aggregate_step_intersection(steps1, steps2)
-
13
intersection = []
-
13
steps1_remaining = []
-
13
steps2_remaining = []
-
13
broken = false
-
13
steps1.zip steps2 do |step1, step2|
-
44
broken = true unless step1 && step2 && step1 == step2
-
44
if broken
-
1
steps1_remaining << step1 unless step1.nil?
-
1
steps2_remaining << step2 unless step2.nil?
-
else
-
43
intersection << step1
-
end
-
end
-
-
13
[intersection, steps1_remaining, steps2_remaining]
-
end
-
end
-
-
1
attr_reader :parent_steps, :start_steps, :end_steps
-
-
# @param parent_steps [Array<Step>] common steps between start and end
-
# @param start_steps [Array<Step>] steps to start from +parent_steps+
-
# @param end_steps [Array<Step>] steps to end from +parent_steps+
-
1
def initialize(parent_steps, start_steps, end_steps)
-
82
@parent_steps, @start_steps, @end_steps = parent_steps, start_steps, end_steps
-
end
-
-
1
def to_cfi
-
3
str = [@parent_steps, @start_steps, @end_steps].collect {|steps|
-
9
steps ? steps.collect(&:to_cfi).join : nil
-
}.compact.join(',')
-
3
EPUB::CFI(str)
-
end
-
-
1
def ==(other)
-
18
[@parent_steps + @start_steps.to_a] == [other.parent_steps + other.start_steps.to_a] and
-
[@parent_steps + @end_steps.to_a] == [other.parent_steps + other.end_steps.to_a]
-
end
-
-
1
class Step
-
1
attr_reader :type, :index, :info
-
-
1
def initialize(type, index, info={})
-
557
@type, @index, @info = type, index, info
-
end
-
-
1
def ==(other)
-
190
self.type == other.type and
-
self.index == other.index and
-
self.info == other.info
-
end
-
-
1
def to_cfi
-
30
case type
-
when :element
-
23
'/%d%s' % [(index + 1) * 2, id_assertion]
-
when :text
-
2
'/%d' % [(index + 1)]
-
when :character
-
4
':%d' % [index]
-
when :itemref
-
1
'/%d%s!' % [(index + 1) * 2, id_assertion]
-
end
-
end
-
-
1
private
-
-
1
def id_assertion
-
24
info[:id] ? "[#{info[:id]}]" : nil
-
end
-
end
-
end
-
end
-
end
-
1
require 'epub'
-
1
require 'epub/parser/xml_document'
-
-
1
module EPUB
-
1
module Searcher
-
1
class XHTML
-
1
using Parser::XMLDocument::Refinements
-
-
1
ALGORITHMS = {}
-
-
1
class << self
-
# @param element [REXML::Element, REXML::Document, Oga::XML::ELement, Oga::XML::Document, Nokogiri::XML::Element, Nokogiri::XML::Document]
-
# @param word [String]
-
# @return [Array<Result>]
-
1
def search_text(element, word)
-
33
new(element.respond_to?(:root) ? element.root : element).search_text(word)
-
end
-
end
-
-
# @param word [String]
-
1
def initialize(element)
-
33
@element = element
-
end
-
-
1
class Restricted < self
-
# @param element [REXML::Element, Oga::XML::Element, Nokogiri::XML::Element]
-
# @return [Array<Result>]
-
1
def search_text(word, element=nil)
-
137
results = []
-
-
137
elem_index = 0
-
137
(element || @element).children.each do |child|
-
313
if child.element?
-
132
child_step = Result::Step.new(:element, elem_index, {:name => child.name, :id => child.attribute_with_prefix('id')})
-
132
if child.name == 'img'
-
5
if child.attribute_with_prefix('alt').index(word)
-
2
results << Result.new([child_step], nil, nil)
-
end
-
else
-
127
search_text(word, child).each do |sub_result|
-
34
results << Result.new([child_step] + sub_result.parent_steps, sub_result.start_steps, sub_result.end_steps)
-
end
-
end
-
132
elem_index += 1
-
181
elsif child.text?
-
181
text_index = elem_index
-
181
char_index = 0
-
181
text_step = Result::Step.new(:text, text_index)
-
181
while char_index = child.text.index(word, char_index)
-
8
results << Result.new([text_step], [Result::Step.new(:character, char_index)], [Result::Step.new(:character, char_index + word.length)])
-
8
char_index += 1
-
end
-
end
-
end
-
-
137
results
-
end
-
end
-
1
ALGORITHMS[:restricted] = Restricted
-
-
1
class Seamless < self
-
1
def initialize(element)
-
23
super
-
23
@indices = nil
-
end
-
-
1
def search_text(word)
-
23
unless @indices
-
23
@indices, @content = build_indices(@element)
-
end
-
23
visit(@indices, @content, word)
-
end
-
-
1
def build_indices(element)
-
151
indices = {}
-
151
content = ''
-
-
151
elem_index = 0
-
151
element.children.each do |child|
-
317
if child.element?
-
133
child_step = [:element, elem_index, {:name => child.name, :id => child.attribute_with_prefix('id')}]
-
133
elem_index += 1
-
133
if child.name == 'img'
-
5
alt = child.attribute_with_prefix('alt')
-
5
next if alt.nil? || alt.empty?
-
5
indices[content.length] = [child_step]
-
5
content << alt
-
else
-
# TODO: Consider block level elements
-
128
content_length = content.length
-
128
sub_indices, sub_content = build_indices(child)
-
# TODO: Pass content_length and child_step to build_indices and remove this block
-
128
sub_indices.each_pair do |sub_pos, child_steps|
-
625
indices[content_length + sub_pos] = [child_step] + child_steps
-
end
-
128
content << sub_content
-
end
-
184
elsif child.text? || child.cdata?
-
184
text_index = elem_index
-
184
text_step = [:text, text_index]
-
184
indices[content.length] = [text_step]
-
184
content << child.content
-
end
-
end
-
-
151
[indices, content]
-
end
-
-
1
private
-
-
1
def visit(indices, content, word)
-
23
results = []
-
23
offsets = indices.keys
-
23
i = 0
-
23
while i = content.index(word, i)
-
14
offset = find_offset(offsets, i)
-
14
start_steps = to_result_steps(indices[offset])
-
14
last_step = start_steps.last
-
14
if last_step.info[:name] == 'img'
-
1
parent_steps = start_steps
-
1
start_steps = end_steps = nil
-
else
-
13
word_length = word.length
-
13
start_char_step = Result::Step.new(:character, i - offset)
-
13
end_offset = find_offset(offsets, i + word_length, true)
-
13
end_steps = to_result_steps(indices[end_offset])
-
13
end_char_step = Result::Step.new(:character, i + word_length - end_offset)
-
13
parent_steps, start_steps, end_steps = Result.aggregate_step_intersection(start_steps, end_steps)
-
13
start_steps << start_char_step
-
13
end_steps << end_char_step
-
end
-
14
results << Result.new(parent_steps, start_steps, end_steps)
-
14
i += 1
-
end
-
-
23
results
-
end
-
-
# Find max offset greater than or equal to index
-
# @param offsets [Array<Integer>] keys of indices
-
# @param index [Integer] position of search word in content string
-
# @todo: more efficient algorithm
-
1
def find_offset(offsets, index, for_end_position=false)
-
27
comparison_operator = for_end_position ? :< : :<=
-
27
l = offsets.length
-
27
offset_index = (0..l).bsearch {|i|
-
99
o = offsets[l - i]
-
99
next false unless o
-
88
o.send(comparison_operator, index)
-
}
-
27
offsets[l - offset_index]
-
end
-
-
1
def to_result_steps(steps)
-
121
steps.map {|step| Result::Step.new(*step)}
-
end
-
end
-
1
ALGORITHMS[:seamless] = Seamless
-
end
-
end
-
end