# encoding: UTF-8
require_relative 'spine_item_processor'
require_relative 'font_icon_map'
module Asciidoctor
module Epub3
#WordJoiner = [8288].pack 'U*'
WordJoiner = [65279].pack 'U*'
# Public: The main converter for the epub3 backend that handles packaging the
# EPUB3 or KF8 publication file.
class Converter
include ::Asciidoctor::Converter
include ::Asciidoctor::Writer
register_for 'epub3'
def initialize backend, opts
super
basebackend 'html'
outfilesuffix '.epub' # dummy outfilesuffix since it may be .mobi
htmlsyntax 'xml'
@validate = false
@extract = false
end
def convert spine_doc, name = nil
@validate = true if spine_doc.attr? 'ebook-validate'
@extract = true if spine_doc.attr? 'ebook-extract'
Packager.new spine_doc, (spine_doc.references[:spine_items] || [spine_doc]), spine_doc.attributes['ebook-format'].to_sym
end
# FIXME we have to package in write because we don't have access to target before this point
def write packager, target
# NOTE we use dirname of target since filename is calculated automatically
packager.package validate: @validate, extract: @extract, to_dir: (::File.dirname target)
nil
end
end
# Public: The converter for the epub3 backend that converts the individual
# content documents in an EPUB3 publication.
class ContentConverter
include ::Asciidoctor::Converter
register_for 'epub3-xhtml5'
WordJoiner = Epub3::WordJoiner
EOL = "\n"
NoBreakSpace = ' '
ThinNoBreakSpace = ' '
RightAngleQuote = '›'
XmlElementRx = /<\/?.+?>/
CharEntityRx = /&#(\d{2,5});/
NamedEntityRx = /&([A-Z]+);/
UppercaseTagRx = /<(\/)?([A-Z]+)>/
FromHtmlSpecialCharsMap = {
'<' => '<',
'>' => '>',
'&' => '&'
}
FromHtmlSpecialCharsRx = /(?:#{FromHtmlSpecialCharsMap.keys * '|'})/
ToHtmlSpecialCharsMap = {
'&' => '&',
'<' => '<',
'>' => '>'
}
ToHtmlSpecialCharsRx = /[#{ToHtmlSpecialCharsMap.keys.join}]/
OpenParagraphTagRx = /^
/
CloseParagraphTagRx = /<\/p>$/
def initialize backend, opts
super
basebackend 'html'
outfilesuffix '.xhtml'
htmlsyntax 'xml'
@xrefs_used = ::Set.new
@icon_names = []
end
def convert node, name = nil
if respond_to?(name ||= node.node_name)
send name, node
else
warn %(conversion missing in epub3 backend for #{name})
end
end
# TODO aggregate authors of spine document into authors attribute(s) on main document
def navigation_document node, spine
doctitle_sanitized = ((node.doctitle sanitize: true) || (node.attr 'untitled-label')).gsub WordJoiner, ''
lines = [%(
#{doctitle_sanitized}
#{doctitle_sanitized}
)
lines * EOL
end
def document node
docid = node.id
if (doctitle = node.doctitle)
doctitle_sanitized = (node.doctitle sanitize: :sgml).gsub WordJoiner, ''
if doctitle.include? ': '
title, _, subtitle = doctitle.rpartition ': '
else
# HACK until we get proper handling of title-only in CSS
title = ''
subtitle = doctitle
end
else
# HACK until we get proper handling of title-only in CSS
title = ''
subtitle = node.attr 'untitled-label'
end
subtitle_formatted = subtitle.gsub(WordJoiner, '').split(' ').map {|w| %(#{w}) } * ' '
title_upper = title.upcase
# FIXME make this uppercase routine more intelligent, less fragile
subtitle_formatted_upper = subtitle_formatted.upcase
.gsub(UppercaseTagRx) { %(<#{$1}#{$2.downcase}>) }
.gsub(NamedEntityRx) { %(&#{$1.downcase};) }
author = node.attr 'author'
username = node.attr 'username', 'default'
# FIXME needs to resolve to the imagesdir of the spine document, not this document
#imagesdir = (node.attr 'imagesdir', '.').chomp '/'
#imagesdir = (imagesdir == '.' ? nil : %(#{imagesdir}/))
imagesdir = 'images/'
mark_last_paragraph node
content = node.content
# NOTE must run after content is resolved
# NOTE pubtree requires icon CSS to be repeated inside (or in a linked stylesheet); perhaps create dynamic CSS file?
icon_css = unless @icon_names.empty?
icon_defs = @icon_names.map {|name|
%(.i-#{name}::before { content: "#{FontIconMap[name.tr('-', '_').to_sym]}"; })
} * EOL
%(
)
end
# NOTE kindlegen seems to mangle the element, so we wrap its content in a div
lines = [%(
#{doctitle_sanitized}
#{icon_css}
#{icon_css && (icon_css.sub '