require_relative 'core_ext/string' autoload :FileUtils, 'fileutils' autoload :Open3, 'open3' autoload :Shellwords, 'shellwords' module Asciidoctor module Epub3 module GepubBuilderMixin DATA_DIR = ::File.expand_path(::File.join ::File.dirname(__FILE__), '..', '..', 'data') SAMPLES_DIR = ::File.join DATA_DIR, 'samples' CharEntityRx = ContentConverter::CharEntityRx XmlElementRx = ContentConverter::XmlElementRx FromHtmlSpecialCharsMap = ContentConverter::FromHtmlSpecialCharsMap FromHtmlSpecialCharsRx = ContentConverter::FromHtmlSpecialCharsRx CsvDelimiterRx = /\s*,\s*/ DefaultCoverImage = 'images/default-cover.png' ImageMacroRx = /^image::?(.*?)\[(.*?)\]$/ ImgSrcScanRx = / '@import url("epub3-proxied.css");'.to_ios file 'styles/epub3-css3-only.css' => '@import url("epub3-css3-only-proxied.css");'.to_ios file 'styles/epub3-proxied.css' => (builder.postprocess_css_file ::File.join(workdir, 'epub3.css'), format) file 'styles/epub3-css3-only-proxied.css' => (builder.postprocess_css_file ::File.join(workdir, 'epub3-css3-only.css'), format) else file 'styles/epub3.css' => (builder.postprocess_css_file ::File.join(workdir, 'epub3.css'), format) file 'styles/epub3-css3-only.css' => (builder.postprocess_css_file ::File.join(workdir, 'epub3-css3-only.css'), format) end end resources do font_files, font_css = builder.select_fonts ::File.join(DATA_DIR, 'styles/epub3-fonts.css'), (doc.attr 'scripts', 'latin') file 'styles/epub3-fonts.css' => font_css unless font_files.empty? # NOTE metadata property in oepbs package manifest doesn't work; must use proprietary iBooks file instead #(@book.metadata.add_metadata 'meta', 'true')['property'] = 'ibooks:specified-fonts' unless format == :kf8 builder.optional_file 'META-INF/com.apple.ibooks.display-options.xml' => ' '.to_ios unless format == :kf8 with_media_type 'application/x-font-ttf' do font_files.each do |font_file| file font_file => ::File.join(DATA_DIR, font_file) end end end end nil end def add_cover_image doc imagesdir = (doc.attr 'imagesdir', '.').chomp '/' imagesdir = (imagesdir == '.' ? nil : %(#{imagesdir}/)) if (image_path = doc.attr 'front-cover-image') image_attrs = {} if (image_path.include? ':') && image_path =~ ImageMacroRx if image_path.start_with? 'image::' warn %(asciidoctor: WARNING: deprecated block macro syntax detected in front-cover-image attribute) end image_path = %(#{imagesdir}#{$1}) (::Asciidoctor::AttributeList.new $2).parse_into image_attrs, %w(alt width height) unless $2.empty? end workdir = (workdir = doc.attr 'docdir').nil_or_empty? ? '.' : workdir if ::File.readable?(::File.join workdir, image_path) unless !image_attrs.empty? && (width = image_attrs['width']) && (height = image_attrs['height']) width, height = 1050, 1600 end else warn %(asciidoctor: ERROR: front cover image not found or readable: #{image_path}) image_path = nil end end unless image_path image_path, workdir, width, height = DefaultCoverImage, DATA_DIR, 1050, 1600 end resources do cover_image %(#{imagesdir}jacket/cover#{::File.extname image_path}) => (::File.join workdir, image_path) @last_defined_item.tap do |last_item| last_item['width'] = width last_item['height'] = height end end nil end # NOTE must be called within the ordered block def add_cover_page doc, spine_builder, manifest cover_item_attrs = manifest.items['item_cover'].instance_variable_get :@attributes href = cover_item_attrs['href'] # NOTE we only store width and height temporarily to pass through the values width = cover_item_attrs.delete 'width' height = cover_item_attrs.delete 'height' # NOTE SVG wrapper maintains aspect ratio and confines image to view box content = %( #{sanitize_doctitle_xml doc, :cdata} ).to_ios # Gitden expects a cover.xhtml, so add it to the spine spine_builder.file 'cover.xhtml' => content assigned_id = (spine_builder.instance_variable_get :@last_defined_item).item.id spine_builder.id 'cover' # clearly a deficiency of gepub that it does not match the id correctly # FIXME can we move this hack elsewhere? @book.spine.itemref_by_id[assigned_id].idref = 'cover' nil end def add_images_from_front_matter (::File.read 'front-matter.html').scan ImgSrcScanRx do resources do file $1 end end if ::File.file? 'front-matter.html' nil end def add_front_matter_page doc, spine_builder if ::File.file? 'front-matter.html' front_matter_content = ::File.read 'front-matter.html' spine_builder.file 'front-matter.xhtml' => (postprocess_xhtml front_matter_content, @format) unless (spine_builder.property? 'svg') || SvgImgSniffRx !~ front_matter_content spine_builder.add_property 'svg' end end nil end # FIXME add inline images def add_content_images doc, images docimagesdir = (doc.attr 'imagesdir', '.').chomp '/' docimagesdir = (docimagesdir == '.' ? nil : %(#{docimagesdir}/)) workdir = (workdir = doc.attr 'docdir').nil_or_empty? ? '.' : workdir resources workdir: workdir do images.each do |image| imagesdir = (image.document.attr 'imagesdir', '.').chomp '/' imagesdir = (imagesdir == '.' ? nil : %(#{imagesdir}/)) image_path = %(#{imagesdir}#{image.attr 'target'}) if image_path.start_with? %(#{docimagesdir}jacket/cover.) warn %(asciidoctor: WARNING: image path is reserved for cover artwork: #{image_path}; skipping image found in content) elsif ::File.readable? image_path file image_path else warn %(asciidoctor: ERROR: image not found or not readable: #{image_path}) end end end nil end def add_profile_images doc, usernames imagesdir = (doc.attr 'imagesdir', '.').chomp '/' imagesdir = (imagesdir == '.' ? nil : %(#{imagesdir}/)) resources do file %(#{imagesdir}avatars/default.jpg) => ::File.join(DATA_DIR, 'images/default-avatar.jpg') file %(#{imagesdir}headshots/default.jpg) => ::File.join(DATA_DIR, 'images/default-headshot.jpg') end workdir = (workdir = doc.attr 'docdir').nil_or_empty? ? '.' : workdir resources do usernames.each do |username| avatar = %(#{imagesdir}avatars/#{username}.jpg) if ::File.readable?(resolved_avatar = ::File.join(workdir, avatar)) file avatar => resolved_avatar else warn %(asciidoctor: ERROR: avatar for #{username} not found or readable: #{avatar}; falling back to default avatar) file avatar => ::File.join(DATA_DIR, 'images/default-avatar.jpg') end headshot = %(#{imagesdir}headshots/#{username}.jpg) if ::File.readable?(resolved_headshot = ::File.join(workdir, headshot)) file headshot => resolved_headshot elsif doc.attr? 'builder', 'editions' warn %(asciidoctor: ERROR: headshot for #{username} not found or readable: #{headshot}; falling back to default headshot) file headshot => ::File.join(DATA_DIR, 'images/default-headshot.jpg') end end end nil end def add_content doc builder, spine, format = self, @spine, @format workdir = (doc.attr 'docdir').nil_or_empty? ? '.' : workdir resources workdir: workdir do extend GepubResourceBuilderMixin builder.add_images_from_front_matter builder.add_nav_doc doc, self, spine, format builder.add_ncx_doc doc, self, spine ordered do builder.add_cover_page doc, self, @book.manifest unless format == :kf8 builder.add_front_matter_page doc, self spine.each_with_index do |item, i| file %(#{item.id || (item.attr 'docname')}.xhtml) => (builder.postprocess_xhtml item.convert, format) add_property 'svg' if ((item.attr 'epub-properties') || []).include? 'svg' # QUESTION reenable? #linear 'yes' if i == 0 end end end nil end def add_nav_doc doc, spine_builder, spine, format spine_builder.nav 'nav.xhtml' => (postprocess_xhtml nav_doc(doc, spine), format) spine_builder.id 'nav' nil end # TODO aggregate authors of spine document into authors attribute(s) on main document def nav_doc doc, spine lines = [%( #{sanitize_doctitle_xml doc, :cdata}

#{sanitize_doctitle_xml doc, :pcdata}

) lines * EOL end def nav_level items, depth, state = {} lines = [] lines << '
    ' items.each do |item| #index = (state[:index] = (state.fetch :index, 0) + 1) if item.context == :document # NOTE we sanitize the chapter titles because we use formatting to control layout item_label = sanitize_doctitle_xml item, :cdata item_href = (state[:content_doc_href] = %(#{item.id || (item.attr 'docname')}.xhtml)) else item_label = sanitize_xml item.title, :pcdata item_href = %(#{state[:content_doc_href]}##{item.id}) end lines << %(
  1. #{item_label}) unless depth == 0 || (child_sections = item.sections).empty? lines << (nav_level child_sections, depth - 1, state) lines << '
  2. ' else lines[-1] = %(#{lines[-1]}) end state.delete :content_doc_href if item.context == :document end lines << '
' lines * EOL end # NOTE gepub doesn't support building a ncx TOC with depth > 1, so do it ourselves def add_ncx_doc doc, spine_builder, spine spine_builder.file 'toc.ncx' => (ncx_doc doc, spine).to_ios spine_builder.id 'ncx' nil end def ncx_doc doc, spine # TODO populate docAuthor element based on unique authors in work lines = [%( %{depth} #{sanitize_doctitle_xml doc, :cdata} )] lines << (ncx_level spine, [(doc.attr 'toclevels', 1).to_i, 0].max, state = {}) lines[0] = lines[0].sub '%{depth}', %() lines << %( ) lines * EOL end def ncx_level items, depth, state = {} lines = [] state[:max_depth] = (state.fetch :max_depth, 0) + 1 items.each do |item| index = (state[:index] = (state.fetch :index, 0) + 1) if item.context == :document item_id = %(nav_#{index}) item_label = sanitize_doctitle_xml item, :cdata item_href = (state[:content_doc_href] = %(#{item.id || (item.attr 'docname')}.xhtml)) else item_id = %(nav_#{index}) item_label = sanitize_xml item.title, :cdata item_href = %(#{state[:content_doc_href]}##{item.id}) end lines << %() lines << %(#{item_label}) lines << %() unless depth == 0 || (child_sections = item.sections).empty? lines << (ncx_level child_sections, depth - 1, state) end lines << %() state.delete :content_doc_href if item.context == :document end lines * EOL end def collect_keywords doc, spine ([doc] + spine).map do |item| if item.attr? 'keywords' (item.attr 'keywords').split CsvDelimiterRx else [] end end.flatten.uniq end # Swap fonts in CSS based on the value of the document attribute 'scripts', # then return the list of fonts as well as the font CSS. def select_fonts filename, scripts = 'latin' font_css = ::File.read(filename) font_css = font_css.gsub(/(?<=-)latin(?=\.ttf\))/, scripts) unless scripts == 'latin' font_list = font_css.scan(/url\(\.\.\/(.+\.ttf)\);$/).flatten return [font_list, font_css.to_ios] end def postprocess_css_file filename, format return filename unless format == :kf8 postprocess_css ::File.read(filename), format end def postprocess_css content, format return content.to_ios unless format == :kf8 # TODO convert regular expressions to constants content .gsub(/^ -webkit-column-break-.*\n/, '') .gsub(/^ max-width: .*\n/, '') .to_ios end def postprocess_xhtml_file filename, format return filename unless format == :kf8 postprocess_xhtml ::File.read(filename), format end # NOTE Kindle requires that # # be converted to # def postprocess_xhtml content, format return content.to_ios unless format == :kf8 # TODO convert regular expressions to constants content .gsub(//, '') .gsub(/]+) style="width: (\d\d)%;"/, '.*?<\/script>\n?/m, '') .to_ios end end module GepubResourceBuilderMixin # Add missing method to builder to add a property to last defined item def add_property property @last_defined_item.add_property property end # Add helper method to builder to check if property is set on last defined item def property? property (@last_defined_item['properties'] || []).include? property end end class Packager KINDLEGEN = ENV['KINDLEGEN'] || 'kindlegen' EPUBCHECK = ENV['EPUBCHECK'] || %(epubcheck#{::Gem.win_platform? ? '.bat' : '.sh'}) EpubExtensionRx = /\.epub$/i KindlegenCompression = ::Hash['0', '-c0', '1', '-c1', '2', '-c2', 'none', '-c0', 'standard', '-c1', 'huffdic', '-c2'] def initialize spine_doc, spine, format = :epub3, options = {} @document = spine_doc @spine = spine || [] @format = format end def package options = {} doc = @document spine = @spine fmt = @format target = options[:target] dest = File.dirname target images = spine.map {|item| item.find_by context: :image }.compact.flatten .uniq {|img| %(#{(img.document.attr 'imagesdir', '.').chomp '/'}/#{img.attr 'target'}) } # FIXME authors should be aggregated already on parent document authors = if doc.attr? 'authors' (doc.attr 'authors').split(GepubBuilderMixin::CsvDelimiterRx).concat(spine.map {|item| item.attr 'author' }).uniq else [] end builder = ::GEPUB::Builder.new do extend GepubBuilderMixin @document = doc @spine = spine @format = fmt @book.epub_backward_compat = (fmt != :kf8) language(doc.attr 'lang', 'en') id 'pub-language' if doc.attr? 'uuid' unique_identifier doc.attr('uuid'), 'pub-identifier', 'uuid' else unique_identifier doc.id, 'pub-identifier', 'uuid' end # replace with next line once the attributes argument is supported #unique_identifier doc.id, 'pub-id', 'uuid', 'scheme' => 'xsd:string' # NOTE we must use :plain_text here since gepub reencodes title(sanitize_doctitle_xml doc, :plain_text) id 'pub-title' # FIXME this logic needs some work if doc.attr? 'publisher' publisher(publisher_name = doc.attr('publisher')) # marc role: Book producer (see http://www.loc.gov/marc/relators/relaterm.html) creator doc.attr('producer', publisher_name), 'bkp' else # NOTE Use producer as both publisher and producer if publisher isn't specified if doc.attr? 'producer' producer_name = doc.attr 'producer' publisher producer_name # marc role: Book producer (see http://www.loc.gov/marc/relators/relaterm.html) creator producer_name, 'bkp' # NOTE Use author as creator if both publisher or producer are absent elsif doc.attr? 'author' # marc role: Author (see http://www.loc.gov/marc/relators/relaterm.html) creator doc.attr('author'), 'aut' end end if doc.attr? 'creator' # marc role: Creator (see http://www.loc.gov/marc/relators/relaterm.html) creator doc.attr('creator'), 'cre' else # marc role: Manufacturer (see http://www.loc.gov/marc/relators/relaterm.html) # QUESTION should this be bkp? creator 'Asciidoctor', 'mfr' end # TODO getting author list should be a method on Asciidoctor API contributors(*authors) if doc.attr? 'revdate' # TODO ensure this is a real date date(doc.attr 'revdate') else date ::Time.now.strftime('%Y-%m-%dT%H:%M:%SZ') end if doc.attr? 'description' description(doc.attr 'description') end (collect_keywords doc, spine).each do |s| subject s end if doc.attr? 'source' source(doc.attr 'source') end if doc.attr? 'copyright' rights(doc.attr 'copyright') end #add_metadata 'ibooks:specified-fonts', true add_theme_assets doc add_cover_image doc if (doc.attr 'publication-type', 'book') != 'book' usernames = spine.map {|item| item.attr 'username' }.compact.uniq add_profile_images doc, usernames end # QUESTION move add_content_images to add_content method? add_content_images doc, images add_content doc end ::FileUtils.mkdir_p dest unless ::File.directory? dest epub_file = fmt == :kf8 ? %(#{::Asciidoctor::Helpers.rootname target}-kf8.epub) : target builder.generate_epub epub_file puts %(Wrote #{fmt.upcase} to #{epub_file}) if $VERBOSE if options[:extract] extract_dir = epub_file.sub EpubExtensionRx, '' ::FileUtils.remove_dir extract_dir if ::File.directory? extract_dir ::Dir.mkdir extract_dir ::Dir.chdir extract_dir do ::Zip::File.open epub_file do |entries| entries.each do |entry| next unless entry.file? unless (entry_dir = ::File.dirname entry.name) == '.' || (::File.directory? entry_dir) ::FileUtils.mkdir_p entry_dir end entry.extract end end end puts %(Extracted #{fmt.upcase} to #{extract_dir}) if $VERBOSE end if fmt == :kf8 # QUESTION shouldn't we validate this epub file too? distill_epub_to_mobi epub_file, target, options[:compress] elsif options[:validate] validate_epub epub_file end end def distill_epub_to_mobi epub_file, target, compress kindlegen_cmd = KINDLEGEN unless ::File.executable? kindlegen_cmd require 'kindlegen' unless defined? ::Kindlegen kindlegen_cmd = ::Kindlegen.command end mobi_file = ::File.basename(target.sub EpubExtensionRx, '.mobi') compress_flag = KindlegenCompression[compress ? (compress.empty? ? '1' : compress.to_s) : '0'] cmd = [kindlegen_cmd, '-dont_append_source', compress_flag, '-o', mobi_file, epub_file].compact ::Open3.popen2e(::Shellwords.join cmd) {|input, output, wait_thr| output.each {|line| puts line } unless $VERBOSE.nil? } puts %(Wrote MOBI to #{::File.join ::File.dirname(epub_file), mobi_file}) if $VERBOSE end def validate_epub epub_file epubcheck_cmd = EPUBCHECK unless ::File.executable? epubcheck_cmd epubcheck_cmd = ::Gem.bin_path 'epubcheck', 'epubcheck' end # NOTE epubcheck gem doesn't support epubcheck command options; enable -quiet once supported ::Open3.popen2e(::Shellwords.join [epubcheck_cmd, epub_file]) {|input, output, wait_thr| output.each {|line| puts line } unless $VERBOSE.nil? } end end end end