jekyll-epub 0.0.1

data/lib/jekyll/epub.rb

@@ -0,0 +1,242 @@
+require 'rubygems'
+require 'jekyll'
+require 'uuid'
+require 'mime/types'
+require 'jekyll/tags/epub'
+
+module Jekyll
+  class StaticFile #:nodoc:
+    # This is a Jekyll[http://jekyllrb.com] extension
+    #
+    # Give the URL of a static file
+    def url #:nodoc:
+      File.join( @dir, @name )
+    end
+  end
+  
+  class Site #:nodoc:    
+    def all
+      if self.config["epub"]["pages-order"]
+        pages + posts
+      else
+        posts + pages
+      end
+    end
+    
+    # This is a Jekyll[http://jekyllrb.com] extension
+    #
+    # Same as Site::process but generate the epub. 
+    def epub #:nodoc:
+      self.reset
+      self.read
+      
+      # Change layout to use epub
+      self.layouts.each do |name, layout|
+        self.layouts[name].data['layout'] = layout.data['epub'] if layout.data['epub']
+      end
+      
+      # Generate specifics epub files
+      FileUtils.rm_rf( self.dest )
+      self.package_epub
+      
+      self.render
+      
+      # Apply filters
+      self.apply_epub_filters( pages )
+      self.apply_epub_filters( posts )
+      
+      self.write
+      
+      # Create epub file
+      self.zip
+    end
+    
+    # This is a Jekyll[http://jekyllrb.com] extension
+    #
+    # Generate the specifics epub files : content.opf, toc.ncx, mimetype, 
+    # page-template.xpgt and META-INF/container.xml
+    def package_epub #:nodoc:
+      files = []
+      order = 0
+      
+      # Check for cover image
+      if self.config["epub"]["cover-image"]
+        self.config["epub"]["cover"] = {
+          "image" => self.config["epub"]["cover-image"],
+          "mime" => MIME::Types.type_for( self.config["epub"]["cover-image"] ).to_s
+        }
+      end
+      
+      (all + static_files).each do |p|
+        url = p.url.gsub( /^\//, "" )
+        next if url == self.config["epub"]["cover-image"]
+        mime = MIME::Types.type_for( url ).to_s
+        mime = "application/xhtml+xml" if mime == "text/html"     
+        next if self.config['exclude'].include?(File.basename( url ))
+        
+        if mime == "" then
+          $stderr.puts "** Ignore file #{url}, unknown mime type!"
+          next
+        end
+        
+        file_data = {
+          'id' => url.gsub( /\/|\./, "_" ),
+          'url' => url,
+          'mime' => mime
+        }
+        begin
+          p.data['layout'] = p.data['epub'] if p.data['epub']
+          file_data['title'] = p.data["title"]
+          file_data['order'] = order
+          order += 1
+        rescue => e
+          if file_data['mime'] == "text/html"
+            $stderr.puts "** Ignore file #{url} : #{e.message}"
+            next
+          end
+        end
+        files << file_data
+      end
+      
+      FileUtils.mkdir_p(self.dest)
+      FileUtils.mkdir_p(File.join( self.dest, "META-INF" ))
+      
+      write_epub_file( "content.opf", files )
+      write_epub_file( "toc.ncx", files )
+      write_epub_file( "mimetype", files )
+      write_epub_file( "page-template.xpgt", files )
+      write_epub_file( File.join( "META-INF", "container.xml" ) , files )
+      if self.config["epub"]["cover-image"]
+        write_epub_file( "cover.xhtml", files )
+      end
+    end
+    
+    # This is a Jekyll[http://jekyllrb.com] extension
+    #
+    # Write a specific epub file using Liquid. See Jekyll::Site::package_epub
+    def write_epub_file( tmpl, files ) #:nodoc:
+      $stderr.puts "** Create #{tmpl}"
+      template_file = File.join( File.expand_path( File.dirname( __FILE__ ) ), "epub", "templates", tmpl )
+      template_content = Liquid::Template.parse(File.open(template_file).read).render( 'epub' => self.config['epub'], 'files' => files )
+      File.open( File.join( self.dest, tmpl ), "w+" ).puts template_content
+    end
+  
+    # This is a Jekyll[http://jekyllrb.com] extension
+    #
+    # Very simple post-filters
+    #
+    # This method need to be rewritten and add the possibility to use user's defined filters
+    def apply_epub_filters( files ) #:nodoc:
+      files.each do |file|
+        file.output = file.output.gsub( /(src\s*=\s*['|"])\//, '\1' )
+        file.output = file.output.gsub( /(href\s*=\s*['|"])\//, '\1' )
+
+        # Remove all <script> tags
+        file.output = file.output.gsub( /<script[^>]*>[^<\/script>]*<\/script>/, "" )
+        file.output = file.output.gsub( /<script[^>]*\/>/, "" )
+        file.output = file.output.gsub( /<noscript>.*<\/noscript>/, "" )
+      end
+    end
+  
+    # This is a Jekyll[http://jekyllrb.com] extension
+    #
+    # Create the epub file...
+    #
+    # WARNING: does not work !!! So please generate the epub file by hand :
+    #
+    #  cd _epub/src
+    #  zip -Xr9D MyBook.epub mimetype *
+    def zip #:nodoc:
+      Dir.chdir( self.dest ) do
+        filename = self.config['epub']['name']
+        filename += ".epub" unless File.extname(filename) == ".epub"
+        $stderr.puts "** Create epub file #{filename} in #{Dir.pwd}..."
+        %x(zip -Xr9D \"#{filename}\" mimetype *)
+      end
+    end
+  end
+  
+  class Epub
+    include Jekyll::Filters
+    
+    DEFAULTS = Jekyll::DEFAULTS.merge( {
+      'destination' => File.join('.', '_epub', 'src'),
+      'permalink'   => '/:title.html',
+      'epub' => {
+        'title' => "My Jekyll Blog",
+        'language' => 'en',
+        'identifier' => UUID.generate
+      }
+    } )
+    
+    # Generate a Jekyll::Epub configuration Hash by merging the default options
+    # with anything in _epub.yml, and adding the given options on top
+    # +override+ is a Hash of config directives
+    #
+    # Returns Hash
+    def self.configuration(override = {})
+      # _epub.yml may override default source location, but until
+      # then, we need to know where to look for _config.yml
+      source = override['source'] || Jekyll::Epub::DEFAULTS['source']
+
+      # Get configuration from <source>/_epub.yml
+      config_file = File.join(source, '_epub.yml')
+      begin
+        config = YAML.load_file(config_file)
+        raise "Invalid configuration - #{config_file}" if !config.is_a?(Hash)
+        $stdout.puts "** Configuration from #{config_file}"
+      rescue => err
+        $stderr.puts "** WARNING: Could not read configuration. Using defaults (and options)."
+        $stderr.puts "\t" + err.to_s
+        config = {}
+      end
+
+      # Merge DEFAULTS < _config.yml < override
+      Jekyll::Epub::DEFAULTS.deep_merge(config).deep_merge(override)
+    end
+    
+    # Generate the epub! All in one!
+    def create( override )
+      options = Jekyll::Epub.configuration( override )
+      
+      site = Jekyll::Site.new(options)
+      site.epub
+      
+      if options['epub']['validate'] == true
+        self.validate( site )
+      end
+    end
+    
+    # A tiny XHTML validator.
+    # 
+    # If you want to validate your xhtml files, juste add 
+    #
+    #  epub:
+    #    validate: true
+    #
+    # in your _epub.yml file.
+    def validate( site )
+      begin
+        require 'xml/libxml'
+      rescue => e
+        $stderr.puts "** WARNING: libxml-ruby is not installed. Can't validate!"
+        return
+      end
+      
+      dtd_file = File.join( File.expand_path( File.dirname( __FILE__ ) ), "epub", "dtd", "xhtml1-strict.dtd" )
+      dtd = XML::Dtd.new("-//W3C//DTD XHTML 1.0 Strict//EN", dtd_file)
+      
+      (site.posts + site.pages).each do |path|
+        file = File.join( site.dest, path.url )
+        $stderr.puts "** Validate #{file}."
+        begin
+          doc = XML::Document.file(file)
+          doc.validate(dtd)
+        rescue => e
+          $stderr.puts e.message
+        end
+      end
+    end
+    
+  end
+end

data/lib/jekyll/epub/dtd/xhtml-lat1.ent

@@ -0,0 +1,196 @@
+<!-- Portions (C) International Organization for Standardization 1986
+     Permission to copy in any form is granted for use with
+     conforming SGML systems and applications as defined in
+     ISO 8879, provided this notice is included in all copies.
+-->
+<!-- Character entity set. Typical invocation:
+    <!ENTITY % HTMLlat1 PUBLIC
+       "-//W3C//ENTITIES Latin 1 for XHTML//EN"
+       "http://www.w3.org/TR/xhtml1/DTD/xhtml-lat1.ent">
+    %HTMLlat1;
+-->
+
+<!ENTITY nbsp   "&#160;"> <!-- no-break space = non-breaking space,
+                                  U+00A0 ISOnum -->
+<!ENTITY iexcl  "&#161;"> <!-- inverted exclamation mark, U+00A1 ISOnum -->
+<!ENTITY cent   "&#162;"> <!-- cent sign, U+00A2 ISOnum -->
+<!ENTITY pound  "&#163;"> <!-- pound sign, U+00A3 ISOnum -->
+<!ENTITY curren "&#164;"> <!-- currency sign, U+00A4 ISOnum -->
+<!ENTITY yen    "&#165;"> <!-- yen sign = yuan sign, U+00A5 ISOnum -->
+<!ENTITY brvbar "&#166;"> <!-- broken bar = broken vertical bar,
+                                  U+00A6 ISOnum -->
+<!ENTITY sect   "&#167;"> <!-- section sign, U+00A7 ISOnum -->
+<!ENTITY uml    "&#168;"> <!-- diaeresis = spacing diaeresis,
+                                  U+00A8 ISOdia -->
+<!ENTITY copy   "&#169;"> <!-- copyright sign, U+00A9 ISOnum -->
+<!ENTITY ordf   "&#170;"> <!-- feminine ordinal indicator, U+00AA ISOnum -->
+<!ENTITY laquo  "&#171;"> <!-- left-pointing double angle quotation mark
+                                  = left pointing guillemet, U+00AB ISOnum -->
+<!ENTITY not    "&#172;"> <!-- not sign = angled dash,
+                                  U+00AC ISOnum -->
+<!ENTITY shy    "&#173;"> <!-- soft hyphen = discretionary hyphen,
+                                  U+00AD ISOnum -->
+<!ENTITY reg    "&#174;"> <!-- registered sign = registered trade mark sign,
+                                  U+00AE ISOnum -->
+<!ENTITY macr   "&#175;"> <!-- macron = spacing macron = overline
+                                  = APL overbar, U+00AF ISOdia -->
+<!ENTITY deg    "&#176;"> <!-- degree sign, U+00B0 ISOnum -->
+<!ENTITY plusmn "&#177;"> <!-- plus-minus sign = plus-or-minus sign,
+                                  U+00B1 ISOnum -->
+<!ENTITY sup2   "&#178;"> <!-- superscript two = superscript digit two
+                                  = squared, U+00B2 ISOnum -->
+<!ENTITY sup3   "&#179;"> <!-- superscript three = superscript digit three
+                                  = cubed, U+00B3 ISOnum -->
+<!ENTITY acute  "&#180;"> <!-- acute accent = spacing acute,
+                                  U+00B4 ISOdia -->
+<!ENTITY micro  "&#181;"> <!-- micro sign, U+00B5 ISOnum -->
+<!ENTITY para   "&#182;"> <!-- pilcrow sign = paragraph sign,
+                                  U+00B6 ISOnum -->
+<!ENTITY middot "&#183;"> <!-- middle dot = Georgian comma
+                                  = Greek middle dot, U+00B7 ISOnum -->
+<!ENTITY cedil  "&#184;"> <!-- cedilla = spacing cedilla, U+00B8 ISOdia -->
+<!ENTITY sup1   "&#185;"> <!-- superscript one = superscript digit one,
+                                  U+00B9 ISOnum -->
+<!ENTITY ordm   "&#186;"> <!-- masculine ordinal indicator,
+                                  U+00BA ISOnum -->
+<!ENTITY raquo  "&#187;"> <!-- right-pointing double angle quotation mark
+                                  = right pointing guillemet, U+00BB ISOnum -->
+<!ENTITY frac14 "&#188;"> <!-- vulgar fraction one quarter
+                                  = fraction one quarter, U+00BC ISOnum -->
+<!ENTITY frac12 "&#189;"> <!-- vulgar fraction one half
+                                  = fraction one half, U+00BD ISOnum -->
+<!ENTITY frac34 "&#190;"> <!-- vulgar fraction three quarters
+                                  = fraction three quarters, U+00BE ISOnum -->
+<!ENTITY iquest "&#191;"> <!-- inverted question mark
+                                  = turned question mark, U+00BF ISOnum -->
+<!ENTITY Agrave "&#192;"> <!-- latin capital letter A with grave
+                                  = latin capital letter A grave,
+                                  U+00C0 ISOlat1 -->
+<!ENTITY Aacute "&#193;"> <!-- latin capital letter A with acute,
+                                  U+00C1 ISOlat1 -->
+<!ENTITY Acirc  "&#194;"> <!-- latin capital letter A with circumflex,
+                                  U+00C2 ISOlat1 -->
+<!ENTITY Atilde "&#195;"> <!-- latin capital letter A with tilde,
+                                  U+00C3 ISOlat1 -->
+<!ENTITY Auml   "&#196;"> <!-- latin capital letter A with diaeresis,
+                                  U+00C4 ISOlat1 -->
+<!ENTITY Aring  "&#197;"> <!-- latin capital letter A with ring above
+                                  = latin capital letter A ring,
+                                  U+00C5 ISOlat1 -->
+<!ENTITY AElig  "&#198;"> <!-- latin capital letter AE
+                                  = latin capital ligature AE,
+                                  U+00C6 ISOlat1 -->
+<!ENTITY Ccedil "&#199;"> <!-- latin capital letter C with cedilla,
+                                  U+00C7 ISOlat1 -->
+<!ENTITY Egrave "&#200;"> <!-- latin capital letter E with grave,
+                                  U+00C8 ISOlat1 -->
+<!ENTITY Eacute "&#201;"> <!-- latin capital letter E with acute,
+                                  U+00C9 ISOlat1 -->
+<!ENTITY Ecirc  "&#202;"> <!-- latin capital letter E with circumflex,
+                                  U+00CA ISOlat1 -->
+<!ENTITY Euml   "&#203;"> <!-- latin capital letter E with diaeresis,
+                                  U+00CB ISOlat1 -->
+<!ENTITY Igrave "&#204;"> <!-- latin capital letter I with grave,
+                                  U+00CC ISOlat1 -->
+<!ENTITY Iacute "&#205;"> <!-- latin capital letter I with acute,
+                                  U+00CD ISOlat1 -->
+<!ENTITY Icirc  "&#206;"> <!-- latin capital letter I with circumflex,
+                                  U+00CE ISOlat1 -->
+<!ENTITY Iuml   "&#207;"> <!-- latin capital letter I with diaeresis,
+                                  U+00CF ISOlat1 -->
+<!ENTITY ETH    "&#208;"> <!-- latin capital letter ETH, U+00D0 ISOlat1 -->
+<!ENTITY Ntilde "&#209;"> <!-- latin capital letter N with tilde,
+                                  U+00D1 ISOlat1 -->
+<!ENTITY Ograve "&#210;"> <!-- latin capital letter O with grave,
+                                  U+00D2 ISOlat1 -->
+<!ENTITY Oacute "&#211;"> <!-- latin capital letter O with acute,
+                                  U+00D3 ISOlat1 -->
+<!ENTITY Ocirc  "&#212;"> <!-- latin capital letter O with circumflex,
+                                  U+00D4 ISOlat1 -->
+<!ENTITY Otilde "&#213;"> <!-- latin capital letter O with tilde,
+                                  U+00D5 ISOlat1 -->
+<!ENTITY Ouml   "&#214;"> <!-- latin capital letter O with diaeresis,
+                                  U+00D6 ISOlat1 -->
+<!ENTITY times  "&#215;"> <!-- multiplication sign, U+00D7 ISOnum -->
+<!ENTITY Oslash "&#216;"> <!-- latin capital letter O with stroke
+                                  = latin capital letter O slash,
+                                  U+00D8 ISOlat1 -->
+<!ENTITY Ugrave "&#217;"> <!-- latin capital letter U with grave,
+                                  U+00D9 ISOlat1 -->
+<!ENTITY Uacute "&#218;"> <!-- latin capital letter U with acute,
+                                  U+00DA ISOlat1 -->
+<!ENTITY Ucirc  "&#219;"> <!-- latin capital letter U with circumflex,
+                                  U+00DB ISOlat1 -->
+<!ENTITY Uuml   "&#220;"> <!-- latin capital letter U with diaeresis,
+                                  U+00DC ISOlat1 -->
+<!ENTITY Yacute "&#221;"> <!-- latin capital letter Y with acute,
+                                  U+00DD ISOlat1 -->
+<!ENTITY THORN  "&#222;"> <!-- latin capital letter THORN,
+                                  U+00DE ISOlat1 -->
+<!ENTITY szlig  "&#223;"> <!-- latin small letter sharp s = ess-zed,
+                                  U+00DF ISOlat1 -->
+<!ENTITY agrave "&#224;"> <!-- latin small letter a with grave
+                                  = latin small letter a grave,
+                                  U+00E0 ISOlat1 -->
+<!ENTITY aacute "&#225;"> <!-- latin small letter a with acute,
+                                  U+00E1 ISOlat1 -->
+<!ENTITY acirc  "&#226;"> <!-- latin small letter a with circumflex,
+                                  U+00E2 ISOlat1 -->
+<!ENTITY atilde "&#227;"> <!-- latin small letter a with tilde,
+                                  U+00E3 ISOlat1 -->
+<!ENTITY auml   "&#228;"> <!-- latin small letter a with diaeresis,
+                                  U+00E4 ISOlat1 -->
+<!ENTITY aring  "&#229;"> <!-- latin small letter a with ring above
+                                  = latin small letter a ring,
+                                  U+00E5 ISOlat1 -->
+<!ENTITY aelig  "&#230;"> <!-- latin small letter ae
+                                  = latin small ligature ae, U+00E6 ISOlat1 -->
+<!ENTITY ccedil "&#231;"> <!-- latin small letter c with cedilla,
+                                  U+00E7 ISOlat1 -->
+<!ENTITY egrave "&#232;"> <!-- latin small letter e with grave,
+                                  U+00E8 ISOlat1 -->
+<!ENTITY eacute "&#233;"> <!-- latin small letter e with acute,
+                                  U+00E9 ISOlat1 -->
+<!ENTITY ecirc  "&#234;"> <!-- latin small letter e with circumflex,
+                                  U+00EA ISOlat1 -->
+<!ENTITY euml   "&#235;"> <!-- latin small letter e with diaeresis,
+                                  U+00EB ISOlat1 -->
+<!ENTITY igrave "&#236;"> <!-- latin small letter i with grave,
+                                  U+00EC ISOlat1 -->
+<!ENTITY iacute "&#237;"> <!-- latin small letter i with acute,
+                                  U+00ED ISOlat1 -->
+<!ENTITY icirc  "&#238;"> <!-- latin small letter i with circumflex,
+                                  U+00EE ISOlat1 -->
+<!ENTITY iuml   "&#239;"> <!-- latin small letter i with diaeresis,
+                                  U+00EF ISOlat1 -->
+<!ENTITY eth    "&#240;"> <!-- latin small letter eth, U+00F0 ISOlat1 -->
+<!ENTITY ntilde "&#241;"> <!-- latin small letter n with tilde,
+                                  U+00F1 ISOlat1 -->
+<!ENTITY ograve "&#242;"> <!-- latin small letter o with grave,
+                                  U+00F2 ISOlat1 -->
+<!ENTITY oacute "&#243;"> <!-- latin small letter o with acute,
+                                  U+00F3 ISOlat1 -->
+<!ENTITY ocirc  "&#244;"> <!-- latin small letter o with circumflex,
+                                  U+00F4 ISOlat1 -->
+<!ENTITY otilde "&#245;"> <!-- latin small letter o with tilde,
+                                  U+00F5 ISOlat1 -->
+<!ENTITY ouml   "&#246;"> <!-- latin small letter o with diaeresis,
+                                  U+00F6 ISOlat1 -->
+<!ENTITY divide "&#247;"> <!-- division sign, U+00F7 ISOnum -->
+<!ENTITY oslash "&#248;"> <!-- latin small letter o with stroke,
+                                  = latin small letter o slash,
+                                  U+00F8 ISOlat1 -->
+<!ENTITY ugrave "&#249;"> <!-- latin small letter u with grave,
+                                  U+00F9 ISOlat1 -->
+<!ENTITY uacute "&#250;"> <!-- latin small letter u with acute,
+                                  U+00FA ISOlat1 -->
+<!ENTITY ucirc  "&#251;"> <!-- latin small letter u with circumflex,
+                                  U+00FB ISOlat1 -->
+<!ENTITY uuml   "&#252;"> <!-- latin small letter u with diaeresis,
+                                  U+00FC ISOlat1 -->
+<!ENTITY yacute "&#253;"> <!-- latin small letter y with acute,
+                                  U+00FD ISOlat1 -->
+<!ENTITY thorn  "&#254;"> <!-- latin small letter thorn,
+                                  U+00FE ISOlat1 -->
+<!ENTITY yuml   "&#255;"> <!-- latin small letter y with diaeresis,
+                                  U+00FF ISOlat1 -->

data/lib/jekyll/epub/dtd/xhtml-special.ent

@@ -0,0 +1,80 @@
+<!-- Special characters for XHTML -->
+
+<!-- Character entity set. Typical invocation:
+     <!ENTITY % HTMLspecial PUBLIC
+        "-//W3C//ENTITIES Special for XHTML//EN"
+        "http://www.w3.org/TR/xhtml1/DTD/xhtml-special.ent">
+     %HTMLspecial;
+-->
+
+<!-- Portions (C) International Organization for Standardization 1986:
+     Permission to copy in any form is granted for use with
+     conforming SGML systems and applications as defined in
+     ISO 8879, provided this notice is included in all copies.
+-->
+
+<!-- Relevant ISO entity set is given unless names are newly introduced.
+     New names (i.e., not in ISO 8879 list) do not clash with any
+     existing ISO 8879 entity names. ISO 10646 character numbers
+     are given for each character, in hex. values are decimal
+     conversions of the ISO 10646 values and refer to the document
+     character set. Names are Unicode names. 
+-->
+
+<!-- C0 Controls and Basic Latin -->
+<!ENTITY quot    "&#34;"> <!--  quotation mark, U+0022 ISOnum -->
+<!ENTITY amp     "&#38;#38;"> <!--  ampersand, U+0026 ISOnum -->
+<!ENTITY lt      "&#38;#60;"> <!--  less-than sign, U+003C ISOnum -->
+<!ENTITY gt      "&#62;"> <!--  greater-than sign, U+003E ISOnum -->
+<!ENTITY apos	 "&#39;"> <!--  apostrophe = APL quote, U+0027 ISOnum -->
+
+<!-- Latin Extended-A -->
+<!ENTITY OElig   "&#338;"> <!--  latin capital ligature OE,
+                                    U+0152 ISOlat2 -->
+<!ENTITY oelig   "&#339;"> <!--  latin small ligature oe, U+0153 ISOlat2 -->
+<!-- ligature is a misnomer, this is a separate character in some languages -->
+<!ENTITY Scaron  "&#352;"> <!--  latin capital letter S with caron,
+                                    U+0160 ISOlat2 -->
+<!ENTITY scaron  "&#353;"> <!--  latin small letter s with caron,
+                                    U+0161 ISOlat2 -->
+<!ENTITY Yuml    "&#376;"> <!--  latin capital letter Y with diaeresis,
+                                    U+0178 ISOlat2 -->
+
+<!-- Spacing Modifier Letters -->
+<!ENTITY circ    "&#710;"> <!--  modifier letter circumflex accent,
+                                    U+02C6 ISOpub -->
+<!ENTITY tilde   "&#732;"> <!--  small tilde, U+02DC ISOdia -->
+
+<!-- General Punctuation -->
+<!ENTITY ensp    "&#8194;"> <!-- en space, U+2002 ISOpub -->
+<!ENTITY emsp    "&#8195;"> <!-- em space, U+2003 ISOpub -->
+<!ENTITY thinsp  "&#8201;"> <!-- thin space, U+2009 ISOpub -->
+<!ENTITY zwnj    "&#8204;"> <!-- zero width non-joiner,
+                                    U+200C NEW RFC 2070 -->
+<!ENTITY zwj     "&#8205;"> <!-- zero width joiner, U+200D NEW RFC 2070 -->
+<!ENTITY lrm     "&#8206;"> <!-- left-to-right mark, U+200E NEW RFC 2070 -->
+<!ENTITY rlm     "&#8207;"> <!-- right-to-left mark, U+200F NEW RFC 2070 -->
+<!ENTITY ndash   "&#8211;"> <!-- en dash, U+2013 ISOpub -->
+<!ENTITY mdash   "&#8212;"> <!-- em dash, U+2014 ISOpub -->
+<!ENTITY lsquo   "&#8216;"> <!-- left single quotation mark,
+                                    U+2018 ISOnum -->
+<!ENTITY rsquo   "&#8217;"> <!-- right single quotation mark,
+                                    U+2019 ISOnum -->
+<!ENTITY sbquo   "&#8218;"> <!-- single low-9 quotation mark, U+201A NEW -->
+<!ENTITY ldquo   "&#8220;"> <!-- left double quotation mark,
+                                    U+201C ISOnum -->
+<!ENTITY rdquo   "&#8221;"> <!-- right double quotation mark,
+                                    U+201D ISOnum -->
+<!ENTITY bdquo   "&#8222;"> <!-- double low-9 quotation mark, U+201E NEW -->
+<!ENTITY dagger  "&#8224;"> <!-- dagger, U+2020 ISOpub -->
+<!ENTITY Dagger  "&#8225;"> <!-- double dagger, U+2021 ISOpub -->
+<!ENTITY permil  "&#8240;"> <!-- per mille sign, U+2030 ISOtech -->
+<!ENTITY lsaquo  "&#8249;"> <!-- single left-pointing angle quotation mark,
+                                    U+2039 ISO proposed -->
+<!-- lsaquo is proposed but not yet ISO standardized -->
+<!ENTITY rsaquo  "&#8250;"> <!-- single right-pointing angle quotation mark,
+                                    U+203A ISO proposed -->
+<!-- rsaquo is proposed but not yet ISO standardized -->
+
+<!-- Currency Symbols -->
+<!ENTITY euro   "&#8364;"> <!--  euro sign, U+20AC NEW -->