metanorma-ietf 1.0.0

data/lib/metanorma-ietf.rb

@@ -0,0 +1,7 @@
+require "asciidoctor" unless defined? Asciidoctor::Converter
+require "metanorma"
+
+require_relative "metanorma/ietf"
+require_relative "asciidoctor/rfc"
+
+Metanorma::Registry.instance.register(Metanorma::Ietf::Processor)

data/lib/metanorma/ietf.rb

@@ -0,0 +1,8 @@
+require_relative "ietf/processor"
+require_relative "ietf/version"
+
+module Metanorma
+  module Ietf
+
+  end
+end

data/lib/metanorma/ietf/processor.rb

@@ -0,0 +1,89 @@
+require "metanorma/processor"
+require "tempfile"
+
+module Metanorma
+  module Ietf
+    class Processor < Metanorma::Processor
+
+      def initialize
+        @short = :ietf
+        @input_format = :asciidoc
+        @asciidoctor_backend = :rfc2
+      end
+
+      def output_formats
+        {
+          xmlrfc2: "xml",
+          xmlrfc3: "v3.xml",
+          html: "html",
+          txt: "txt"
+        }
+      end
+
+      def version
+        "Metanorma::Ietf #{::Metanorma::Ietf::VERSION}"
+      end
+
+      def input_to_isodoc(file, filename)
+        # TODO: storing these two variables for xmlrfc2. Remove when we have IsoDoc
+        @file = file
+        @filename = filename
+
+        # This is XML RFC v3 output in text
+        Metanorma::Input::Asciidoc.new.process(file, filename, @asciidoctor_backend)
+      end
+
+      # TODO: we're not yet using IsoDoc here
+      def extract_options(isodocxml)
+        {}
+      end
+
+      # From mislav: https://stackoverflow.com/questions/2108727
+      #        /which-in-ruby-checking-if-program-exists-in-path-from-ruby
+      def which(cmd)
+        exts = ENV['PATHEXT'] ? ENV['PATHEXT'].split(';') : ['']
+        ENV['PATH'].split(File::PATH_SEPARATOR).each do |path|
+          exts.each { |ext|
+            exe = File.join(path, "#{cmd}#{ext}")
+            return exe if File.executable?(exe) && !File.directory?(exe)
+          }
+        end
+        nil
+      end
+
+      def output(isodoc_node, outname, format, options={})
+        case format
+        when :xmlrfc2
+          # TODO: we're using XML RFC v2 as the central format because our processor
+          # is not updated to the new schema
+
+          # xmlrfcdoc = Metanorma::Input::Asciidoc.new.process(@file, @filename, :rfc2)
+          # File.open(outname, 'w') { |f| f << xmlrfcdoc }
+
+          # TODO: When we have IsoDoc, we just translate IsoDoc to XML RFC v2
+          File.open(outname, 'w') { |f| f << isodoc_node }
+        when :xmlrfc3
+          # TODO: When we have IsoDoc, we just translate IsoDoc to XML RFC v3
+          xmlrfcdoc = Metanorma::Input::Asciidoc.new.process(@file, @filename, :rfc3)
+          File.open(outname, 'w') { |f| f << xmlrfcdoc }
+
+        when :txt, :html
+          Tempfile.open(outname) do |f|
+            f << isodoc_node
+
+            unless which("xml2rfc")
+              warn "[metanorma-ietf] Error: unable to generate #{format}, the command `xml2rfc` is not found in path."
+              return
+            end
+
+            # In xml2rfc, --text and --html are used
+            format = :text if format == :txt
+            # puts "xml2rfc --#{format} #{f.path} -o #{outname}"
+            system("xml2rfc --#{format} #{f.path} -o #{outname}")
+          end
+        end
+      end
+
+    end
+  end
+end

data/lib/metanorma/ietf/version.rb

@@ -0,0 +1,5 @@
+module Metanorma
+  module Ietf
+    VERSION = "1.0.0".freeze
+  end
+end

data/metanorma-ietf.gemspec

@@ -0,0 +1,51 @@
+# coding: utf-8
+
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "metanorma/ietf/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "metanorma-ietf"
+  spec.version       = Metanorma::Ietf::VERSION
+  spec.authors       = ["Ribose Inc."]
+  spec.email         = ["open.source@ribose.com"]
+
+  spec.summary       = "metanorma-ietf lets you write IETF documents, such as Internet-Drafts and RFCs, in AsciiDoc."
+  spec.description   = <<~DESCRIPTION
+    metanorma-ietf lets you write IETF documents, such as Internet-Drafts and RFCs,
+    in native AsciiDoc syntax. This is part of the Metanorma publishing framework.
+
+    RFC XML ("xml2rfc" Vocabulary XML, RFC7322) is the XML-based language used for
+    writing Internet-Drafts and RFCs, but not everyone likes hand-crafting XML,
+    especially when the focus should be on the content.
+
+    This gem is in active development.
+
+    Formerly known as asciidoctor-ietf.
+  DESCRIPTION
+
+  spec.homepage      = "https://github.com/riboseinc/metanorma-ietf"
+  spec.license       = "BSD-2-Clause"
+
+  spec.files         = `git ls-files -z`.split("\x0").reject do |f|
+    f.match(%r{^(test|spec|features)/})
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_dependency "metanorma-standoc", "~> 1.0.0"
+  spec.add_dependency "isodoc", "~> 0.9.6"
+
+  spec.add_development_dependency "bundler", "~> 1.15"
+  spec.add_development_dependency "byebug", "~> 9.1"
+  spec.add_development_dependency "equivalent-xml", "~> 0.6"
+  spec.add_development_dependency "guard", "~> 2.14"
+  spec.add_development_dependency "guard-rspec", "~> 4.7"
+  spec.add_development_dependency "rake", "~> 12.0"
+  spec.add_development_dependency "rspec", "~> 3.6"
+  spec.add_development_dependency "rubocop", "~> 0.50"
+  spec.add_development_dependency "simplecov", "~> 0.15"
+  spec.add_development_dependency "timecop", "~> 0.9"
+  spec.add_development_dependency "metanorma", "~> 0.3.0"
+end

data/rfc2629-other.ent

@@ -0,0 +1,61 @@
+<!-- rfc2629-other.ent
+
+     Character entity set for RFC-2629 source xml documents.
+     There is no need to invoke this directly from
+     the source document itself; just invoke the DTD.
+
+     These are unknown to (X)HTML, so any converter to these
+     formats must either substitute these entities
+     or invoke this file from the output file.
+
+     Conversion to txt or nroff format will replace
+     these entities by the parenthesized text.
+
+     Typical invocation:
+       <!ENTITY % rfc2629-other
+                PUBLIC "-//IETF//ENTITIES Other for RFC 2629//EN"
+                       "http://xml.resource.org/authoring/rfc2629-other.ent">
+       %rfc2629-other;
+-->
+
+<!-- Magical -->
+<!--     rfc.number            (automatically expanded to content
+                                of number="..." attribute
+                                of <rfc> element, or to "XXXX")                       -->
+
+<!-- ASCII -->
+<!ENTITY excl     "&#33;"><!-- U+0021 EXCLAMATION MARK                  ("!")         -->
+<!ENTITY num      "&#35;"><!-- U+0023 NUMBER SIGN                       ("#")         -->
+<!ENTITY dollar   "&#36;"><!-- U+0024 DOLLAR SIGN                       ("$")         -->
+<!ENTITY percnt   "&#37;"><!-- U+0025 PERCENT SIGN                      ("%")         -->
+<!ENTITY lpar     "&#40;"><!-- U+0028 LEFT PARENTHESIS                  ("(")         -->
+<!ENTITY rpar     "&#41;"><!-- U+0029 RIGHT PARENTHESIS                 (")")         -->
+<!ENTITY ast      "&#42;"><!-- U+002A ASTERISK                          ("*")         -->
+<!ENTITY plus     "&#43;"><!-- U+002B PLUS SIGN                         ("+")         -->
+<!ENTITY comma    "&#44;"><!-- U+002C COMMA                             (",")         -->
+<!ENTITY hyphen   "&#45;"><!-- U+002D HYPHEN-MINUS                      ("-")         -->
+<!ENTITY period   "&#46;"><!-- U+002E FULL STOP                         (".")         -->
+<!ENTITY sol      "&#47;"><!-- U+002F SOLIDUS                           ("/")         -->
+<!ENTITY colon    "&#58;"><!-- U+003A COLON                             (":")         -->
+<!ENTITY semi     "&#59;"><!-- U+003B SEMICOLON                         (";")         -->
+<!ENTITY equals   "&#61;"><!-- U+003D EQUALS SIGN                       ("=")         -->
+<!ENTITY quest    "&#63;"><!-- U+003F QUESTION MARK                     ("?")         -->
+<!ENTITY commat   "&#64;"><!-- U+0040 COMMERCIAL AT                     ("@")         -->
+<!ENTITY lsqb     "&#91;"><!-- U+005B LEFT SQUARE BRACKET               ("[")         -->
+<!ENTITY bsol     "&#92;"><!-- U+005C REVERSE SOLIDUS                   ("\\")        -->
+<!ENTITY rsqb     "&#93;"><!-- U+005D RIGHT SQUARE BRACKET              ("]")         -->
+<!ENTITY circ     "&#94;"><!-- U+005E CIRCUMFLEX ACCENT                 ("^")         -->
+<!ENTITY lowbar   "&#95;"><!-- U+005F LOW LINE                          ("_")         -->
+<!ENTITY grave    "&#96;"><!-- U+0060 GRAVE ACCENT                      ("`")         -->
+<!ENTITY lcub    "&#123;"><!-- U+007B LEFT CURLY BRACKET                ("{")         -->
+<!ENTITY verbar  "&#124;"><!-- U+007C VERTICAL LINE                     ("|")         -->
+<!ENTITY rcub    "&#125;"><!-- U+007D RIGHT CURLY BRACKET               ("}")         -->
+
+<!-- Useful Unicode -->
+<!ENTITY Zcaron  "&#381;"><!-- U+017D LATIN CAPITAL LETTER Z WITH CARON ("Z")         -->
+<!ENTITY zcaron  "&#382;"><!-- U+017E LATIN SMALL LETTER Z WITH CARON   ("z")         -->
+<!ENTITY dash   "&#8208;"><!-- U+2010 HYPHEN                            ("-")         -->
+<!ENTITY nbhy   "&#8209;"><!-- U+2011 NON-BREAKING HYPHEN               (special "-") -->
+<!ENTITY wj     "&#8288;"><!-- U+2060 WORD JOINER                       (special "")  -->
+
+<!-- EOF -->

data/rfc2629-xhtml.ent

@@ -0,0 +1,165 @@
+<!-- rfc2629-xhtml.ent
+
+     Character entity set for RFC-2629 source xml documents.
+     There is no need to invoke this directly from
+     the source document itself; just invoke the DTD.
+
+     These are known to (X)HTML, so any converter to these
+     formats can just leave them as is without having
+     to invoke this file from the output file.
+
+     Conversion to txt or nroff format will replace
+     these entities by the parenthesized text.
+
+     Typical invocation:
+       <!ENTITY % rfc2629-xhtml
+                PUBLIC "-//IETF//ENTITIES XHTML subset for RFC 2629//EN"
+                       "http://xml.resource.org/authoring/rfc2629-xhtml.ent">
+       %rfc2629-xhtml;
+-->
+
+<!-- All of ISO Latin 1 -->
+<!ENTITY nbsp    "&#160;"><!-- U+00A0 NO-BREAK SPACE                             (special " ")        -->
+<!ENTITY iexcl   "&#161;"><!-- U+00A1 INVERTED EXCLAMATION MARK                  ("!")                -->
+<!ENTITY cent    "&#162;"><!-- U+00A2 CENT SIGN                                  ("[cents]")          -->
+<!ENTITY pound   "&#163;"><!-- U+00A3 POUND SIGN                                 ("GBP")              -->
+<!ENTITY curren  "&#164;"><!-- U+00A4 CURRENCY SIGN                              ("[currency units]") -->
+<!ENTITY yen     "&#165;"><!-- U+00A5 YEN SIGN                                   ("JPY")              -->
+<!ENTITY brvbar  "&#166;"><!-- U+00A6 BROKEN BAR                                 ("|")                -->
+<!ENTITY sect    "&#167;"><!-- U+00A7 SECTION SIGN                               ("S.")               -->
+<!ENTITY uml     "&#168;"><!-- U+00A8 DIAERESIS                                  ('"')                -->
+<!ENTITY copy    "&#169;"><!-- U+00A9 COPYRIGHT SIGN                             ("(C)")              -->
+<!ENTITY ordf    "&#170;"><!-- U+00AA FEMININE ORDINAL INDICATOR                 ("a")                -->
+<!ENTITY laquo   "&#171;"><!-- U+00AB LEFT-POINTING DOUBLE ANGLE QUOTATION MARK  ("<<")               -->
+<!ENTITY not     "&#172;"><!-- U+00AC NOT SIGN                                   ("[not]")            -->
+<!ENTITY shy     "&#173;"><!-- U+00AD SOFT HYPHEN                                (ignored "")         -->
+<!ENTITY reg     "&#174;"><!-- U+00AE REGISTERED SIGN                            ("(R)")              -->
+<!ENTITY macr    "&#175;"><!-- U+00AF MACRON                                     ("_")                -->
+<!ENTITY deg     "&#176;"><!-- U+00B0 DEGREE SIGN                                ("o")                -->
+<!ENTITY plusmn  "&#177;"><!-- U+00B1 PLUS-MINUS SIGN                            ("+/-")              -->
+<!ENTITY sup2    "&#178;"><!-- U+00B2 SUPERSCRIPT TWO                            ("^2")               -->
+<!ENTITY sup3    "&#179;"><!-- U+00B3 SUPERSCRIPT THREE                          ("^3")               -->
+<!ENTITY acute   "&#180;"><!-- U+00B4 ACUTE ACCENT                               ("'")                -->
+<!ENTITY micro   "&#181;"><!-- U+00B5 MICRO SIGN                                 ("[micro]")          -->
+<!ENTITY para    "&#182;"><!-- U+00B6 PILCROW SIGN                               ("P.")               -->
+<!ENTITY middot  "&#183;"><!-- U+00B7 MIDDLE DOT                                 (".")                -->
+<!ENTITY cedil   "&#184;"><!-- U+00B8 CEDILLA                                    (",")                -->
+<!ENTITY sup1    "&#185;"><!-- U+00B9 SUPERSCRIPT ONE                            ("^1")               -->
+<!ENTITY ordm    "&#186;"><!-- U+00BA MASCULINE ORDINAL INDICATOR                ("o")                -->
+<!ENTITY raquo   "&#187;"><!-- U+00BB RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK (">>")               -->
+<!ENTITY frac14  "&#188;"><!-- U+00BC VULGAR FRACTION ONE QUARTER                ("1/4")              -->
+<!ENTITY frac12  "&#189;"><!-- U+00BD VULGAR FRACTION ONE HALF                   ("1/2")              -->
+<!ENTITY frac34  "&#190;"><!-- U+00BE VULGAR FRACTION THREE QUARTERS             ("3/4")              -->
+<!ENTITY iquest  "&#191;"><!-- U+00BF INVERTED QUESTION MARK                     ("?")                -->
+<!ENTITY Agrave  "&#192;"><!-- U+00C0 LATIN CAPITAL LETTER A WITH GRAVE          ("A")                -->
+<!ENTITY Aacute  "&#193;"><!-- U+00C1 LATIN CAPITAL LETTER A WITH ACUTE          ("A")                -->
+<!ENTITY Acirc   "&#194;"><!-- U+00C2 LATIN CAPITAL LETTER A WITH CIRCUMFLEX     ("A")                -->
+<!ENTITY Atilde  "&#195;"><!-- U+00C3 LATIN CAPITAL LETTER A WITH TILDE          ("A")                -->
+<!ENTITY Auml    "&#196;"><!-- U+00C4 LATIN CAPITAL LETTER A WITH DIAERESIS      ("Ae")               -->
+<!ENTITY Aring   "&#197;"><!-- U+00C5 LATIN CAPITAL LETTER A WITH RING ABOVE     ("Ae")               -->
+<!ENTITY AElig   "&#198;"><!-- U+00C6 LATIN CAPITAL LETTER AE                    ("AE")               -->
+<!ENTITY Ccedil  "&#199;"><!-- U+00C7 LATIN CAPITAL LETTER C WITH CEDILLA        ("C")                -->
+<!ENTITY Egrave  "&#200;"><!-- U+00C8 LATIN CAPITAL LETTER E WITH GRAVE          ("E")                -->
+<!ENTITY Eacute  "&#201;"><!-- U+00C9 LATIN CAPITAL LETTER E WITH ACUTE          ("E")                -->
+<!ENTITY Ecirc   "&#202;"><!-- U+00CA LATIN CAPITAL LETTER E WITH CIRCUMFLEX     ("E")                -->
+<!ENTITY Euml    "&#203;"><!-- U+00CB LATIN CAPITAL LETTER E WITH DIAERESIS      ("E")                -->
+<!ENTITY Igrave  "&#204;"><!-- U+00CC LATIN CAPITAL LETTER I WITH GRAVE          ("I")                -->
+<!ENTITY Iacute  "&#205;"><!-- U+00CD LATIN CAPITAL LETTER I WITH ACUTE          ("I")                -->
+<!ENTITY Icirc   "&#206;"><!-- U+00CE LATIN CAPITAL LETTER I WITH CIRCUMFLEX     ("I")                -->
+<!ENTITY Iuml    "&#207;"><!-- U+00CF LATIN CAPITAL LETTER I WITH DIAERESIS      ("I")                -->
+<!ENTITY ETH     "&#208;"><!-- U+00D0 LATIN CAPITAL LETTER ETH                   ("[ETH]")            -->
+<!ENTITY Ntilde  "&#209;"><!-- U+00D1 LATIN CAPITAL LETTER N WITH TILDE          ("N")                -->
+<!ENTITY Ograve  "&#210;"><!-- U+00D2 LATIN CAPITAL LETTER O WITH GRAVE          ("O")                -->
+<!ENTITY Oacute  "&#211;"><!-- U+00D3 LATIN CAPITAL LETTER O WITH ACUTE          ("O")                -->
+<!ENTITY Ocirc   "&#212;"><!-- U+00D4 LATIN CAPITAL LETTER O WITH CIRCUMFLEX     ("O")                -->
+<!ENTITY Otilde  "&#213;"><!-- U+00D5 LATIN CAPITAL LETTER O WITH TILDE          ("O")                -->
+<!ENTITY Ouml    "&#214;"><!-- U+00D6 LATIN CAPITAL LETTER O WITH DIAERESIS      ("Oe")               -->
+<!ENTITY times   "&#215;"><!-- U+00D7 MULTIPLICATION SIGN                        ("x")                -->
+<!ENTITY Oslash  "&#216;"><!-- U+00D8 LATIN CAPITAL LETTER O WITH STROKE         ("Oe")               -->
+<!ENTITY Ugrave  "&#217;"><!-- U+00D9 LATIN CAPITAL LETTER U WITH GRAVE          ("U")                -->
+<!ENTITY Uacute  "&#218;"><!-- U+00DA LATIN CAPITAL LETTER U WITH ACUTE          ("U")                -->
+<!ENTITY Ucirc   "&#219;"><!-- U+00DB LATIN CAPITAL LETTER U WITH CIRCUMFLEX     ("U")                -->
+<!ENTITY Uuml    "&#220;"><!-- U+00DC LATIN CAPITAL LETTER U WITH DIAERESIS      ("Ue")               -->
+<!ENTITY Yacute  "&#221;"><!-- U+00DD LATIN CAPITAL LETTER Y WITH ACUTE          ("Y")                -->
+<!ENTITY THORN   "&#222;"><!-- U+00DE LATIN CAPITAL LETTER THORN                 ("[THORN]")          -->
+<!ENTITY szlig   "&#223;"><!-- U+00DF LATIN SMALL LETTER SHARP S                 ("ss")               -->
+<!ENTITY agrave  "&#224;"><!-- U+00E0 LATIN SMALL LETTER A WITH GRAVE            ("a")                -->
+<!ENTITY aacute  "&#225;"><!-- U+00E1 LATIN SMALL LETTER A WITH ACUTE            ("a")                -->
+<!ENTITY acirc   "&#226;"><!-- U+00E2 LATIN SMALL LETTER A WITH CIRCUMFLEX       ("a")                -->
+<!ENTITY atilde  "&#227;"><!-- U+00E3 LATIN SMALL LETTER A WITH TILDE            ("a")                -->
+<!ENTITY auml    "&#228;"><!-- U+00E4 LATIN SMALL LETTER A WITH DIAERESIS        ("ae")               -->
+<!ENTITY aring   "&#229;"><!-- U+00E5 LATIN SMALL LETTER A WITH RING ABOVE       ("ae")               -->
+<!ENTITY aelig   "&#230;"><!-- U+00E6 LATIN SMALL LETTER AE                      ("ae")               -->
+<!ENTITY ccedil  "&#231;"><!-- U+00E7 LATIN SMALL LETTER C WITH CEDILLA          ("c")                -->
+<!ENTITY egrave  "&#232;"><!-- U+00E8 LATIN SMALL LETTER E WITH GRAVE            ("e")                -->
+<!ENTITY eacute  "&#233;"><!-- U+00E9 LATIN SMALL LETTER E WITH ACUTE            ("e")                -->
+<!ENTITY ecirc   "&#234;"><!-- U+00EA LATIN SMALL LETTER E WITH CIRCUMFLEX       ("e")                -->
+<!ENTITY euml    "&#235;"><!-- U+00EB LATIN SMALL LETTER E WITH DIAERESIS        ("e")                -->
+<!ENTITY igrave  "&#236;"><!-- U+00EC LATIN SMALL LETTER I WITH GRAVE            ("i")                -->
+<!ENTITY iacute  "&#237;"><!-- U+00ED LATIN SMALL LETTER I WITH ACUTE            ("i")                -->
+<!ENTITY icirc   "&#238;"><!-- U+00EE LATIN SMALL LETTER I WITH CIRCUMFLEX       ("i")                -->
+<!ENTITY iuml    "&#239;"><!-- U+00EF LATIN SMALL LETTER I WITH DIAERESIS        ("i")                -->
+<!ENTITY eth     "&#240;"><!-- U+00F0 LATIN SMALL LETTER ETH                     ("[eth]")            -->
+<!ENTITY ntilde  "&#241;"><!-- U+00F1 LATIN SMALL LETTER N WITH TILDE            ("n")                -->
+<!ENTITY ograve  "&#242;"><!-- U+00F2 LATIN SMALL LETTER O WITH GRAVE            ("o")                -->
+<!ENTITY oacute  "&#243;"><!-- U+00F3 LATIN SMALL LETTER O WITH ACUTE            ("o")                -->
+<!ENTITY ocirc   "&#244;"><!-- U+00F4 LATIN SMALL LETTER O WITH CIRCUMFLEX       ("o")                -->
+<!ENTITY otilde  "&#245;"><!-- U+00F5 LATIN SMALL LETTER O WITH TILDE            ("o")                -->
+<!ENTITY ouml    "&#246;"><!-- U+00F6 LATIN SMALL LETTER O WITH DIAERESIS        ("oe")               -->
+<!ENTITY divide  "&#247;"><!-- U+00F7 DIVISION SIGN                              ("/")                -->
+<!ENTITY oslash  "&#248;"><!-- U+00F8 LATIN SMALL LETTER O WITH STROKE           ("oe")               -->
+<!ENTITY ugrave  "&#249;"><!-- U+00F9 LATIN SMALL LETTER U WITH GRAVE            ("u")                -->
+<!ENTITY uacute  "&#250;"><!-- U+00FA LATIN SMALL LETTER U WITH ACUTE            ("u")                -->
+<!ENTITY ucirc   "&#251;"><!-- U+00FB LATIN SMALL LETTER U WITH CIRCUMFLEX       ("u")                -->
+<!ENTITY uuml    "&#252;"><!-- U+00FC LATIN SMALL LETTER U WITH DIAERESIS        ("ue")               -->
+<!ENTITY yacute  "&#253;"><!-- U+00FD LATIN SMALL LETTER Y WITH ACUTE            ("y")                -->
+<!ENTITY thorn   "&#254;"><!-- U+00FE LATIN SMALL LETTER THORN                   ("[thorn]")          -->
+<!ENTITY yuml    "&#255;"><!-- U+00FF LATIN SMALL LETTER Y WITH DIAERESIS        ("y")                -->
+
+<!-- Some of ISO Latin 9 and 10 -->
+<!ENTITY OElig   "&#338;"><!-- U+0152 LATIN CAPITAL LIGATURE OE                  ("OE")               -->
+<!ENTITY oelig   "&#339;"><!-- U+0153 LATIN SMALL LIGATURE OE                    ("oe")               -->
+<!ENTITY Scaron  "&#352;"><!-- U+0160 LATIN CAPITAL LETTER S WITH CARON          ("S")                -->
+<!ENTITY scaron  "&#353;"><!-- U+0161 LATIN SMALL LETTER S WITH CARON            ("s")                -->
+<!ENTITY Yuml    "&#376;"><!-- U+0178 LATIN CAPITAL LETTER Y WITH DIAERESIS      ("Y")                -->
+
+<!-- Other Unicode (including some characters from the windows-1252 repertoire) -->
+<!ENTITY fnof    "&#402;"><!-- U+0192 LATIN SMALL LETTER F WITH HOOK             ("f")                -->
+<!ENTITY tilde   "&#732;"><!-- U+02DC SMALL TILDE                                ("~")                -->
+<!ENTITY ensp   "&#8194;"><!-- U+2002 EN SPACE                                   (" ")                -->
+<!ENTITY emsp   "&#8195;"><!-- U+2003 EM SPACE                                   (" ")                -->
+<!ENTITY thinsp "&#8201;"><!-- U+2009 THIN SPACE                                 (" ")                -->
+<!ENTITY ndash  "&#8211;"><!-- U+2013 EN DASH                                    ("-")                -->
+<!ENTITY mdash  "&#8212;"><!-- U+2014 EM DASH                                    ("-\u002D")          -->
+<!ENTITY lsquo  "&#8216;"><!-- U+2018 LEFT SINGLE QUOTATION MARK                 ("'")                -->
+<!ENTITY rsquo  "&#8217;"><!-- U+2019 RIGHT SINGLE QUOTATION MARK                ("'")                -->
+<!ENTITY sbquo  "&#8218;"><!-- U+201A SINGLE LOW-9 QUOTATION MARK                ("'")                -->
+<!ENTITY ldquo  "&#8220;"><!-- U+201C LEFT DOUBLE QUOTATION MARK                 ('"')                -->
+<!ENTITY rdquo  "&#8221;"><!-- U+201D RIGHT DOUBLE QUOTATION MARK                ('"')                -->
+<!ENTITY bdquo  "&#8222;"><!-- U+201E DOUBLE LOW-9 QUOTATION MARK                ('"')                -->
+<!ENTITY dagger "&#8224;"><!-- U+2020 DAGGER                                     ("*!*")              -->
+<!ENTITY Dagger "&#8225;"><!-- U+2021 DOUBLE DAGGER                              ("*!!*")             -->
+<!ENTITY bull   "&#8226;"><!-- U+2022 BULLET                                     ("o")                -->
+<!ENTITY hellip "&#8230;"><!-- U+2026 HORIZONTAL ELLIPSIS                        ("...")              -->
+<!ENTITY permil "&#8242;"><!-- U+2030 PER MILLE SIGN                             ("[/1000]")          -->
+<!ENTITY prime  "&#8242;"><!-- U+2032 PRIME                                      ("'")                -->
+<!ENTITY Prime  "&#8243;"><!-- U+2033 DOUBLE PRIME                               ('"')                -->
+<!ENTITY lsaquo "&#8249;"><!-- U+2039 SINGLE LEFT-POINTING ANGLE QUOTATION MARK  ("<")                -->
+<!ENTITY rsaquo "&#8250;"><!-- U+203A SINGLE RIGHT-POINTING ANGLE QUOTATION MARK (">")                -->
+<!ENTITY frasl  "&#8260;"><!-- U+2044 FRACTION SLASH                             ("/")                -->
+<!ENTITY euro   "&#8364;"><!-- U+20AC EURO SIGN                                  ("EUR")              -->
+<!ENTITY trade  "&#8482;"><!-- U+2122 TRADE MARK SIGN                            ("[TM]")             -->
+<!ENTITY larr   "&#8592;"><!-- U+2190 LEFTWARDS ARROW                            ("<-\u002D")         -->
+<!ENTITY rarr   "&#8594;"><!-- U+2192 RIGHTWARDS ARROW                           ("\u002D->")         -->
+<!ENTITY harr   "&#8596;"><!-- U+2194 LEFT RIGHT ARROW                           ("<->")              -->
+<!ENTITY lArr   "&#8656;"><!-- U+21D0 LEFTWARDS DOUBLE ARROW                     ("<==")              -->
+<!ENTITY rArr   "&#8658;"><!-- U+21D2 RIGHTWARDS DOUBLE ARROW                    ("==>")              -->
+<!ENTITY hArr   "&#8660;"><!-- U+21D4 LEFT RIGHT DOUBLE ARROW                    ("<=>")              -->
+<!ENTITY minus  "&#8722;"><!-- U+2212 MINUS SIGN                                 ("-")                -->
+<!ENTITY lowast "&#8727;"><!-- U+2217 ASTERISK OPERATOR                          ("*")                -->
+<!ENTITY le     "&#8804;"><!-- U+2264 LESS-THAN OR EQUAL TO                      ("<=")               -->
+<!ENTITY ge     "&#8805;"><!-- U+2265 GREATER-THAN OR EQUAL TO                   (">=")               -->
+<!ENTITY lang   "&#9001;"><!-- U+2329 LEFT-POINTING ANGLE BRACKET                ("<")                -->
+<!ENTITY rang   "&#9002;"><!-- U+232A RIGHT-POINTING ANGLE BRACKET               (">")                -->
+
+<!-- EOF -->

data/rfc2629.dtd

@@ -0,0 +1,312 @@
+<!--
+  revised DTD for the RFC document series, draft of 2009-10-06
+  -->
+
+
+<!--
+  Typical invocation:
+      <!DOCTYPE rfc PUBLIC "-//IETF//DTD RFC 2629//EN"
+                           "http://xml.resource.org/authoring/rfc2629.dtd" [
+        ... dtd subset ...
+      ]>
+    or
+      <!DOCTYPE rfc SYSTEM "rfc2629.dtd" [
+        ... dtd subset ...
+      ]>
+  -->
+
+
+<!--
+  Contents
+
+    Character entities
+
+    DTD data types
+
+    The top-level
+
+    Front matter
+
+    The Body
+
+    Back matter
+  -->
+
+
+<!--
+  Character entities
+  -->
+
+
+<!ENTITY % rfc2629-xhtml
+         PUBLIC "-//IETF//ENTITIES XHTML subset for RFC 2629//EN"
+                "rfc2629-xhtml.ent">
+%rfc2629-xhtml;
+
+<!ENTITY % rfc2629-other
+         PUBLIC "-//IETF//ENTITIES Other for RFC 2629//EN"
+                "rfc2629-other.ent">
+%rfc2629-other;
+
+
+<!--
+  DTD data types:
+
+        entity        description
+        ======        ===============================================
+        NUMBER        [0-9]+
+        NUMBERS       a comma-separated list of NUMBER
+
+        DAY           the day of the month, e.g., "1"
+        MONTH         the month of the year, e.g., "January"
+        YEAR          a four-digit year, e.g., "1999"
+
+        URI           e.g., "http://invisible.net/"
+
+        ATEXT/CTEXT   printable ASCII text (no line-terminators)
+
+        TEXT          character data
+  -->
+
+
+<!ENTITY % NUMBER     "CDATA">
+<!ENTITY % NUMBERS    "CDATA">
+
+<!ENTITY % DAY        "CDATA">
+<!ENTITY % MONTH      "CDATA">
+<!ENTITY % YEAR       "CDATA">
+
+<!ENTITY % URI        "CDATA">
+
+<!ENTITY % ATEXT      "CDATA">
+<!ENTITY % CTEXT      "#PCDATA">
+
+<!ENTITY % TEXT       "#PCDATA">
+
+<!ENTITY   rfc.number "XXXX">
+
+
+<!--
+  The top-level
+  -->
+
+
+<!--
+  attributes for the "rfc" element are supplied by the RFC
+  editor. when preparing drafts, authors should leave them blank.
+
+  the "seriesNo" attribute is used if the category is, e.g., BCP.
+  -->
+<!ELEMENT rfc         (front,middle,back?)>
+<!ATTLIST rfc
+          number      %NUMBER;           #IMPLIED
+          obsoletes   %NUMBERS;          ""
+          updates     %NUMBERS;          ""
+          category    (std|bcp|info|exp|historic)
+                                         #IMPLIED
+          consensus   (no|yes)           #IMPLIED
+          seriesNo    %NUMBER;           #IMPLIED
+          ipr         (full2026|noDerivativeWorks2026|none
+                      |full3667|noModification3667|noDerivatives3667
+                      |full3978|noModification3978|noDerivatives3978
+                      |trust200811|noModificationTrust200811|noDerivativesTrust200811
+                      |trust200902|noModificationTrust200902|noDerivativesTrust200902
+                      |pre5378Trust200902)
+                                         #IMPLIED
+          iprExtract  IDREF              #IMPLIED
+          submissionType
+                      (IETF|IAB|IRTF|independent) "IETF"
+          docName     %ATEXT;            #IMPLIED
+          xml:lang    %ATEXT;            "en">
+
+
+<!--
+  Front matter
+  -->
+
+
+<!ELEMENT front       (title,author+,date,area*,workgroup*,keyword*,
+                       abstract?,note*)>
+
+<!-- the "abbrev" attribute is used for headers, etc. -->
+<!ELEMENT title       (%CTEXT;)>
+<!ATTLIST title
+          abbrev      %ATEXT;            #IMPLIED> 
+
+<!ELEMENT author      (organization?,address?)>
+<!ATTLIST author
+          initials    %ATEXT;            #IMPLIED
+          surname     %ATEXT;            #IMPLIED
+          fullname    %ATEXT;            #IMPLIED
+          role        (editor)           #IMPLIED>
+
+<!ELEMENT organization
+                      (%CTEXT;)>
+<!ATTLIST organization
+          abbrev      %ATEXT;            #IMPLIED> 
+ 
+<!ELEMENT address     (postal?,phone?,facsimile?,email?,uri?)>
+
+<!-- this content model should be more strict:
+     at most one of each the city, region, code, and country
+     elements may be present -->
+<!ELEMENT postal      (street+,(city|region|code|country)*)>
+<!ELEMENT street      (%CTEXT;)>
+<!ELEMENT city        (%CTEXT;)>
+<!ELEMENT region      (%CTEXT;)>
+<!ELEMENT code        (%CTEXT;)>
+<!ELEMENT country     (%CTEXT;)>
+<!ELEMENT phone       (%CTEXT;)>
+<!ELEMENT facsimile   (%CTEXT;)>
+<!ELEMENT email       (%CTEXT;)>
+<!ELEMENT uri         (%CTEXT;)>
+
+<!ELEMENT date        EMPTY>
+<!ATTLIST date
+          day         %DAY;              #IMPLIED
+          month       %MONTH;            #IMPLIED
+          year        %YEAR;             #IMPLIED>
+
+<!-- meta-data... -->
+<!ELEMENT area        (%CTEXT;)>
+<!ELEMENT workgroup   (%CTEXT;)>
+<!ELEMENT keyword     (%CTEXT;)>
+
+<!ELEMENT abstract    (t)+>
+<!ELEMENT note        (t)+>
+<!ATTLIST note
+          title       %ATEXT;            #REQUIRED>
+
+
+<!--
+  The body
+  -->
+
+
+<!ELEMENT middle      (section+)>
+
+<!ELEMENT section     ((t|figure|texttable|iref)*,section*)>
+<!ATTLIST section
+          anchor      ID                 #IMPLIED
+          title       %ATEXT;            #REQUIRED
+          toc         (include|exclude|default)
+                                         "default">
+
+<!-- use of <appendix/> is deprecated...
+<!ELEMENT appendix    ((t|figure|texttable|iref)*,appendix*)>
+<!ATTLIST appendix
+          anchor      ID                 #IMPLIED
+          title       %ATEXT;            #REQUIRED
+          toc         (include|exclude|default)
+                                         "default">
+  -->
+
+<!-- use of <figure/> is deprecated... -->
+<!ELEMENT t           (%TEXT;|list|figure|xref|eref|iref|cref|spanx|vspace)*>
+<!ATTLIST t
+          anchor      ID                 #IMPLIED
+          hangText    %ATEXT;            #IMPLIED>
+
+<!-- the value of the style attribute is inherited from the closest 
+     parent -->
+<!ELEMENT list        (t+)>
+<!ATTLIST list
+          style       %ATEXT;            #IMPLIED
+          hangIndent  %NUMBER;           #IMPLIED
+          counter     %ATEXT;            #IMPLIED>
+
+<!ELEMENT xref        (%CTEXT;)>
+<!ATTLIST xref
+          target      IDREF              #REQUIRED
+          pageno      (true|false)       "false"
+          format      (counter|title|none|default)
+                                         "default">
+
+<!ELEMENT eref        (%CTEXT;)>
+<!ATTLIST eref
+          target      %URI;              #REQUIRED>
+
+<!ELEMENT iref        EMPTY>
+<!ATTLIST iref
+          item        %ATEXT;            #REQUIRED
+          subitem     %ATEXT;            ""
+          primary    (true|false)       "false">
+
+<!ELEMENT cref        (%CTEXT;)>
+<!ATTLIST cref
+          anchor      ID                 #IMPLIED
+          source      %ATEXT;            #IMPLIED>
+
+<!ELEMENT spanx       (%CTEXT;)>
+<!ATTLIST spanx
+          xml:space   (default|preserve) "preserve"
+          style       %ATEXT;            "emph">
+
+<!ELEMENT vspace      EMPTY>
+<!ATTLIST vspace
+          blankLines  %NUMBER;           "0">
+
+<!ELEMENT figure      (iref*,preamble?,artwork,postamble?)>
+<!ATTLIST figure
+          anchor      ID                 #IMPLIED
+          title       %ATEXT;            ""
+          suppress-title (true|false)    "false"
+          src         %URI;              #IMPLIED
+          align       (left|center|right) "left"
+          alt         %ATEXT;            ""
+          width       %ATEXT;            ""
+          height      %ATEXT;            "">
+
+<!ELEMENT preamble    (%TEXT;|xref|eref|iref|cref|spanx)*>
+<!ELEMENT artwork     (%TEXT;)*>
+<!ATTLIST artwork
+          xml:space   (default|preserve) "preserve"
+          name        %ATEXT;            ""
+          type        %ATEXT;            ""
+          src         %URI;              #IMPLIED
+          align       (left|center|right) "left"
+          alt         %ATEXT;            ""
+          width       %ATEXT;            ""
+          height      %ATEXT;            "">
+
+<!ELEMENT postamble   (%TEXT;|xref|eref|iref|cref|spanx)*>
+    
+<!ELEMENT texttable   (preamble?,ttcol+,c*,postamble?)>
+<!ATTLIST texttable
+          anchor      ID                 #IMPLIED
+          title       %ATEXT;            ""
+          suppress-title (true|false)    "false"
+          align       (left|center|right) "center"
+          style       (all|none|headers|full) "full">
+<!ELEMENT ttcol       (%CTEXT;)>
+<!ATTLIST ttcol
+          width       %ATEXT;            #IMPLIED
+          align       (left|center|right) "left">
+<!ELEMENT c           (%TEXT;|xref|eref|iref|cref|spanx)*>
+
+
+<!--
+  Back matter
+  -->
+
+
+<!-- sections, if present, are appendices -->
+<!ELEMENT back        (references*,section*)>
+
+<!ELEMENT references  (reference+)>
+<!ATTLIST references
+          title       %ATEXT;            "References">
+<!ELEMENT reference   (front,seriesInfo*,format*,annotation*)>
+<!ATTLIST reference
+          anchor      ID                 #IMPLIED
+          target      %URI;              #IMPLIED>
+<!ELEMENT seriesInfo  EMPTY>
+<!ATTLIST seriesInfo
+          name        %ATEXT;            #REQUIRED
+          value       %ATEXT;            #REQUIRED>
+<!ELEMENT format      EMPTY>
+<!ATTLIST format
+          target      %URI;              #IMPLIED
+          type        %ATEXT;            #REQUIRED
+          octets      %NUMBER;           #IMPLIED>
+<!ELEMENT annotation  (%TEXT;|xref|eref|iref|cref|spanx)*>