metanorma-m3d 1.0.0

data/lib/isodoc/m3d/m3dhtmlconvert.rb

@@ -0,0 +1,154 @@
+require "isodoc"
+require_relative "metadata"
+require_relative "m3dhtmlrender"
+require "fileutils"
+
+module IsoDoc
+  module M3d
+    # A {Converter} implementation that generates CSAND output, and a document
+    # schema encapsulation of the document for validation
+    class HtmlConvert < IsoDoc::HtmlConvert
+      def add_image(filenames)
+        filenames.each do |filename|
+          #system "cp #{html_doc_path(filename)} #{filename}"
+          FileUtils.cp html_doc_path(filename), filename
+          @files_to_delete << filename
+        end
+      end
+
+      def initialize(options)
+        @libdir = File.dirname(__FILE__)
+        super
+        add_image(%w(logo.jpg m3-logo.png))
+      end
+
+      def default_fonts(options)
+        {
+          bodyfont: (options[:script] == "Hans" ? '"SimSun",serif' : '"Overpass",sans-serif'),
+          headerfont: (options[:script] == "Hans" ? '"SimHei",sans-serif' : '"Overpass",sans-serif'),
+          monospacefont: '"Space Mono",monospace'
+        }
+      end
+
+      def default_file_locations(_options)
+        {
+          htmlstylesheet: html_doc_path("htmlstyle.scss"),
+          htmlcoverpage: html_doc_path("html_m3d_titlepage.html"),
+          htmlintropage: html_doc_path("html_m3d_intro.html"),
+          scripts: html_doc_path("scripts.html"),
+        }
+      end
+
+      def metadata_init(lang, script, labels)
+        @meta = Metadata.new(lang, script, labels)
+      end
+
+      def colophon(body, docxml)
+        body.div **{ class: "colophon" } do |div|
+          div << <<~"COLOPHON"
+          <p>As with all M3AAWG documents that we publish, please check the M3AAWG website
+          (<a href="http://www.m3aawg.org">www.m3aawg.org</a>) for updates to this paper.</p>
+          <p>&copy; 2017 copyright by the Messaging, Malware and Mobile Anti-Abuse Working Group (M3AAWG)</p>
+          COLOPHON
+        end
+      end
+
+      def html_head()
+        <<~HEAD.freeze
+    <script type="text/javascript" src="https://ajax.googleapis.com/ajax/libs/jquery/3.3.1/jquery.min.js"></script>
+
+    <!--TOC script import-->
+    <script type="text/javascript"  src="https://cdn.rawgit.com/jgallen23/toc/0.3.2/dist/toc.min.js"></script>
+
+    <!--Google fonts-->
+    <link href="https://fonts.googleapis.com/css?family=Open+Sans:300,300i,400,400i,600,600i|Space+Mono:400,700" rel="stylesheet">
+    <link href="https://fonts.googleapis.com/css?family=Overpass:300,300i,600,900" rel="stylesheet">
+    <!--Font awesome import for the link icon-->
+    <link rel="stylesheet" href="https://use.fontawesome.com/releases/v5.0.8/css/solid.css" integrity="sha384-v2Tw72dyUXeU3y4aM2Y0tBJQkGfplr39mxZqlTBDUZAb9BGoC40+rdFCG0m10lXk" crossorigin="anonymous">
+    <link rel="stylesheet" href="https://use.fontawesome.com/releases/v5.0.8/css/fontawesome.css" integrity="sha384-q3jl8XQu1OpdLgGFvNRnPdj5VIlCvgsDQTQB6owSOHWlAurxul7f+JpUOVdAiJ5P" crossorigin="anonymous">
+<style class="anchorjs"></style>
+        HEAD
+      end
+
+      def make_body(xml, docxml)
+        body_attr = { lang: "EN-US", link: "blue", vlink: "#954F72", "xml:lang": "EN-US", class: "container" }
+        xml.body **body_attr do |body|
+          make_body1(body, docxml)
+          make_body2(body, docxml)
+          make_body3(body, docxml)
+          colophon(body, docxml)
+        end
+      end
+
+      def html_toc(docxml)
+        docxml
+      end
+
+      def annex_name(annex, name, div)
+        div.h1 **{ class: "Annex" } do |t|
+          t << "#{get_anchors[annex['id']][:label]} "
+          t << "<b>#{name.text}</b>"
+        end
+      end
+
+      def annex_name_lbl(clause, num)
+        obl = l10n("(#{@inform_annex_lbl})")
+        obl = l10n("(#{@norm_annex_lbl})") if clause["obligation"] == "normative"
+        l10n("<b>#{@annex_lbl} #{num}</b> #{obl}")
+      end
+
+      def pre_parse(node, out)
+        out.pre node.text # content.gsub(/</, "&lt;").gsub(/>/, "&gt;")
+      end
+
+      def term_defs_boilerplate(div, source, term, preface)
+        if source.empty? && term.nil?
+          div << @no_terms_boilerplate
+        else
+          div << term_defs_boilerplate_cont(source, term)
+        end
+      end
+
+      def i18n_init(lang, script)
+        super
+        @annex_lbl = "Appendix"
+      end
+
+      def error_parse(node, out)
+        # catch elements not defined in ISO
+        case node.name
+        when "pre"
+          pre_parse(node, out)
+        when "keyword"
+          out.span node.text, **{ class: "keyword" }
+        else
+          super
+        end
+      end
+
+      def fileloc(loc)
+        File.join(File.dirname(__FILE__), loc)
+      end
+
+      def cleanup(docxml)
+        super
+        term_cleanup(docxml)
+      end
+
+      def term_cleanup(docxml)
+        docxml.xpath("//p[@class = 'Terms']").each do |d|
+          h2 = d.at("./preceding-sibling::*[@class = 'TermNum'][1]")
+          h2.add_child("&nbsp;")
+          h2.add_child(d.remove)
+        end
+        docxml
+      end
+
+      def info(isoxml, out)
+        @meta.url isoxml, out
+        super
+      end
+    end
+  end
+end
+

data/lib/isodoc/m3d/m3dhtmlrender.rb

@@ -0,0 +1,68 @@
+module IsoDoc
+  module M3d
+    # A {Converter} implementation that generates CSAND output, and a document
+    # schema encapsulation of the document for validation
+    class HtmlConvert < IsoDoc::HtmlConvert
+            def annex_name(annex, name, div)
+        div.h1 **{ class: "Annex" } do |t|
+          t << "#{get_anchors[annex['id']][:label]} "
+          t << "<b>#{name.text}</b>"
+        end
+      end
+
+      def annex_name_lbl(clause, num)
+        obl = l10n("(#{@inform_annex_lbl})")
+        obl = l10n("(#{@norm_annex_lbl})") if clause["obligation"] == "normative"
+        l10n("<b>#{@annex_lbl} #{num}</b> #{obl}")
+      end
+
+      def pre_parse(node, out)
+        out.pre node.text # content.gsub(/</, "&lt;").gsub(/>/, "&gt;")
+      end
+
+      def term_defs_boilerplate(div, source, term, preface)
+        if source.empty? && term.nil?
+          div << @no_terms_boilerplate
+        else
+          div << term_defs_boilerplate_cont(source, term)
+        end
+      end
+
+      def i18n_init(lang, script)
+        super
+        @annex_lbl = "Appendix"
+      end
+
+      def error_parse(node, out)
+        # catch elements not defined in ISO
+        case node.name
+        when "pre"
+          pre_parse(node, out)
+        when "keyword"
+          out.span node.text, **{ class: "keyword" }
+        else
+          super
+        end
+      end
+
+      def fileloc(loc)
+        File.join(File.dirname(__FILE__), loc)
+      end
+
+      def cleanup(docxml)
+        super
+        term_cleanup(docxml)
+      end
+
+      def term_cleanup(docxml)
+        docxml.xpath("//p[@class = 'Terms']").each do |d|
+          h2 = d.at("./preceding-sibling::*[@class = 'TermNum'][1]")
+          h2.add_child("&nbsp;")
+          h2.add_child(d.remove)
+        end
+        docxml
+      end
+    end
+  end
+end
+

data/lib/isodoc/m3d/m3dwordconvert.rb

@@ -0,0 +1,105 @@
+require "isodoc"
+require_relative "m3wordrender"
+require "fileutils"
+
+module IsoDoc
+  module M3d
+    # A {Converter} implementation that generates GB output, and a document
+    # schema encapsulation of the document for validation
+
+    class WordConvert < IsoDoc::WordConvert
+      def initialize(options)
+        @libdir = File.dirname(__FILE__)
+        super
+        #system "cp #{html_doc_path('logo.jpg')}  logo.jpg"
+        FileUtils.cp html_doc_path("logo.jpg"), "logo.jpg"
+      end
+
+      def default_fonts(options)
+        {
+          bodyfont: (options[:script] == "Hans" ? '"SimSun",serif' : '"Garamond",serif'),
+          headerfont: (options[:script] == "Hans" ? '"SimHei",sans-serif' : '"Garamond",serif'),
+          monospacefont: '"Courier New",monospace'
+        }
+      end
+
+      def default_file_locations(_options)
+        {
+          htmlstylesheet: html_doc_path("htmlstyle.scss"),
+          htmlcoverpage: html_doc_path("html_m3d_titlepage.html"),
+          htmlintropage: html_doc_path("html_m3d_intro.html"),
+          scripts: html_doc_path("scripts.html"),
+          wordstylesheet: html_doc_path("wordstyle.scss"),
+          standardstylesheet: html_doc_path("m3d.scss"),
+          header: html_doc_path("header.html"),
+          wordintropage: html_doc_path("word_m3d_intro.html"),
+          ulstyle: "l3",
+          olstyle: "l2",
+        }
+      end
+
+      def metadata_init(lang, script, labels)
+        @meta = Metadata.new(lang, script, labels)
+      end
+
+      def colophon(body, docxml)
+        section_break(body)
+        body.div **{ class: "colophon" } do |div|
+        end
+      end
+
+      def make_body(xml, docxml)
+        body_attr = { lang: "EN-US", link: "blue", vlink: "#954F72" }
+        xml.body **body_attr do |body|
+          make_body2(body, docxml)
+          make_body3(body, docxml)
+          colophon(body, docxml)
+        end
+      end
+
+      def make_body2(body, docxml)
+        body.div **{ class: "WordSection2" } do |div2|
+          info docxml, div2
+          div2.p { |p| p << "&nbsp;" } # placeholder
+        end
+        # body.br **{ clear: "all", style: "page-break-before:auto;mso-break-type:section-break;" }
+        # apparently that was not intended: enforce page break between ToC and body
+        section_break(body)
+      end
+
+      def title(isoxml, _out)
+        main = isoxml&.at(ns("//title[@language='en']"))&.text
+        set_metadata(:doctitle, main)
+      end
+
+      def generate_header(filename, dir)
+        return unless @header
+        template = Liquid::Template.parse(File.read(@header, encoding: "UTF-8"))
+        meta = @meta.get
+        meta[:filename] = filename
+        params = meta.map { |k, v| [k.to_s, v] }.to_h
+        File.open("header.html", "w") { |f| f.write(template.render(params)) }
+        @files_to_delete << "header.html"
+        "header.html"
+      end
+
+      def header_strip(h)
+        h = h.to_s.gsub(%r{<br/>}, " ").sub(/<\/?h[12][^>]*>/, "")
+        h1 = to_xhtml_fragment(h.dup)
+        h1.traverse do |x|
+          x.replace(" ") if x.name == "span" &&
+            /mso-tab-count/.match(x["style"])
+          x.remove if x.name == "span" && x["class"] == "MsoCommentReference"
+          x.remove if x.name == "a" && x["epub:type"] == "footnote"
+          x.replace(x.children) if x.name == "a"
+        end
+        from_xhtml(h1)
+      end
+
+      def info(isoxml, out)
+        @meta.url isoxml, out
+        super
+      end
+    end
+  end
+end

data/lib/isodoc/m3d/m3wordrender.rb

@@ -0,0 +1,68 @@
+module IsoDoc
+  module M3d
+    # A {Converter} implementation that generates CSAND output, and a document
+    # schema encapsulation of the document for validation
+    class WordConvert < IsoDoc::WordConvert
+            def annex_name(annex, name, div)
+        div.h1 **{ class: "Annex" } do |t|
+          t << "#{get_anchors[annex['id']][:label]} "
+          t << "<b>#{name.text}</b>"
+        end
+      end
+
+      def annex_name_lbl(clause, num)
+        obl = l10n("(#{@inform_annex_lbl})")
+        obl = l10n("(#{@norm_annex_lbl})") if clause["obligation"] == "normative"
+        l10n("<b>#{@annex_lbl} #{num}</b> #{obl}")
+      end
+
+      def pre_parse(node, out)
+        out.pre node.text # content.gsub(/</, "&lt;").gsub(/>/, "&gt;")
+      end
+
+      def term_defs_boilerplate(div, source, term, preface)
+        if source.empty? && term.nil?
+          div << @no_terms_boilerplate
+        else
+          div << term_defs_boilerplate_cont(source, term)
+        end
+      end
+
+      def i18n_init(lang, script)
+        super
+        @annex_lbl = "Appendix"
+      end
+
+      def error_parse(node, out)
+        # catch elements not defined in ISO
+        case node.name
+        when "pre"
+          pre_parse(node, out)
+        when "keyword"
+          out.span node.text, **{ class: "keyword" }
+        else
+          super
+        end
+      end
+
+      def fileloc(loc)
+        File.join(File.dirname(__FILE__), loc)
+      end
+
+      def cleanup(docxml)
+        super
+        term_cleanup(docxml)
+      end
+
+      def term_cleanup(docxml)
+        docxml.xpath("//p[@class = 'Terms']").each do |d|
+          h2 = d.at("./preceding-sibling::*[@class = 'TermNum'][1]")
+          h2.add_child("&nbsp;")
+          h2.add_child(d.remove)
+        end
+        docxml
+      end
+    end
+  end
+end
+

data/lib/isodoc/m3d/metadata.rb

@@ -0,0 +1,87 @@
+require "isodoc"
+
+module IsoDoc
+  module M3d
+    # A {Converter} implementation that generates CSAND output, and a document
+    # schema encapsulation of the document for validation
+    class Metadata < IsoDoc::Metadata
+      def initialize(lang, script, labels)
+        super
+        set(:status, "XXX")
+      end
+
+      def title(isoxml, _out)
+        main = isoxml&.at(ns("//title[@language='en']"))&.text
+        set(:doctitle, main)
+      end
+
+      def subtitle(_isoxml, _out)
+        nil
+      end
+
+      def author(isoxml, _out)
+        set(:tc, "XXXX")
+        tc = isoxml.at(ns("//editorialgroup/technical-committee"))
+        set(:tc, tc.text) if tc
+      end
+
+      def docid(isoxml, _out)
+        docnumber = isoxml.at(ns("//bibdata/docidentifier"))
+        docstatus = isoxml.at(ns("//bibdata/status"))
+        dn = docnumber&.text
+        if docstatus
+          set(:status, status_print(docstatus.text))
+          abbr = status_abbr(docstatus.text)
+          dn = "#{dn}(#{abbr})" unless abbr.empty?
+        end
+        set(:docnumber, dn)
+      end
+
+      def status_print(status)
+        status.split(/-/).map{ |w| w.capitalize }.join(" ")
+      end
+
+      def status_abbr(status)
+        case status
+        when "working-draft" then "wd"
+        when "committee-draft" then "cd"
+        when "draft-standard" then "d"
+        else
+          ""
+        end
+      end
+
+      def version(isoxml, _out)
+        super
+        revdate = get[:revdate]
+        set(:revdate_monthyear, monthyr(revdate))
+      end
+
+      MONTHS = {
+        "01": "January",
+        "02": "February",
+        "03": "March",
+        "04": "April",
+        "05": "May",
+        "06": "June",
+        "07": "July",
+        "08": "August",
+        "09": "September",
+        "10": "October",
+        "11": "November",
+        "12": "December",
+      }.freeze
+
+      def monthyr(isodate)
+        m = /(?<yr>\d\d\d\d)-(?<mo>\d\d)/.match isodate
+        return isodate unless m && m[:yr] && m[:mo]
+        return "#{MONTHS[m[:mo].to_sym]} #{m[:yr]}"
+      end
+
+      def url(isoxml, _out)
+        url = isoxml.at(ns("//bibdata/source"))
+        set(:url, url.text) if url
+      end
+    end
+  end
+end